gem_newdesign

Solar Predictive maintenance & power Business Study

gal.garniek@gembo.co — Thu, 12 Dec 2024 11:55:54 GMT

GEMBO ( www.gembo.co ) has a SaaS Industrial IOT Platform which provides enterprises and users with mission critical data, insights and decision making tools enabling cost reduction and revenue growth through optimization via the use of IoT, Artificial Intelligence and Machine Learning.

Farm Operator Intro

A large-scale solar farm operator, managing a 50 MW solar farm with significant investments in infrastructure. The solar farm has a current efficiency of 24% and a target of increasing this efficiency over time. The farm operates in an area where electricity prices are approximately $32 per MWh, and it has a large operational budget dedicated to maintaining its equipment.

GEM has deployed the Precare cloud, predictive maintenance and solar power prediction Package, on the customers Data, extracted from the solar farm's SCADA system.

Problem

Due to the complexity of solar equipment and environmental factors, the customer has faced a gradual decline in efficiency, dropping from 26% to 24% over the past few years. As a result, the farm's revenue has been impacted by lower power output, and operational expenses have been steadily increasing. Furthermore, the lack of predictive maintenance (PdM) has led to frequent downtime and unplanned maintenance, further increasing the inefficiencies.

The farm owner reached out for a solution that could improve operational efficiency, reduce costs, and enhance overall power production by using predictive analytics to forecast and mitigate potential issues before they occur.

Solution

After evaluating the farm’s needs and existing system, GEM’s Predictive Maintenance (PdM) and Solar Power Prediction packages were discussed and found as the right fit. This solution was implemented through GEM’s Precare analytics platform, which helps monitor and predict performance, detect faults early, and optimize maintenance schedules.

The key components of GEM’s solution included:

Real-time Monitoring: Continuous monitoring of solar inverters, panels, and environmental conditions.
Predictive Maintenance: Advanced machine learning models to predict the likelihood of system failures and performance degradation.
Power Output Forecasting: Predictive analytics to model expected energy production based on historical data and real-time inputs, leading to more accurate forecasting and optimizing grid management.

Results

After deploying GEM’s predictive maintenance and power optimization system, GEM provided the customer a calculation of a 3 year business analysis

Financial Benefits:

Revenue Increase: The system’s efficiency would increase by an additional $864,320 in revenue over 3 years due to the increased power output from the higher efficiency (25% vs. 24%).
OPEX Reduction: Predictive maintenance would reduce the monthly operational expenses by 3%, leading to OPEX savings of $78,810 over the 3-year period.
Net Benefits: The customer will realize a total net benefit of $758,130 after deducting the initial system cost and subscription fees.
ROI: The ROI of 658.13% was computed from the net benefits of $758,130 after accounting for system cost investments.

Figure 1: Comparative Analysis - Before vs After GEM Implementation

Operational Benefits:

Increased Efficiency: The system will help increase the solar farm's efficiency by 1% over the 3 years, avoiding the anticipated 3% decline.
Reduced Downtime: By predicting failures before they occurred, GEM’s PdM system will minimize unexpected downtime and reduce the need for costly emergency repairs.
Optimized Maintenance: The predictive maintenance feature will enable the customer to perform maintenance only when necessary, reducing the frequency of reactive maintenance and labor costs.

Figure 2: Comparative Analysis - Efficiency and Downtime over 3 years

Conclusion

By integrating GEM's Precare Platform, and applying Renewable Energy Predictive Maintenance and Power Prediction packages, the customer will see not only increase in operational efficiency but also experienced significant financial gains. The combination of proactive fault detection, predictive power forecasting, and optimized maintenance schedules enabled the customer to achieve higher energy production while reducing unnecessary costs.

This writeup highlights how predictive analytics can have a transformative impact on solar farm operations, ensuring long-term profitability and sustainability.

The 658.13% ROI demonstrates the clear value of adopting advanced predictive maintenance in the solar energy industry, showcasing both operational and financial improvements.

Self-Service Data Studio Case Study

gal.garniek@gembo.co — Fri, 15 Dec 2023 15:01:52 GMT

SELF SERVICE DATA STUDIO CASE STUDY

This case study showcases GEMBO, a leader in SaaS Industrial IoT Platforms, enhancing a global manufacturer's operations by deploying its Precare Data Studio BI product across 70 machines. The solution, focused on self-service data management and analytics, resulted in significant manpower savings, improved self-service efficiency, and automated analytics distribution. Unique to GEMBO Precare is its ability to deploy independent sensors, connecting any machine to its cloud, thereby offering predictive maintenance and operational insights without substantial capital expenditure, distinguishing it from other market solutions.

Ticketing System Case Study

gal.garniek@gembo.co — Tue, 08 Aug 2023 18:24:27 GMT

GEMBO ( www.gembo.co ) is a leading innovator in the world of SaaS Industrial IoT Platforms, with a proven track record of delivering cutting-edge solutions that help customers achieve their business goals. The company's platform uses a combination of IoT, machine learning, and AI to provide customers with real-time insights into their operations, enabling them to make better decisions and optimize their performance. GEMBO is committed to continuous innovation, and the company is constantly looking for new ways to use technology to help its customers succeed.

Customer Intro

The customer is a multi $B Tier one manufacturer, with multiple factories around the globe. Manufacturing lines vary between electronic manufacturing to semiconductor, serving a variety of markets including Automotive, Networking, Industrial, Audio and Gaming.

GEM has deployed Precare Cloud , Precare Edge , OEE Availability and predictive analytics Package . Its footprint grew from a few machines to over 90 machines in a few of their factories.

Problem

The customer has been utilizing OEE Availability analytics to identify machines with low availability and assigning them to responsible technicians. The customer's management team has been overwhelmed with emails from technicians providing status updates on the machines after they have taken corrective actions.

The customer intends to streamline the process of monitoring machine status from the receipt of OEE Availability status to the resolution of availability issues, enabling the machines to operate efficiently based on established availability KPIs. The customer has provided the following workflow to illustrate their requirements.

The customer expects that tickets will be automatically generated for all machines with availability lower than the established KPIs and sent to the responsible technicians. The technicians must ensure that appropriate corrective actions are implemented and updates are made to the tickets until the machines are fully repaired, at which point the tickets will be closed upon validation by the technicians' superiors.

Solution

Following the discussion with the customer, GEM suggested to perform the following in the existing OEE platform to properly execute the ticketing system:

Customer to establish OEE Availability KPIs by machines
Configure the Rules in the GEM Rule Engine
Generate the OEE Analytics per machine at a specified time daily
Define the calculation process comparing the availability status per machine vs. the established availability KPI per machine
Tickets will be triggered for all machines with lower availability vs. the established availability KPI
These tickets will be sent to the technicians handling the machines
Technicians will update the ticket once they have completed their corrective actions
Managers will validate the effectivity of their corrective actions by running the OEE availability of the said machine
Upon successful validation, managers will close the ticket
Execute the rules and monitor the implementation

Results

The ticketing system is now an integral part of the OEE Platform, with rules set up in the Rule Engine based on the customer's workflow. The rules are designed to automate the process of generating and tracking tickets, ensuring that all tickets are properly classified and routed to the appropriate personnel. The ticketing system also includes a knowledge base of troubleshooting guidelines, which can be accessed by technicians to quickly resolve issues.

GEM and the customer are working to deploy the ticketing system and ensure it is aligned with the customer's requirements. This includes configuring the system to meet the customer's specific workflow, as well as training the customer's personnel on how to use the system.

The ticketing system will help the customer improve machine availability by providing a centralized repository for all machine-related issues. This will allow the customer to quickly identify and resolve issues that affect uptime, saving them money on maintenance costs.

Conclusions

GEMBO Precare has a set of powerful data acquisition, analytics, predictive and OEE tools for manufacturing equipment. GEMBO Precare compiles critical KPIs that can be used to easily trace back which machine or machine subsystem is responsible for a low KPI score. GEMBO Precare is also able to make predictions at equal or better than humanly possible for machine maintenance to be scheduled before a failure occurs. But most importantly, unlike other market solutions, GEMBO Precare is able to deploy its own sensors independently from any machine controller and fully connect any machine data island to the GEMBO Precare Cloud at a fraction of the cost of a new machine; hence, saving manufacturers from having to make large and risky CAPEX and OPEX investments for new machines.

Visit us at www.gembo.co or contact us via email at sales@gembo.co

Digital Transformation of Reporting Case Study

gal.garniek@gembo.co — Thu, 27 Jul 2023 06:16:02 GMT

Customer Intro

The customer is a Tier 1 multi-billion dollar global manufacturing leader in the power, discrete semiconductor, and passive electronic components (PES) space. GEMBO has deployed a suite of innovative, cloud-based solutions to the customer, including Precare Cloud, Precare Edge, OEE Availability, Performance, and Quality packages. These solutions have been deployed to 70 machines across two factory floors, and the customer intends to scale the deployment across their entire Asia-Pacific footprint.

Problem

The customer's equipment engineering team has been managing the productivity of their machines through manual Excel reports. These reports are prepared by machine operators, checked and consolidated by supervisors, and then reported to management by factory floor managers. The customer needs to minimize or eliminate these manual reports to improve the accuracy of the reports and save on manpower costs.

The following are examples of manual reports that the customer needs to eliminate:

1. Calculation of the share of subcategories of Performance and Quality

2. Calculation of the percentage of Planned Downtime to Total Run Time

3. Graphical presentation of OEE Availability with Time Frame

These reports are time-consuming and error-prone. They also require a significant amount of manpower to create and maintain. By eliminating these manual reports, the customer can improve the accuracy of their productivity data and save on manpower costs.

Solution

After a technical discussion with the customer, GEM integrated the manual Excel reports into the OEE analytics framework. The team then implemented the following process:

Define the customer requirements
Gather the excel reports
Create an output image showing changes in the analytics
Define data to be collected
Collect data from the customers
Collect the data from customer
Validate the completeness of the data based on the requirements
Collect missing data
Confirm with customer if all data are accurate and structured properly based on their requirements
Prepare the design
Overview
Customer Requirements
Use Case
System Diagram
Code Diagram
Review and approval of the design
Testing on Developer Environment
Deployment to Production
Customer acceptance

Results

The migration of previously manually prepared OEE reports to a digital format using OEE Analytics resulted in the following benefits:

100% savings on manpower costs, as the reports are now generated automatically and do not require manual input.
100% accuracy, as the data is collected directly from the machines and is not subject to human error.
100% time savings for management, as they no longer need to spend time reviewing and validating the reports.
Improved decision-making, as the Operations Group can now access real-time data and insights to make better decisions.
Increased efficiency, as the Operations Group can now focus on core tasks and not on data entry and reporting.

Conclusions

Visit us at www.gembo.co or contact us via email at sales@gembo.co

GEM Precare Case Study: Predictive Analytics

gal.garniek@gembo.co — Mon, 12 Jun 2023 22:41:10 GMT

How did GEMBO Precare enable increased uptime and improved productivity by accurate predictions?

Key Benefits

End to end generic workflow for failure prediction
Increase of of uptime and OEE availability for by 10s of Percentage via predictive maintenance
Reduction of Operating Expense (Opex) on maintenance personnel
Reduction of Capital expense (Capex) on parts
Increased Productivity

About the client

Problem statement

Due to an elevated downtime at the back end test floor, with multiple of their handles, the customers reached out to GEM, asking for assistance. After analyzing the data (part of GEM Data Analyst Services) GEM identified a few top failures, impacting downtime the most. For example, a top failure event in their “S” (abstracting the vendor name) Handlers had been related to device drop error. The Pick up arm lifts the device but before it puts the socket into the shuttle it drops the device. If this happens, the operator stops the machine and calls the supervisor and if there is a device in the socket, he calls the maintenance who will remove the hardware and the operator redoes the complete lot. This type of failure drastically impacts productivity: impacts the OEE Availability with the resulting unplanned downtime and OEE Quality which is inaccurate since the rerun is not based on a defective device.

The customer expected to have a trending, modeling and predictions. Together with GEM, customer intends to establish a threshold which will trigger tickets with corrective actions for the maintenance team. The team should see to it that the trend will improve over time.

The solution

The client learned about the GEM Precare Cloud solution, which provides real-time ML and AI-based insights into the equipment's overall efficiency so that corrective steps can be made to improve overall equipment effectiveness and service quality. The solution incorporates connection and big data analytics into Industry 4.0 digital twins of equipment, such as turbines, generators, engines, and infrastructure in general, to improve overall equipment efficiency via real-time and predictive analytics.

To allow smooth deployment of the Data product into Precare ML/ AI workflow, GEM performed initial data analysis, around time and frequency of the failure across machines, verified results with the customer subject matter expert and execute a complete process:

Extract Trend
Split trend into train-test
Model Training on train data
Create Result Data/Predictions (2 weeks into the future)
Model Evaluation
Model Selection (best one)

Deployment of solution

Based on the evaluation of the performance of various prediction models GEM selected a model and deployed into its AI ML framework to the following components:

Precare Cloud (Cloud Edition): To perform machine data aggregation and storage, training and validation of machine learning models for machine vision and predictive maintenance, computation of KPIs, and display of data on dashboards
Precare Edge (Cloud Edition): To perform complex edge processing of machine digital twin data in real-time for latency-sensitive tasks, such as status and alarm notifications, as well as machine vision
AI/ML and Predictive Analytics Packages/ Data product: To provide increased equipment productivity through just-in-time maintenance scheduling

Key Results

Based on the evaluation of the performance of various prediction models GEM selected a model and deployed into its AI ML framework.

GEM successfully showed that the accuracy or the gap between the predicted and actual data is over 96%, which means that the customer can now accurately predict a future failure.

GEM and the customer are now working to deploy this on GEM out of the box Predictive analytics workflow allowing not only predicting future failure gradient increase, but also enabling a ticket to be automatically raised against the machine owner, triggering predictive maintenance job on the machines for this type of failure.

Conclusion

Equipped with Unique Artificial Intelligence and Machine learning, GEM Precare SaaS Predictive Analytics Industrial IOT Platform Is stronger than ever. GEM real-time & Predictive analytics are top of the lines in the Semiconductor, Electronic Manufacturing, and Automotive. GEM enables any customer user, from executive to machine operator, to get critical operational analytics insight, allowing them to take predictive actions. GEM Agents are able to take full advantage of the hardware they run on for complex event processing at the edge rather than in the cloud. It allows real-time remote monitoring and visualization via the cloud of critical parameters and signals with notifications for alarms and other events. This significantly helps manufacturing organizations reduce latency for time-critical monitoring and control applications.

GEM Precare Case Study: Heavy Manufacturing

gal.garniek@gembo.co — Tue, 17 May 2022 16:16:31 GMT

How did GEMBO Precare help create end-to-end generic workflows for Remaining Useful Life and provide accurate predictions?

Key Benefits

End to end generic workflow for Remaining Useful Life
Increase of useful life by 10s of Percentage via predictive maintenance
Reduction of Operating Expense (Opex) on maintenance personnel
Reduction of Capital expense (Capex) on parts
Increased Productivity

About the client

The client is one of the agencies of the US government. The client specializes and in charge of the manufacturing of massive energy production. The client was using in-house manufacturing execution systems and products from competitors.

Problem statement

While being a government agency and a leading name in massive energy production, its operations and maintenance were heavily relying on manual work. A major pain point was older machinery, lack of efficient digital communication, lack of embedded sensors, and ability to move from reactive to predictive operations. The client had no way to predict failures nor RUL (Remaining Useful Life) of the machines, hence, no accurate way to track the degrading efficiency and productivity. The client was in urgent need of an immediate yet effective solution that can scale across types of products.

The solution

Deployment of solution

The solution deployment started in 2019 with the following products:

Precare Cloud (Cloud Edition): To perform machine data aggregation and storage, training and validation of machine learning models for machine vision and predictive maintenance, computation of KPIs, and display of data on dashboards
Precare Edge (Cloud Edition): To perform complex edge processing of machine digital twin data in real-time for latency-sensitive tasks, such as status and alarm notifications, as well as machine vision
AI/ML and Predictive Analytics Packages/ Data product: To provide increased equipment productivity through just-in-time maintenance scheduling

GEM started the deployment of the solution using its machine onboarding and analytics frameworks. The company started the deployment with 1 virtual factory floor and 2 machines. GEM tested and trained the AI and ML models and deployed the models followed by documenting them.

Key Results

With the deployment of the GEM Cloud, Edge, and AI/ML package solution, the client observed tangible and immediate benefits. The client was provided with end-to-end generic workflows for RUL of the machinery by collecting data and preprocessing it through GEM’s efficient AI/ML algorithms. Additionally, the client was also provided with approaches for accurately predicting the RUL for the machinery they were running.

Additionally, the following benefits were also observed:

Maximum returns on investment in machinery
Minimum production losses and greater competitiveness
Rapid improvement in machine performance
Minimized repetition and defective products which eventually adds considerably to the cost savings
Quantification of production efficiency which provides precise insight into the operations process
Reduced machinery and repair costs
Increased equipment productivity through just-in-time maintenance scheduling

Conclusion

Today, the GEM Precare SaaS Predictive Analytics Industrial IOT Platform Is stronger than ever. GEM real-time & Predictive analytics are top of the lines in the Semiconductor, Electronic Manufacturing, and Automotive. GEM enables any customer user, from executive to machine operator, to get critical operational analytics insight, allowing them to take predictive actions. GEM Agents are able to take full advantage of the hardware they run on for complex event processing at the edge rather than in the cloud. It allows real-time remote monitoring and visualization via the cloud of critical parameters and signals with notifications for alarms and other events. This significantly helps manufacturing organizations reduce latency for time-critical monitoring and control applications.

GEM Precare Case Study: Semiconductor Manufacturing

gal.garniek@gembo.co — Tue, 10 May 2022 03:23:14 GMT

Key Benefits

24% improvement in availability
10% improvement in annual performance
5% increase in energy cost savings
7% increase in revenue

About the client

The client is a tier 1 semi-product and factory owner having multiple factories worldwide and a market cap of over $3B. The client specializes in the manufacturing of power, discrete semiconductor, and passive electronic components and owns multiple machines for this purpose. The client was using Applied Materials manufacturing execution systems, Nation Instruments’ OptimalPlus+, and machine OEM (Original Equipment Manufacturer) for their standard manufacturing requirements, such as collection, cleaning, and aggregation of data from multiple manufacturing locations, its analysis, and mining for coherent information.

Problem statement

While this investment in continuous improvement using high-quality legacy machines sets the client apart from its competitors, it also required heavy manual work. Digital OEE (overall equipment effectiveness) and Predictive Maintenance is one of the best measurements you can use to optimize production operations, lacking this was preventing the client from improving its production operations. Lacking digital, and having partial human data collection, the client was unable to identify losses, track and benchmark progress, and optimize the productivity of manufacturing equipment. Additionally, the client was facing issues like human erroneous data, and limitations of its own solution.

The solution

The client learned about the GEM Precare SaaS Predictive Analytics Industrial IoT Platform, which enables manufacturers to make an almost seamless transition to Industry 4.0 while maintaining their legacy machine investments, allowing them to take advantage of the potential of real-time access to machine data to improve efficiency, productivity, and quality.

The solution deployment started in 2019 with the following products:

Precare Cloud (On-Premise Edition) : To perform machine data aggregation and storage, training and validation of machine learning models for machine vision and predictive maintenance, computation of KPIs, and display of data on dashboards
Precare Edge: To perform complex edge processing of machine digital twin data in real-time for latency-sensitive tasks, such as status and alarm notifications, as well as machine vision
OEE Availability, Performance, and Quality Packages: To gain important insights on how to efficiently improve your manufacturing process

GEM started the deployment of the solution using its machine onboarding and OEE frameworks. The company started the deployment on 1 floor with a few machines, and gradually expanded to more machines across the floor, then to a second floor totaling over 80 machines. The customer and GEM are now engaging in discussion regarding further floors and factories in the Philippines, Taiwan, and more.

Key Results

With the deployment of the OEE availability, performance, and quality package solution, the client observed tangible and immediate benefits. The client observed more than a 24% improvement in availability, 10% improvement in yearly performance improvements, a 5% increase in energy cost savings, and an overall more than 7% increase in revenues.

Additionally, the following benefits were also observed:

Maximum returns on investment in machinery
Minimum production losses and greater competitiveness
Rapid improvement in machine performance
Minimized repetition and defective products eventually add considerably to the cost savings
Quantification of production efficiency which provides precise insight into the operations process
Reduced machinery and repair costs
Improved efficiency of manufacturing plants

Conclusion

Today, the GEM Precare SaaS Predictive Analytics Industrial IOT Platform Is stronger than ever. GEM real-time & Predictive analytics are top of the lines in the Semiconductor, Electronic Manufacturing, and Automotive. GEM enables any customer user, from executive to machine operator, to get critical operational analytics insight, allowing them to take predictive actions. GEM Agents are able to take full advantage of the hardware they run on for complex event processing at the edge rather than in the cloud. It allows real-time remote monitoring and visualisation via the cloud of critical parameters and signals with notifications for alarms and other events. This significantly helps manufacturing organisations reduce latency for time-critical monitoring and control applications.

How did GEMBO Precare boost availability, cost-saving, and revenue

gal.garniek@gembo.co — Tue, 26 Apr 2022 03:25:27 GMT

Key Benefits

20% improvement in availability
70% new product introduction analytics
10% increase in energy cost savings
15% increase in revenue

About the client

The client is a tier 1 Electronics + IC factory owner having multiple factories worldwide and a market cap of $31B. The client specialises in the manufacturing of network components and owns multiple machines. The client was using in-house manufacturing execution systems, SAP+, and machine OEM (Original Equipment Manufacturer) for their standard manufacturing requirements, such as packaging machines, material handling systems, or units.

Business Need

While this investment in high-quality products and processes is what sets the client apart from its competitors, its lines are combination machines and heavy manual work. Manufacturing, like other industries, has suffered from data silos, which exist not only within the business but also at distinct levels, including but not limited to the machine level, the plant level, or the corporate level. Traditional manufacturing methods lead to more downtime, compromised throughput, and overall, higher cost of supplying quality parts. Additionally, the client was facing issues like lack of coverage, human erroneous data, and overall slowness of its own solution.

Failing to shift to the technology of the Fourth Industrial Revolution was causing the client to fall behind, as their operations were not digitised enough to match competitors.

The Solution

The client learned about the GEM Precare SaaS Predictive Analytics Industrial IOT Platform , which enables manufacturers to Optimise their downtime, predict downtime, reduce carbon footprint, and improve productivity and revenue, as they make an almost seamless transition to Industry 4.0 while maintaining their legacy machine investments. Using Real-time & Predictive Analytics, GEM Precare allow them to take advantage of the potential of real-time access to machine data to improve efficiency, productivity, and quality.

The solution deployment begin in 2018 with the following products:

Precare Cloud (Cloud Edition): To perform machine data aggregation and storage, training and validation of machine learning models for machine vision and predictive maintenance, computation of KPIs, and display of data on dashboards
Precare Edge: To perform complex edge processing of machine digital twin data in real-time for latency-sensitive tasks, such as status and alarm notifications, as well as machine vision
OEE Availability Package: To efficiently monitor and track the effectiveness of the manufacturing process

GEM started the deployment of the solution using our machine onboarding and OEE frameworks. We started with 1 area having 4 machines and at present, there are 4 areas with approximately 70 machines. The client has already proposed the plan to go to up to 700 machines.

Key Results

With the deployment of the solution, the client observed tangible and immediate benefits. The client observed more than a 20% improvement in availability, more than 70% new product introduction analytics, a 10% increase in energy cost savings, and an overall more than 15% increase in revenues.

Additionally, the following benefits were also observed:

Support for a large set of manufacturing equipment for instant time-to-big-data
Flexibility to configure and execute any complex condition and set of actions in real-time
Machine data acquisition without the need for physical connectivity
Up-to-date KPIs, statuses, and alarms to on-site and off-site personnel
Ability to constantly update machine learning model parameters
Flexibility to address rule-based actions for any desired combination of parameters and conditions
Instant and uncluttered information of KPIs, statuses, and alarms
Real-time compilation of important KPIs at any level

Conclusion

Today, the GEM Precare SaaS Predictive Analytics Industrial IOT Platform Is stronger than ever. GEM Realtime & Predictive analytics enable any customer user, from executive to machine operator, to get critical operational analytics insight. GEM Agents are able to take full advantage of the hardware they run on for complex event processing at the edge rather than in the cloud. It allows real-time remote monitoring and visualisation via the cloud of critical parameters and signals with notifications for alarms and other events. This significantly helps manufacturing organisations reduce latency for time-critical monitoring and control applications.

Predictive Maintenance: what it is and how is it transforming manufacturing?

Wed, 30 Mar 2022 08:32:00 GMT

Predictive maintenance uses real-time data collected via the Industrial Internet of Things (IIoT) platforms to continuously analyze the machine's condition as it operates normally so that any sudden and unexpected failure can be avoided. It allows organizations to monitor and check the status of indicators like lubricants, speed, and bearing speed. These tools detect any abnormal behavior when the machine is operating normally and immediately send the report to the owner of the machine so that any potential incident can be avoided. The body content of your post goes here. To edit this text, click on it and delete this default text and start typing your own or paste your own from a different source.

In simpler terms, predictive maintenance analyzes and monitors the health of an asset in real-time and reports abnormalities to the owner in real-time to avoid any potential failure, breakdowns, and so on. It also offers the manufacturer an option to plan maintenance as per their production schedule. agraph

Working of predictive maintenance

Predictive maintenance works in the following ways:

Digital status analytics: Mining of machine digital repositories, understanding the meaning of statuses, and using those together with Machine learning, digital rein, and Artificial Intelligence to predict specific failures. This is specificity important for more expensive, critical, and complex machines.

Infrared analysis: Infrared analysis uses the temperature of the machine as an indicator of the problem. Abnormalities related to airflow, cooling, and motor stress can be identified using this method.

Vibration analysis: Vibration analysis is one of the most common predictive maintenance methods used in plants with rotating machinery. Abnormalities related to balance, alignment, loose parts, etc can be detected via this method.

Sonic acoustical analysis: This method uses sound converted into auditory or visual signals to detect problems like under-lubrication in both low and high rotating machinery.

How is predictive maintenance different from preventive maintenance?

Preventive maintenance:

It occurs at regular time intervals depending on the lifecycle of the machine, irrespective of its usage, to prevent any issues.

Predictive maintenance:

It occurs only as needed based on the reports provided by the IoT sensors regarding the status of the machine. This allows manufacturers to schedule maintenance to avoid any sudden unexpected potential breakdowns or failures.

How is predictive maintenance different from condition-based maintenance?

Condition-based maintenance

This type of proactive maintenance uses sensors to collect real-time insights about a piece of machine based on various factors like temperature, vibration, and pressure. In this case, the service is only deployed when the machine conditions demand. This type of maintenance includes a risk of multiple machines needing service simultaneously.

Predictive maintenance

Predictive maintenance is a type of condition-based maintenance, but it uses IIoT sensors at a larger scale to gain continuous insights into the machine's condition. Along with the equipment condition insights, it also uses big data methodologies to predict the machine degradation depending on the history of the equipment. It allows technicians to detect potential issues beforehand to avoid any potential issues and schedule maintenance more efficiently.

Key benefits of predictive maintenance

Here are the top five benefits predictive maintenance offers your organization:

Minimized downtime
Predictive maintenance alerts technicians of any potential issues in advance so that they can take action upon them beforehand and avoid any unexpected failure of breakdowns. This reduces the downtime by as much as 30%, avoids disruptions that damage brand reputation, and allows you to schedule multiple service procedures.

Better productivity
As there are minimal disruptions due to unexpected malfunction or breakdown, the productivity is optimized. The service time-to-resolution is 83% faster, no productive lags are there, maximum uptime is achieved, and asset usage improves.

Lower field service costs
Pre-planned maintenance saves major costs to service departments by minimizing service truck rolls, better first-time fix rates, and optimized maintenance costs.

Improved product design
The equipment data collected via the IIoT sensors allows product designers to increase equipment life spans, enhance product durability and reliability, and build more efficient machines in the future.

Enhanced worker safety
By predicting and resolving the chances of an unexpected potential failure, you can ensure that no employees are working near machinery that is at risk of a potential malfunction. The service to the machine can be provided before it becomes hazardous..

Implementing predictive maintenance

Follow these steps to start with your predictive maintenance. There are several ways to do it:

Option 1: Do it yourself:

Program design

Acquire permissions from your senior management
Outline the advantages of the predictive maintenance
List out equipment with a history of high failure rates along with its causes

IIoT installation
You can use machines having sensors, connected to an IIoT platform to conduct predictive maintenance.

System integration

Use IIoT tools to implement predictive maintenance. The connectivity established by IIoT based condition monitoring can be used to enhance efficiency using analytics, automation, and integration between OT and IT.

Schedule maintenance
Your team is equipped with advanced real-time alerts about equipment insights for scheduling service delivery and coordinating maintenance.

Option 2: accelerate with the combined platform and data science:

Factory and machine survey: analyze all sources of data and identify critical ones
Onboard machines: use iiot platform with already support for the functionality: from data collection to prediction.
Focus on what’s important: data science and modeling: Avoid expensive timely and risky data integration: the platform will make data concerted for information to your data scientist or subject matter expert.
Deploy and periodically train: deploy the model and utilize the platform user interface, alarms, and dashboard to manage your predictive Maintenance operations.

Use predictive maintenance and stand apart from the competition

The ultimate and numerous benefits of predictive maintenance will provide you an edge over your competitors. Don’t face the risk of downtime and its associated hurdles. Be proactive with your plan and service delivery using predictive maintenance.

FIGHTING CLIMATE CHANGE WITH GREEN MANUFACTURING

Wed, 02 Mar 2022 06:52:30 GMT

APPROACHING GLOBAL SUSTAINABILITY BY INCREASING ENERGY EFFICIENCY

ABSTRACT

To achieve global sustainability, we need to become more mindful about the usage of limited energy resources, or it is mandatory to bring focus, primarily, on energy efficiency. Energy optimization requires lessening energy consumption. To consume only required energy and cut out unnecessary energy loss, optimizing appliances is the first step.

Analytics show that we can save 34% of global energy consumption by incorporating green manufacturing techniques and tools. Energy optimization is attainable, and so is energy efficiency. The advanced technologies assist in optimizing tools by tracking the big data and by keeping schedules of maintenance to help us be regular with inspections of appliances. With the help of digitalization, it becomes easy to choose the most efficient machine or do the daily work with the functioning that requires fewer energy resources than others.

Investing in commercially available technologies is a profound way to reach closer to the desired outcome. Plus, incorporating green manufacturing in industries is proven to be cost-effective. It is to build globally sustainable and profitable industrial plants.

GEM provides best-in-industry end-to-end IIoT real-time Infrastructure analytics, predictive analytics, OEE, and Energy Optimization solutions for manufacturing industries, empowering production processes that pollute less and creating less overall production waste, reducing manufacturing carbon footprint.

From scheduling maintenance of machines to having advanced digitalization tools for tracking and monitoring big data, GEM works with a mission to achieve optimization with IloT and machine learning.

In pursuing constant growth, industries need to embody a plan to work with climate change and not against it. Studies show that industries consume 54% of the world’s accessible energy, so we hold an ensuing duty to improve energy efficiency to our highest potential. It is crucial to balance the improper ratio of increased production and limited energy resources for not letting the scenarios cease industrial growth especially when it is possible to save 34% of the global energy consumption. Although we do not have any control over increasing production demand, we can be more careful and strategic about energy usage. Once we become aware of the energy levels we utilize every day and get more organized with the data, We then can incorporate and develop specific green manufacturing technologies and tools to increase energy efficiency.

We can decide to minimize the usage of energy resources, and at the same time, not compromise the quality of the production. For this, we need to invest in more energy-efficient machines. The measures of required energy levels and resources vary with different machines. Some of the devices require an extra bulk of particular energy resources such as water or gas than others. Similarly, a single modern machine has several functioning modes, and each demands different energy levels. Now how to make sure that we are working with more efficient machines only? Advanced technologies and analytic tools display the required energy usage for different functions that helps determine the most efficient function of a particular machine. Eventually, it is a massive help to manufacturers and buyers as the decision-making process now becomes faster and less complex.

Profound energy management is required to have a reliable layout to increase energy efficiency. digitalization plays a significant role in that. It makes the procedure of choosing the most efficient tool transparent and simpler. The monitoring software tracks big data and required energy usage, which helps us compare the efficiency of one machine with another in a more standardized way. To consistently work with optimized tools, regular and frequent technical checkups are necessary. Monthly scheduling for regular machine checkups can save a million kilowatts of leakage of CO2. Using optimized machines is getting the same work done with fewer energy resources.

Limiting oneself to not using more than a certain amount of energy for production is challenging in a good way: when one is forced to find more profound ways to optimize more energy, the best way to do that is by making investments in commercially available technologies that intend to improve energy efficiency. It is a potent step in becoming more sustainable because by using these technologies and services, we are choosing to work with the most optimized tools every day, and investments in technologies and innovations that boost energy efficiency contribute to achieving global sustainability by increasing 10-30 % energy efficiency.

The adoption of green manufacturing reduces the cost of production with increased energy efficiency. Research shows that as industries spend 10-30% of the cost of production on energy, and by reducing energy consumption, large cost optimizations are achieved. Industries with higher energy consumption should be laser-focused on energy efficiency. Moreover, Smart investments we make in buying, using, or losing energy helps with savings that later can be invested in obtaining higher energy optimization.

To pursue the overall efficiency of equipment, the GEM Precare platform gives valuable analytics-based insights, right actions for achieving desired energy efficiency. GEM Precare platform Energy Analytics Package allows for simple yet deep insights, which in turn yield profits with low investments, eventually helping in outlining a solid plan to obtain the overall energy efficiency of a manufacturing line, floor, plan, and corporation. GEM SaaS platform, Precare, provides historical, Current, and using ML&AI for Predictive analytics.

For optimizing energy levels, GEM offers just-in-time and predictive maintenance scheduling to be consistent and organized with technical checkups. Using advanced digitalization tools, it also gives access to hierarchical dashboards that assist in displaying statuses and KPIs at any corporation level. By applying big data analytics, combines with loT and machine learning, GEM improves equipment effectiveness all across: Availability, performance, and quality. Utilizing modern and standardized tools, GEMBO helps users and enterprises achieve desired energy efficiency and global sustainability.

GEMBO IIoT Agent Running on Intel Hardware

Sun, 27 Feb 2022 00:54:31 GMT

INTRODUCTION

The GEMBO PRECARE platform enables manufacturers to seamlessly make the transition to Industry 4.0 literally overnight, while keeping their investments in legacy machines; thus, being able to tap into the potential of real-time access to machine data in order to improve efficiency, productivity and quality.

Real-time access to machine data can be through any combination of sensors, serial and parallel port interfaces, Ethernet and sensors, no matter where the data is originating from, i.e., directly from the machine, or indirectly from a PLC or a data store on a network. Complex event process control at the edge of the cloud or at the machine itself requires hardware platforms with adequate processing power. GEMBO Precare supports edge processing through the use of powerful software agents. These agents take full advantage of the capabilities of the underlying hardware.

In this white paper we show how the GEMBO Precare Industry 4.0 IoT platform takes advantage of Intel® x86 processor and Intel® Altera® Cyclone V SoC FPGA hardware capabilities to implement process monitoring and control at the edge in an industrial flow control application.

GEMBO PRECARE MOTOR CONTROL AGENT

Motors used in machines and production processes are very common and the ability to monitor them in real-time is understandably of crucial importance. GEMBO has developed an end-to-end motor control and monitoring solution in collaboration with Intel® and B&R Automation®, which takes advantage of the versatile and powerful GEMBO Agents for CEP at the edge and the GEMBO Precare cloud platform for monitoring and predictive maintenance. The process diagram shown below depicts a flow control application example. Control of a pump controls the flow rate in a pipe, and a safety valve prevents overpressure inside the pipe.

The critical parameters that are controlled in this setup for the pipe are pressure, flow rate and flow path. The latter is controlled by a safety valve. For the pump these critical parameters are the pump’s motor temperature, RPM, current consumption, vibration and acoustic noise. Pipe pressure and flow rate are directly influenced by the RPM of the pump’s motor.

The system diagram for the monitoring of these parameters and controlling the motor and the safety valve is shown below.

A PCIe add-on card with an Intel® Cyclone V SoC FPGA performs the actual motor control and sensing of motor current consumption, RPM and temperature. An X20CP PLC from B&R Automation monitors vibration and acoustic noise. An Intel® Skylake x86-based computer runs the GEMBO Agent and provides the communication link over Ethernet with the GEMBO PRECARE platform running in the cloud. This computer functions at the same time as a gateway and communicates over Ethernet with the B&R Automation® X20CP PLC.

A GEMBO Agent runs on the embedded ARM processor in the Cyclone V FPGA, collecting the motor parameters. Another GEMBO Agent runs in OPC UA client mode on the computer based on the Intel® Skylake CPU. This agent collects the sensor data coming from the GEMBO Agent on the FPGA and from the B&R Automation® X20CP PLC. This PLC runs in OPC UA server mode. The OPC UA client/server model adds the benefit that all communication between the different entities in the network conform to open industry standards.

GEMBO PRECARE MOTOR CONTROL DASHBOARD

The GEMBO PRECARE dashboard is shown below. The dashboard uses gauge widgets to present the pipe pressure and flow, as well as the pump’s motor temperature in real-time. Pump motor RPM and current consumption, as well as the pump motor vibration and acoustic noise are shown in real-time in graph widgets. The safety valve status is displayed by a “traffic light” widget, which switches on the corresponding light when the valve is open or closed.

The complex event processing (CEP) rules implemented for the control of the motor are as follows:

If motor temperature exceeds temperature threshold level 1 and motor RPM exceeds RPM threshold, then the GEMBO Agent will start reducing the RPM; the GEMBO PRECARE platform will display a high temperature alarm and the action undertaken by the GEMBO Agent to prevent a catastrophic failure, until the temperature has dropped again below temperature threshold level 1.
If motor temperature exceeds temperature threshold level 2 and motor RPM exceed RPM threshold, then the GEMBO Agent will immediately reduce the motor RPM to zero and simultaneously open the safety valve to relieve pressure in the pipe; the GEMBO PRECARE platform will display a catastrophic high temperature alarm and the action undertaken by the GEMBO Agent, until the temperature has dropped again below temperature threshold level 1.
If motor RPM exceeds RPM threshold and pipe pressure exceeds pressure threshold 1, then the GEMBO Agent will start reducing the RPM; the GEMBO PRECARE platform will display a high pressure alarm and the action undertaken by the GEMBO Agent to prevent a catastrophic failure, until the pressure has dropped again below pressure threshold level 1.
If motor RPM exceeds RPM threshold and pipe pressure exceeds pressure threshold 2, then the GEMBO Agent will immediately reduce the motor RPM to zero; the GEMBO PRECARE platform will display a catastrophic high pressure alarm and the action undertaken by the GEMBO Agent, until the pressure has dropped again below pressure threshold level 1.

The above illustrates the power and advantage of the GEMBO Agent in order to execute edge CEP for time-critical monitoring and control. This allows the GEMBO Agent to take immediate action and do so autonomously rather than under control of GEMBO PRECARE.

The same motor control instance can be repeated many times in a large plant with multiple motors and safety valves, such as in a distillery for instance. Each instance is connected via the GEMBO Agents to the GEMBO PRECARE platform. Whereas the GEMBO Agents perform control and CEP at the edge, the GEMBO PRECARE platform is fed data from all motor control instances in the plant, allowing it to present a dashboard for each instance, calculate OEE, MTBF and MTBA for each instance as well as for the entire plant, and analyze the monitored signals to create predictive maintenance models.

CONCLUSIONS

GEMBO Agents are able to take full advantage of the hardware they run on for complex event processing at the edge rather than in the cloud. This includes optimal use of the compute power available on Intel® x86 CPUs and the application specific circuits programmed into Intel® Altera® Cyclone V FPGAs. Such capability reduces latency for time-critical monitoring and control applications, such as for a complex system of motor and valve as illustrated here. Furthermore, GEMBO Agents support the OPC UA client/server model for interoperability with modern PLCs. And finally, GEMBO Precare allows real-time remote monitoring and visualization via the cloud of critical parameters and signals with notifications for alarms and other events.

Industry 4.0 Benefits Without Industry 4.0 Costs

Sun, 27 Feb 2022 00:51:53 GMT

The Customer

Semiconductor manufacturers are constantly under pressure to squeeze the most out of their capital and operational expenses, while at the same time facing tremendous pressure in a global market from their customers to deliver the highest quality within the shortest lead time.

Whereas COOs are held responsible for CapEx, OpEx and overall performance across all manufacturing sites and business units, VPs at each business unit are responsible for CapEx, OpEx and overall performance of their own business unit, while factory floor directors are responsible for manufacturing operations at their plants to run as efficiently and productive as possible. In concrete terms this means minimizing unplanned machine downtime and maximizing machine throughput, while keeping manufacturing quality high; or in industry parlance, maximizing OEE (Overall Equipment Effectiveness).

The Challenge

Maximizing OEE in semiconductor manufacturing is a non-trivial task. The manufacturing workflow involves multiple stages; each handled by machines specialized for the particular operations involved in a stage. It is not uncommon to find machines from different OEMs handling the same or different tasks on the manufacturing floor, where some machines may be controlled by older generation Operating Systems (some with none), PLCs (Programmable Logic Controllers) that don’t have the ability to provide machine status, performance, quality and availability data in real-time to spot trends to predict when maintenance needs to be scheduled and optimize equipment effectiveness.

This situation includes having no access at all to data for analysis and having access, but having to import the data in batch mode, missing crucial data. In addition, where the data is available, it is often in formats that differ from machine to machine, and more often than not, in formats incompatible with prevalent IIoT formats, such as JSON, XML, etc. To top it all off, a plethora of different communication protocols, ranging from SECS/GEMBO , SCADA and RS232/485 to various flavors of Industrial Ethernet compound the problem of access to data for analytics even further.

As a consequence all stakeholders, from factory floor to corporate office, don’t have access to crucial data to help them make well-informed decisions towards OEE optimization in order to meet the end goal of growing bottom line revenue and market share.

The Solution

Industry 4.0 augments Industry 3.0 process control automation systems with big data and big data analytics. At one end of the Industry 4.0 spectrum this means real-time machine data access, while at the other end of the spectrum this means bridging the chasm between operational technology systems on the factory floor and information technology systems in the back-office.

Industry 4.0 creates a digital twin or cyber physical system (CPS) of each machine on the factory floor. These digital twins allow all stakeholders to take advantage of the full Industry 4.0 spectrum of big data analytics opportunities. A 2018 PwC survey of the electronics manufacturing industry estimates that 45% of manufacturers are already deploying or are in process of deploying Industry 4.0 systems, while another 32% is planning to deploy Industry 4.0 systems within the next 5 years.

The GEMBO PRECARE platform is able to offer semiconductor manufacturers a complete Industry 4.0 upgrade which is tailored to their specific needs, with all the benefits of big data analytics to optimize OEE, but without the cost of overhauling their existing machinery. The highlights of this solution are summarized below.

Real-time data from any machine

Future proofing any machine

Large library of machines

Any factory floor data store

Machine MTB data

Machine OEE data

Machine data format uniformity

Low-latency edge processing

Robustness

Security

Big data analytics

Uniform data visualization

Hierarchy representation

Powerful rule engine

Range of notification methods

Flexible hosting options

Whether legacy or latest generation, agents obtain critical status and operational data in real-time, instantly creating digital twins and extending machine life cycles

A large and growing digital twin library of supported semiconductor manufacturing machines drastically reduces time-to-deployment

Agents can access any networked factory floor data store, including support for OPC-UA, NFS or other network file systems

Agents collect machine status data for any status category and at any level of detail required by the manufacturer, including failures and assists

Agents collect machine OEE availability, performance and quality data, with availability at any level of detail and quality for any equipment modality required by the manufacturer

Agents transform differing data formats into formats that are uniform across all machines

Agents perform complex event processing and notifications at the edge for minimal latency

Auto-recovery of agent datacom links and data store & forward guarantees maximum robustness and no missing data

Strong security at every connectivity stage, from agent to cloud, and VPN support prevents data and access breaches

Analytics such as OEE, MTBF, MTBA, predictive maintenance, etc. are instantly available at one’s fingertips, for any time period and at any factory hierarchical level

Status and machine performance data is presented in a machine agnostic way, presenting a unified dashboard across different machines and OEMs

OEE, MTB and statuses can be presented at any level, across all factory locations down to a single machine

A flexible, visually programmable rule engine supports complex rules and multiple parameters

Stakeholders get notifications instantly across multiple applications and platforms, including text, email, mobile, etc.

Platform hosting options include private, public and hybrid clouds

The Results

By deploying GEMBO PRECARE for Industry 4.0, semiconductor manufacturers gain instant access to all machine data and OEE analytics without having to do a complete overhaul of their existing OT infrastructure. As such they realize significant savings in migrating to Industry 4.0 and gain valuable insight in every machine’s availability, performance, quality, MTBF, MTBA, and other KPIs to be able to undertake necessary actions towards process flow and machine performance optimization, as well as when exactly to schedule maintenance. The overall result is that manufacturers are able to realize increases in OEE as much as 30-40%, increasing OEE scores to as high as 90%.

Platform & Resourcing Choices For Your Industry 4.0 Business Transformation Journey

Sun, 27 Feb 2022 00:08:27 GMT

INTERNAL RESOURCES, OUT-SOURCED OR HYBRID APPROACHES

ABSTRACT

The promise of the benefits that can be reaped from Industry 4.0 big data and predictive analytics through access to machine and operator data is compelling enough for most manufacturers to seriously direct their IT and OT departments to look into ways to enable such machine and operator data acquisition.

Historically manufacturers have been focused on yield (quality) improvements only. However, this is just one third of the equation, since equipment availability and performance also directly affect revenue and margin. Being able to optimize overall equipment effectiveness or OEE in terms of equipment availability, performance and the quality of items produced by the equipment is the Holy Grail for manufacturers to improve their bottom lines.

A fully integrated solution requires other aspects of the manufacturing OT and IT infrastructure to be addressed as well. Depending on the scope, GEMBO is able to leverage its partner ecosystem, consisting of Yield Improving Software Vendors, Manufacturing Execution System Vendors and Backend Infrastructure Vendors, to augment their solutions in order to be able to deliver an end-to-end transformational OT/IT solution.

In the quest for big data and predictive analytics the question of rolling a solution in-house vs. outsourcing comes up inevitably. Given the many aspects of a well-designed solution, it is instructive to look at the pros and cons of in-house vs. outsourced.

BENEFITS PERCEPTION OF INDUSTRY 4.0

Rather than focusing on a laundry list of items to consider pros and cons for, it is more useful to boil this list down to the following six KPIs to measure and compare both approaches by:

Flexibility: The ability to add-on new features or to modify existing features.
Resources: The effectiveness and availability of human resources.
Speed: The ability to meet project timeline goals.
Know-How & future-proofing: The Domain expertise to ensure project success.
Cost: The cost of human resources and cost impact on other projects.
Ongoing Support: The resources needed to ensure post-project success.

The following presents an analysis on how each KPI may play out in both cases.

Practical use of this table consists of assigning a ranking for each case for each KPI and computing the total. Among these KPIs perhaps the one that stands out the most is for the know-how and future-proofing of the solution. For example, the IPC – Association Connecting Electronics Industries® recently created the Connected Factory Exchange or IPC-CFX standardized data exchange protocol as an enabler of Industry 4.0, Smart Factory and Digital Factory solutions. Awareness and understanding of IPC-CFX is likely not the focus of in-house IT staff, but certainly within the scope of GEMBO and its partner Aegis Software.

In our experience the ranking of the above KPIs may change a lot between the first project and subsequent ones. Usually the first project is the one with the highest risk and least chances to succeed if done entirely in-house. Therefore, the ideal approach may be a hybrid one, in which a joint team is formed, consisting of internal personnel and expert external resources, and where the first project heavily relies on the expertise, skill sets and full presence of the external experts, while for subsequent projects the internal resources take on a larger role.

GEMBO and its partners are able to deliver end-to-end Industry 4.0 smart factory solutions to manufacturers, spanning the full scope from machine and human operator data acquisition to OEE KPIs, predictive maintenance, as well as comprehensive MES functionality. Through our combined resources, skill sets and expertise in implementing and rolling out Industry 4.0 smart manufacturing solutions we are able to score consistently very high against each KPI in the above table.

CONCLUSIONS

Internal resources are usually behind on state-of-the-art due to a lack of project-specific specialization, which not only negatively impacts the implementation, but also risks that the solution will quickly become outdated. On the other hand, an outside entity can bring the required levels of specialization paired with know-how on the latest technologies, which enables efficient implementations and helps with future-proofing the solution, avoiding future costs of having to redo parts or the whole solution. Deep specialization of GEMBO in digital twin connectivity and predictive analytics combined with Aegis Software’s expertise in MES and the IPC-CFX standardized data exchange protocol assures future-proofed end-to-end smart manufacturing implementations and deployments.

Heavy Industries Manufacturing Reaps Industry 4.0 Benefits with GEMBO Precare

Sun, 27 Feb 2022 00:08:15 GMT

CRITICAL KPIs AND PREDICTIVE ANALYTICS FOR ENHANCED OPERATIONAL

ABSTRACT

The advent of Industry 4.0 or smart manufacturing is transforming industries across the board from an automation-centered to a knowledge-centered focus. This is not surprising since the benefits of big data analytics for the purpose of making predictions and tracing the root cause of an issue is of extreme importance to any manufacturer, regardless of the industry sector. In this white paper we identify the unique problems that manufacturers in the heavy industries sector face in making the transition to smart manufacturing and explain how the GEMBO Precare IIoT platform solution helps solve these issues without the need for an overhaul of existing manufacturing infrastructure.

BENEFITS PERCEPTION OF INDUSTRY 4.0

A survey conducted by the Boston Consulting Group in 2016 on manufacturers’ expectations from Industry 4.0 shows that manufacturing cost as the top expectation gets the highest priority in the range of manufacturing cost to new revenue model, followed by product quality, while manufacturing cost scores the highest in expectation, followed by product quality.

This is not surprising since the main foundational element of Industry 4.0 is the real-time acquisition of data from the factory floor which can lead to immediate improvements in manufacturing costs and product quality. Next in expectation are operations agility, supply chain costs and product innovation, followed by time-to-market, improved customer satisfaction and revenue increase. Since IIoT and predictive analytics directly affect OEE (Overall Equipment Effectiveness), it turns out that when properly implemented and used, there is a dramatic positive effect on revenue growth, as we will demonstrate in this white paper.

ADOPTION OF INDUSTRY 4.0 EXPECTATIONS AND FACTS

In a 2015 survey by PwC of more than 2,000 manufacturers in 26 countries, one-third had already achieved more than 35% of digitization of their factory floors, and almost 77% is planning to reach a greater than 65% level of digitization by 2020. The reality is however is that this is an optimistic view, based on expectation of favorable consumer sentiment and capital market conditions.

What GEMBO has found is that economic uncertainties dramatically temper the adoption rate for smart manufacturing, because of the high capital and operational expenditures associated with replacement of legacy equipment with the latest and greatest digitized equipment. GEMBO has further found that the majority of today’s factory automation consists of data islands with no means to access the machine data in real-time or at all.

There are two common situations, GEMBO has observed. The first one is the existence of the “Digitally Controlled Data Island” where factory automation installations include a PLC or some other form of digital control, but with no network access. Therefore, once programmed, they perform sensor data acquisition and control as a closed system with no access to real-time sensor data. This precludes such systems from providing data for the enablement of smart manufacturing.

The Second one is that of “Missing Critical Data”, where the PLC only monitors signals that are directly related to particular subsystems of the machine, and in most to all cases, monitors only the actions of the machines, related to total parts, good parts and bad parts, leaving out other variables that can provide imperative complementary insights in the root cause of diminished OEE or that are important in order to be able to make highly accurate predictions when to conduct equipment maintenance. Monitoring vibrations, noise, ambient temperature, humidity and power supply conditions are among just a few of these variables that are largely omitted, but yet can contribute in very important ways. Furthermore, it should be noted here that such incompleteness of data holds equally true for machines that are network-enabled, no matter if they belong to the most recent generation of factory automation equipment.

CONNECTING DATA ISLANDS AND EXTENDING DATA ACQUISITION WITH GEMBO PRECARE

GEMBO has recognized the earlier mentioned practical problems which manufacturers face on an ongoing basis, no matter where they are in their journey to transition to smart manufacturing. Where many excellent products exist today for the back-end processing of machine data, GEMBO is unique in that it also solves the “last mile” problem in addition to the back-end processing for critical KPIs and predictive analytics.

The GEMBO Precare IIoT platform consists of GEMBO Precare Edge, GEMBO Precare Cloud and GEMBO Precare KPIs. GEMBO Precare Edge agents are responsible for data acquisition, digital twin representations of the machines, edge processing and communicating machine data to the GEMBO Precare Cloud. GEMBO Precare Cloud uses the machine data for predictive analytics, including machine learning for predictive maintenance, and real-time compilation of critical KPIs, such as equipment Availability, Performance, Quality, OEE, MTBF and MTBA.

GEMBO Precare Agents deploy their own sensors to complement sensor data, if accessible, from the machine, such as from a PLC, or rely entirely on its own sensors where there is no access at all to sensor data. In either case the agents connect via a TCP/IP infrastructure, Ethernet or WiFi, to a GEMBO Precare Cloud. In this fashion GEMBO Precare connects machines into a network infrastructure and eliminating existing data islands.

GEMBO further distinguishes itself from other IoT solution providers via reliable, industrial grade agent and sensor hardware, as well as its broad and deep knowledge of sensor technology. These hardware components are specified to operate in harsh environmental conditions, commonly encountered in heavy industries manufacturing, such as construction materials manufacturing.

Broad and deep knowledge of sensor technology means that GEMBO is able to understand measurement and behavioral parameters which are critical for each machine in the process flow and their relevance to the predictions that can be made from the data. The importance of this cannot be overstated and is best illustrated via the temperature probe example here below.

Although there are literally hundreds of temperature probes available for the same temperature measurement range, making a selection just based on temperature measurement range, substance to be probed (i.e., solid, liquid or gas), probe assembly and electrical interface is not sufficient. The table below lists a subset of variables that are critical in the selection of the correct probe for the job.

GEMBO PRECARE SOLUTIONS

GEMBO Precare uses the power of data, analytics and machine learning to mitigate and minimize the impact of equipment related adverse events, providing the following solutions:

Predictive maintenance . Avoids costly unscheduled and unnecessary scheduled downtime. Instead predicts when precisely to schedule maintenance.
Catastrophic failure prevention. Avoids costly catastrophic failures, for instance by early detection of abnormal vibrations in rotating machine parts or due to unbalanced machine parts.
Maintenance/repair time reduction. Avoids expensive maintenance/repair crew hours with prior knowledge of the kind of maintenance or repair and which spare parts are needed.
Overall Equipment Effectiveness & customer satisfaction optimization. Maximizes OEE, revenues and margins by eliminating unnecessary and unplanned downtime by keeping any downtime at a minimum, rate of production optimal and quantity of scrapped products low.

PREDICTIVE MAINTENANCE

GEMBO Precare collects failure data and uses machine learning to construct models that can accurately predict when a failure has the highest probability of happening. An example is shown below. GEMBO Precare predictions take scheduling time into consideration. For example, if scheduling maintenance requires 30 days ahead scheduling, the prediction is made for 30 days out. Prediction results are expressed in failure probability and accuracy. GEMBO Precare achieves close to 100% accuracy as shown in the example, where a prediction is made on day 110 when a failure will occur. The actual day of failure is at day 159, whereas GEMBO Precare predicts with a 99.9% probability and 99% accuracy that the failure will happen on day 157.

OEE

Just as predictive maintenance is important to optimize equipment availability and to eliminate unnecessary scheduled downtime, so is OEE for productivity. OEE is an important KPI and tool to discover events and factors that adversely affect equipment effectiveness and customer satisfaction.

OEE is expressed as OEE = availability x performance x quality. Each of these components is measured as follows:

Availability ; measured as the ratio of actual production time and total production time for a given production batch.
Performance ; measured as the ratio of actual quantity produced and quantity of units that could have been produced under ideal condition for a given production batch.
Quality ; measured in terms of the ratio of the quantity of good units and the quantity of total units the machine produced in a production batch.

GEMBO Precare not only collects all data necessary to calculate availability, performance, quality and OEE, but drills down to the cause(s) of diminished OEE. An example is shown below for an installation consisting of two chillers and two condensers serving the building lobby and the cafeteria with one pair of chiller and condenser for each space at ACME CA, USA.

At the top level the OEE KPIs are shown for the complete factory. Each OEE KPI lists also the details. For instance, for the Availability KPI the hours of unplanned, planned and total run time are shown.

Since the availability KPI is relatively low compared to the performance and the quality KPIs, the next step is to find out which equipment is experiencing high levels of downtime. Examining the floor plan reveals that machine 1 on floor 1 is currently in the red zone. This doesn’t mean yet that this machine is responsible for the availability KPI to be so low, since this is just a snapshot at the present moment.

At the same time the bar graph below shows that the main reason for the low availability is due to a relatively high number of assist hours.

Clicking on the assist bar shows that machine 1 on floor 2 contributes to nearly 100% of the assist hours.

Further drill-down from here is possible into the exact reason(s) for the high number of assist hours, depending on the number of drill-down levels for assists configured in GEMBO Precare.

GEMBO PRECARE AGENTS

GEMBO Precare deploys agents which can talk directly to equipment controllers over a host of different physical interfaces and protocols, as well as gather machine data independently from the machine’s controller. The key agent features are listed below:

Real-time data acquisition. GEMBO Precare agents collect any equipment and ambient vital data in real-time for overall equipment health analysis and trends.
Any equipment vitals. Whichever is needed to be monitored, including abnormal power supply voltage fluctuations, unusual noise and abnormal vibrations caused by moving parts, ambient temperature, humidity, etc.
Any connectivity. Equipment vitals may be collected through sensors on GEMBO Precare agents, from the equipment’s own programmable logic controllers or through a combination of both.
Low latency . GEMBO Precare agents run on microprocessors which reside in the vicinity of the equipment, performing on the spot anomaly detection, machine vision, complex event processing and other latency-sensitive tasks.
Machine learning . These microprocessors are powerful enough to perform inference, using the machine learning models trained by the GEMBO Precare Cloud platform.
GEMBO Precare agents connect to your choice of private, public or hybrid Cloud, where the data can be used to train machine learning models, visualize KPIs and other data, issue alarms and periodic reports.

CONCLUSIONS

CONTACT US

GEMBO Precare PdM Predictive Maintenance

Sun, 27 Feb 2022 00:08:15 GMT

GEM Precare IIoT Platform Predictive Maintenance Solution

Abstract

Ensuring optimal machine operation is of central importance in any industrial activity. Any degradation in operation, be it availability, performance, or quality, impacts the bottom line, which can be millions of dollars in high volume manufacturing. Therefore planned maintenance at regularly scheduled intervals is a broadly accepted concept and practice in the industry. However, such a practice is sub-optimal in serving the goal of optimal machine operation. Regularly scheduled maintenance can be overkill on the one hand, leading to

unnecessary scheduled machine downtime and therefore productivity loss. On the other hand it doesn’t entirely prevent an unforeseen machine break down. The Holy Grail is to be able to predict when to schedule necessary maintenance under any circumstance before a break down occurs. Big data analytics and machine learning are the primary tools available to manufacturers to predict when to schedule maintenance.

Maintenance Strategies Compared

Maintenance strategies can be categorized as follows:

Reactive maintenance. Maintenance is only performed when the machine breaks down.
Preventive maintenance. Maintenance is performed at regular intervals.
Conditional maintenance. Maintenance is scheduled in anticipation of a breakdown, based on monitoring of the asset and using prior experience to assess the need to schedule maintenance.
Predictive maintenance. Maintenance is scheduled in anticipation of a breakdown, using big data analytics and machine learning to predict the probability of a failure by models trained on discerning usage and wear data patterns. Since maintenance is scheduled not later and not sooner, but at the right moment, predictive maintenance can also be called just-in-time maintenance.

Reactive maintenance sits at the highest end of the cost impact scale and at the lowest end of the maintenance anticipation scale, whereas predictive maintenance sits at the lowest end of the cost impact scale and at the highest end of the maintenance anticipation scale.

Another very important distinction between predictive maintenance and the other maintenance strategies is the fact that the former will be able to predict maintenance to be performed ahead of time even when machine conditions change relatively more rapidly than usual. In contrast, the preventive maintenance strategy will need to fall back to reactive maintenance in case of such conditions, while in case of the conditional maintenance strategy the unusually rapid changes may not be recognized early enough, causing here too the need to fall back to reactive maintenance.

An important aspect of predictive maintenance is that machine learning is able to learn at a much faster rate from historical data then humans are capable of. For instance, if years of recorded machine data are already available, then machine learning algorithms can learn from this data in a matter of hours, whereas a person would need days, weeks, or even longer to analyze the data and learn from it. And even then, it may not be possible at all for a person to learn from it if the data is only available in numeric form and not in a form that is suitable for any of the five senses. Furthermore, if the person leaves the manufacturing organization after having learned from the data, the knowledge is lost and the process has to start all over again.

GEM Precare Predictive Maintenance Worklow

GEM Precare is an Industrial IoT (IIoT) solutions platform that combines real-time machine data acquisition with big data analytics and machine learning. GEM Precare agents installed at the machine (i.e., edge) stream data in real-time to the GEM Precare cloud for big data analytics and training of predictive maintenance machine learning models.

These agents are able to collect data through any means, any protocol and any physical interface, including directly from sensors, from networked data stores, over OPC UA client-server protocols, over Industrial Ethernet, over SCADA, UART, etc. The agents are highly portable to any embedded ARM or x86 hardware platform, with support for any type of physical I/O and network port.

The agents create digital twins for the machines, so that the data provided to the GEM Precare PdM module has the correct semantic meaning attached to it and not just a raw stream of 1’s and 0’s or numbers. This greatly facilitates human interpretation as well as pre-processing and feature extraction which are both very important parts of a machine learning workflow next to big data pools.

The next stage in the workflow is the training and validation of two or more predictive models or two or more variations of the same model. Although this stage is typically performed in the cloud due to its highly scalable inter-connectivity, storage and compute resources, it is possible to perform this also at the edge (i.e., machine learning at the edge) with the right hardware platform.

In the final step the model or model variation with the best prediction accuracy is selected and deployed. This however does not mean that the cycle is complete and no more training is needed. A machine learning algorithm is able to extract from the training data a statistical model with specific model parameter values that best fit the data. As long as the underlying statistical model or model parameter values don’t change, the algorithm will perform as expected.

However, small changes will cause the model parameters to drift and over time this drift will have become significantly large enough that the algorithm’s accuracy is noticeable negatively affected. For this reason the GEM Precare PdM module continues the learning and validation process in perpetuity.

Model Specificity and Right Data Set

It is important to spend a few words on the importance of:

The highly specific nature of a trained machine learning model.
The use of representative training and validation data sets.

Usage patterns and configurations of machines in a manufacturing operation may differ from machine to machine, even when all machines are of the same make and model. For instance, one of two identical machines is operated 5 hours per day over 3 months, then 10 hours per day over the next 9 months, while the other machine is used 10 hours per day for the first 10 months, then 7 hours per day over the next 2 months. The first machine is configured to probe 100 points per chip, while the second machine is configured to probe 50 points per chip.

Since machine learning inherently bases model parameters on the data it is trained on, each machine’s data will result in a different set of values for the model parameters. Hence, using the set of parameter values for one machine on a different machine will most likely not result in the same prediction accuracy for the two machines. It is therefore important to realize that machine learning will have to be performed individually for each machine separately if not all usage patterns and configurations across all the machines are considered in the training and validation data sets.

The makeup of the training and validation data sets is of special importance. If not properly constituted, the training of a perfectly suitable machine learning model will yield unusable parameter values. If a training and validation data set is chosen with very few failure events, the model will be trained to recognize no failures at all, yet the accuracy of the training and validation data sets will be very high, for instance better than 99%. Such data sets are referred to as being skewed and machine learning models trained and validated on these data sets yield very poor results in real-life situations.

GEM Precare PdM Triggers

As explained before, the aim of predictive maintenance is to schedule maintenance not too soon, not too late, but just in time. The relevant question is therefore:

“In how many days from today will maintenance be necessary?”

The GEM Precare PdM solution asks the same question in a different way:

“Has the probability for a failure exceeded the specified threshold for the specified number of days from today?”

Formulating the question in this way is more practical since in real-life scheduling resources to perform the maintenance has to happen a minimum of hours or days in advance. One can then specify a probability threshold above which the maintenance is being scheduled the specified number of days in advance.

Of course the previous will not prevent the possibility of a reactive maintenance event. For example, assume that the specified number of days (P) in the above question is 30 days, and the usual rolling 30 day prediction exhibits a gradually increasing probability (case 1). However, due to some unforeseen circumstance the probability has a much steeper upward trend (case 2) than the usual (case 1). Following the current trend, the probability is likely to cross the threshold within the next 5 days (a << P) for example, instead of the next 30 days (P).

Therefore, the GEM Precare PdM solution also monitors the slope of the trend along which the probability progresses. In case this slope predicts that the preset probability threshold will be exceeded earlier than within the specified number of days, then Precare will issue notifications as it counts down towards the day that the failure probability is predicted to cross north of the threshold.

GEM Precare PdM Example

Following are the results obtained for real-world training and validation data sets. The data sets contained sensor and machine configuration data for operation within normal and outside of normal margins. The machine learning model used was based on a neural network, consisting of an input layer, two hidden layers and an output layer which provides the probability of a failure within specified number of days from today.

The results are listed in the table below. The probability stays small in the first 85 days, but starts to increase thereafter, and accelerates from day 100 towards day 160, with the actual failure occurring on day 159.

Actual Failure: Day 159

The 1st plot below shows graphically how the failure probability evolves from day 1 to day 160. The interpolation illustrates how the failure probability accelerates as mentioned before. The 2nd plot shows how the failure probability evolves from day 1 to day 100. The 3rd plot shows how the failure probability evolves from day 1 to day 110.

Set for a failure probability threshold of 85%, our PdM solution forecasts for the data available up to day 100 in the 2nd plot that the failure will occur at day 212 with a probability of 98%. Given that the actual day of the failure is at day 159, this prediction is 67% accurate. Repeating the forecast based on the data available up to day 110 in the 3rd plot yields a forecast for the failure to occur at day 157 with a probability of 100%. Given that the actual day of the failure is on day 159, the accuracy of this prediction is 99%.

By continuing to predict as more data becomes available, Precare PdM is able to latch on to a trend towards failure resulting in rising predicted failure probabilities at higher and higher accuracy. In the example here, in case the minimum time for advanced allocation of maintenance/repair resources is 30 days, the prediction at day 100 would hold off reserving maintenance resources until day 182, but then change this to day 127 when the prediction changes from day 212 at 98% to day 157 at 100%.

These results illustrate the impressive accuracy with which GEM Precare PdM is able to forecast just-in-time maintenance with ample time to book the resources to perform the maintenance/repair. These results also illustrate how GEM Precare PdM is able to react to a sudden rapid deterioration of the machine’s condition, therefore avoiding reactive maintenance at high cost impact.

OEE Impacts

OEE (Overall Equipment Effectiveness) is an important KPI for manufacturers to measure how effective their manufacturing assets are utilized. OEE is expressed as OEE = availability x performance x quality .

Each of these components is measured as follows:

Availability ; the ratio of actual production time (unplanned down time excluded) and total run time (unplanned downtime included).
Performance ; the ratio of actual and optimal machine throughput.
Quality ; the ratio of good units and total units produced.

GEM Precare compiles these KPIs automatically from the data collected by the GEM Precare agents and provides the ability to zoom in on problem areas. Each of the three OEE components is positively affected by the ability to predict when to perform maintenance. Equipment availability increases by just-in-time maintenance over any of the other types of maintenance mentioned before. The same holds true for performance and quality, since maintenance may improve the throughput of a machine and may reduce the quantity of defects in manufactured units, respectively.

Customer Journey

Deploying GEM Precare PdM on the manufacturing floor starts with the deployment of GEM Precare agents for data acquisition and creation of digital twins of the machines for which one desires to apply predictive maintenance to. The data being captured must contain machine failure events as well as the historical data leading up to the events. This is very important since the training is done using a supervised training method, where failure events are labeled for the machine learning algorithm to be able to distinguish these events from the rest of the data. Supervised learning is similar to learning by example.

In case there is already a repository of historical machine data available, this data set can be used instead to start with, or in conjunction with the acquisition of new data, provided that semantics can be assigned to the data for feature extraction and preprocessing. Note that a pre-existing data set does not obviate the need for ongoing acquisition of machine data for reasons explained before. Therefore, the deployment of the agents is a necessary step. One or more machine learning models are trained, evaluated and results compared based on specified number of days advanced notification for maintenance. The most accurate model is selected, or further tweaking of model attributes is done (e.g., number of nodes or layers in a neural network model) for the most promising model in case the accuracy does not meet the desired minimum accuracy. Once the desired accuracy is achieved on the training and validation data sets, the model is deployed.

Conclusions

GEM Precare provides manufacturers with a powerful solution for IIoT connectivity of any machine for big data and predictive analytics. GEM Precare PdM takes advantage of machine IIoT data to predict failures and when to perform just-in-time maintenance/repairs with enough time to allocate resources, by using powerful machine learning algorithms and methodologies. This has immediate positive impact not only on gross margins and operating margins, but also on revenues as it improves OEE. Furthermore, GEM Precare PdM enables just-in-time maintenance scheduling, customized per individual machine, and learns on a continuous basis, therefore adjusting with changing machine usage, configurations and other factors. Finally, GEM Precare PdM’s very high accuracy not only rivals that of a human expert, but learning is achieved at a much faster rate than humanly possible. Therefore, manufacturers deploying the GEM Precare PDM solution improve their OEE and their bottom line.

Contact Us

Human Operator-in-the-loop OEE

Sun, 27 Feb 2022 00:08:12 GMT

Integrating the Human Factor into Cyber‐Physical Systems

Introduction

Although there are many parts of a factory that contribute to the overall effectiveness of a manufacturing operation, there is no doubt that what happens on the production floor greatly impacts overall effectiveness. Although control and operation of machines in a modern manufacturing operation is highly automated, many such operations rely on a mix of automation and manual operation for aspects that still require operator attention and intervention. Therefore, when measuring equipment OEE (overall equipment effectiveness) from availability, performance and quality, it is not only logical, but necessary to consider the operator as part of the machine.

As such the Cyber-Physical System (CPS) or Digital Twin representation of the equipment must include the human-operator-in-the-loop (HOITL) so that operator data is included as part of the automated collection of data for the entire machine. The challenge is to do this in an unobtrusive fashion, so that the operator is not hampered in any way when interacting with the equipment. Therefore, use of a wearable device requires transmitting operator data wirelessly. An additional requirement is that the solution must be cost-effective.

RFID was designed to meet all these three requirements. In this white paper we explore the use of this technology with GEMBO Precare agents that turn any machine into a CPS by streaming data in real-time to the GEMBO Precare Industry 4.0 IIoT platform.

RFID Overview

Industrial and commercial use power generators are complex systems, which are required to operate reliably without interruption and to be available whenever the need arises for backup power. Like with any complex system any number of things can go wrong and will go wrong, no matter the level of planning and preparation. The challenge is therefore to minimize the financial, operational and psychological cost of any malfunction or suboptimal functioning of the system. The following equipment related events negatively impact operational cost and customer satisfaction:

Equipment breakdown.
Equipment downtime, regardless of maintenance, repair, out of fuel or other reasons.
Reduced power output.

What if you could minimize the probability of any of these events and hence reap the fruits of reduced OpEx and increased customer satisfaction?

The GEMBO PRECARE Solution

RFID is an acronym for Radio Frequency IDentification. It is intended as a low power means of tagging animate and inanimate objects for identification via a wireless reader. Information about the object is stored in an RFID tag’s on-board Flash memory. Based on how the tag is powered, RFID tags are classified in two main categories:

Passive RFID tags
Active RFID tags.

Passive RFID tags operate without the use of a battery. The tag uses its antenna as an induction coupling device to transfer power emitted via a reader’s antenna to power itself so that it can transmit its data to the RFID reader. The main components of a passive RFID tag are

Rx/Tx antenna;
Modem (modulator/demodulator);
Codec (encoder/decoder);
Logic control circuit;
Memory;
RF Energy harvester for passive tags, or battery for active tags.

The main standards bodies for RFID are:

ISO/IEC;
IEEE;
GS1/EPCglobal.

Each country is responsible for defining its own regulations for the use of radio devices, including RFID. The regulations most commonly used are:

The United States of America Federal Communication Commission (FCC);
The European Conference of Postal and Telecommunications Administrations (CEPT) through its European Telecommunications Standards Institute (ETSI).

RFID standards cover short-range (Prox Card), near-range (NFC, MIFARE), mid-range (RAIN) and long-range (ISO 18000-7 RFID). Short and near-range RFID don’t require an integrated power source, since it harvests power from the energy transmitted wirelessly by the reader. However, it restricts operator freedom since it requires the operator to bring the tag very close to the reader.

Long-range RFID allows the operator total freedom, but has the drawback that a power source, such as a battery, is required for the tag. Mid-range RFID combines the advantages of long-range and near-range RFID. Actual range is largely determined by the transmission power of the reader.

The following table summarizes the important features of the four RFID types side-by-side

*) Actual range depends on the transmission power of the reader in case of passive RFID.

The GEMBO Solution

GEMBO’s HOITL extension of CPS representations of manufacturing equipment makes use of mid-range passive RFID tags in combination with one or more readers positioned strategically relative to the machine. The readers are connected to a GEMBO agent which uses reader location and tag RSS to compute the operator’s position relative to the machine.

When combined with events that impact OEE, such as unplanned down-time events, unintended drops in the machine’s throughput, unexpected increase of rejected product quantities, etc., a more complete understanding of loss of OEE is gained and therefore root cause analyses can be more accurate.

GEMBO agents can perform real-time processing and interpretation of the CPS data and take action immediately at the edge. Simultaneously the agents stream the data to the GEMBO Precare cloud platform where data from all agents can be combined for the compilation of factory-wide KPIs, big data analytics for the detection of more general patterns for instance, and for accelerating training and validation of machine learning algorithms.

Conclusions

GEMBO Precare supports inclusion of human-in-the-loop in the CPS representation of machines, so that events that negatively affect OEE can be analyzed in full context that includes the operator. Use of passive, medium-range RFID tags provide freedom of movement for the operator and are maintenance free since they don’t require batteries. Using the tag’s relative signal strength combined with multiple readers for relatively large machines is used to determine approximate position of the operator relative to the machine. Therefore, including the human operator in the CPS representation of the equipment allows manufacturers to not only optimize OEE for machine-specific parameters, but also for operator-specific factors.

Reducing OPEX and Increasing Customer Satisfaction for Industrial and Commercial Use Power Generators

Sun, 27 Feb 2022 00:08:09 GMT

With GEMBO PRECARE IIoT Platform for OEE and Predictive Maintenance

Abstract

Customers of industrial and commercial use power generators place high expectations on the quality, performance and availability of these systems. They expect them to perform reliably at a moment’s notice when needed, with little or no interruption. The same OEE (overall equipment effectiveness) and predictive maintenance principles used in the manufacturing industry apply to industrial and commercial use power generators. With the GEMBO Precare Platform, power generator OEMs and their service partners can achieve significant reductions in operational expenses and see significant increases in customer satisfaction.

Negative Impacts on OPEX and Customer Satisfaction

Equipment breakdown.
Equipment downtime, regardless of maintenance, repair, out of fuel or other reasons.
Reduced power output.

What if you could minimize the probability of any of these events and hence reap the fruits of reduced OpEx and increased customer satisfaction?

The GEMBO PRECARE Solution

GEMBO Precare uses the power of data, analytics and machine learning to mitigate and minimize the impact of equipment related adverse events through the following:

Predictive maintenance. Avoid costly unscheduled and unnecessary scheduled downtime. Instead determine when precisely to schedule maintenance.
Catastrophic failure prevention. Avoid costly catastrophic failures, for instance by early detection of abnormal vibrations in rotating parts.
Maintenance/repair time reduction. Avoid expensive maintenance/repair crew hours with prior knowledge of the kind of maintenance or repair and which spare parts are needed.
Truck-roll reduction. Avoid unnecessary truck rolls by minimizing planned and unplanned downtime while simultaneously having sufficient information upfront to determine what needs maintenance and/or repair.
Overall Equipment Effectiveness & customer satisfaction optimization. Maximize OEE and customer satisfaction by eliminating unnecessary and unplanned downtime by keeping any downtime at a minimum and by keeping customer premise equipment running at optimal performance.

Predictive Maintenance

GEMBO Precare collects failure data and uses machine learning to construct models that can accurately predict when a failure has the highest probability of happening. An example is shown below.

OEE

Just as predictive maintenance is important to optimize equipment availability and to eliminate unnecessary scheduled downtime, so is OEE. OEE is an important KPI and tool to discover events and factors that adversely affect equipment effectiveness and customer satisfaction.

OEE is expressed as OEE = availability x performance x quality. Each of these components is measured as follows:

Availability; measured in terms of the amount of time the equipment is generating power in a specified time interval.

Performance; measured in terms of the rate at which the equipment is producing power, i.e., measured in KW hour, or the amount of energy produced per hour.

Quality; measured in terms of the total power in KW produced within a specified time interval. This includes any down time experienced within the specified interval.

GEMBO Precare not only collects all data necessary to calculate availability, performance, quality and OEE, but drills down to the cause(s) of diminished OEE. An example is shown below for an installation consisting of two buildings, each with two power generator. The GEMBO Precare Rule Engine allows actions to be automatically executed as a result of one or more conditions met simultaneously by one or more monitored signals.

At the top level the OEE KPIs are shown for both buildings, i.e., for both generators combined. Each OEE KPI lists also the details. For instance, for the Availability KPI the hours of unplanned, planned and total run time are shown.

Since the number of unplanned downtime hours is relatively high over the 1 year period selected, the next step is to find out which generator is experiencing high levels of unplanned downtime. Examining the floor plan shows that generator 1A at building 1 is in the red zone currently, experiencing a failure. Generators 1B and 2A are operating normally and generator 2B is experiencing some form of assistive action.

However, this doesn’t necessarily mean that this generator is the cause of the low availability, since the above shows only current status. At the same time the bar graph below shows that the main reason for the downtime is due to number of assist hours.

Clicking on the assist bar shows that the building 2 generator 2A contributes to nearly 100% of the assist hours.

Further drill-down from here is possible into the exact reason(s) for the high number of assist hours, depending on the number of drill-down levels for assists configured in GEMBO Precare

GEMBO PRECARE Agents

GEMBO Precare deploys agents which can talk directly to equipment controllers over a host of different physical interfaces and protocols. The key agent features are listed below:

Real-time data acquisition. GEMBO Precare agents collect any equipment vital data in real-time for overall equipment health analysis and trends.
Any equipment vitals. Whichever is needed to be monitored, including abnormal power supply voltage fluctuations, unusual noise, abnormal vibrations caused by rotating parts, fuel leakages, etc.
Any connectivity. Equipment vitals may be collected through sensors on GEMBO Precare agent hardware, from the equipment’s own programmable logic controllers or through a combination of both.
Low latency. GEMBO Precare agents run on microprocessors which reside in the same location as the equipment, performing on the spot anomaly detection, complex event processing and other latency-sensitive tasks.
Automated Actions & Complex Event Processing. GEMBO Precare Rule Engine allows actions to be automatically executed as a result of one or more conditions met simultaneously by one or more monitored signals.
Machine learning. GEMBO Precare agents stream data to the GEMBO Precare cloud platform, where machine learning models are trained for predictive maintenance.
Dashboards. The GEMBO Precare cloud platform compiles and presents comprehensive KPIs in user-friendly dashboards side by side with equipment status, alarms and graphs, as well as comprehensive reports. KPIs include OEE, availability, performance, quality, MTBF and MTBA, with traceability of problem areas.
Flexible hosting options. GEMBO Precare can be hosted on your choice of private, public or hybrid cloud.

Conclusions

GEMBO Precare has a set of powerful data acquisition, analytics, predictive and OEE tools for industrial and commercial power generator. GEMBO Precare gathers, analyzes and presents critical and actionable data plus key performance indicators (KPIs) before a system, subsystem or component reaches its breaking point. In addition GEMBO Precare collects important data which can significantly reduce maintenance and repair time, as well as truck rolls. Power generator OEMs and service partners using GEMBO Precare have a set of powerful tools at their fingertips to minimize OpEx and boost customer satisfaction.

On Cyber-Physical Systems, IIoT and Digital Twins

Sun, 27 Feb 2022 00:08:08 GMT

With GEMBO PRECARE IIoT Platform for OEE and Predictive Maintenance

The Cyber Physical System (CPS), Internet of Things (IoT) and Digital Twin are all central concepts in Industry 4.0, often used interchangeably in discussions about Industry 4.0. It is therefore worthwhile to examine what each means and how they relate to each other.

The phrase ‘Cyber Physical System’ is said to have been coined for the first time in 2006 by Helen Gill of the National Science Foundation (NSF). The origin of the phrase ‘Internet of Things’ is generally ascribed to Kevin Ashton while at MIT in 1999, whereas the origin of the phrase ‘Digital Twin’ is generally ascribed to Michael Grieves while at University of Michigan in 2001. The phrase ‘Industrial Internet of Things’ was a recent addition to indicate the use of IoT in industrial applications as opposed to consumer applications.

A CPS is generally defined as a combination of physical (mechanical) components, transducers (sensors and actuators), and information technology (IT) systems (network/communication systems and computation/analysis/control systems). Some definitions include the human, such as the machine operator. In other words, a CPS is a physical world system (machine only or machine plus human) that is connected to the cyber world. A CPS can be either a closed-loop or open-loop system; meaning that it may sense the real-world parameters of the physical system and control it, or it may just sense the real-world parameters and make these available for analytical purposes.

IoT or IIoT is generally defined as a combination of any of the following: trackable objects (such as RFID tags), data objects (such as sensors), interactive objects (such as actuators) and smart objects (such as software components that act on sensor data for any purpose, including pre-processing, control, analytics, etc.).

A Digital Twin is a digital replica of a physical asset. The definition of a Digital Twin emphasizes the connection between the physical and the digital replica, and the data that is generated using sensors. A Digital Twin integrates transducers, artificial intelligence/machine learning, data analytics and context awareness. An example of context awareness is an intelligent thermostat, which senses who is present, so that the person’s preferences for ambient conditions can be taken into consideration.

The CPS concept emerged primarily from a systems engineering and control perspective, whereas the IoT concept emerged primarily from a networking and IT perspective with origins in the RFID context. The Digital Twin concept on the other hand, emerged from an artificial intelligence/machine learning perspective. Nonetheless, all three can be and are being used interchangeably, given that the definitions of the three concepts are converging over time.

GEMBO Precare agent technology IP straddles all three definitions and therefore GEMBO refers to CPS, IoT/IIoT and Digital Twin interchangeably. GEMBO agents acquire data on status, operation, ambient conditions, operator-in-the-loop, as well as other aspects of the operation of a machine, resulting in a multi-dimensional Digital Twin representation of a machine. The agents assign semantical meaning to the data, creating an exact digital replica of the machine’s visible/non-visible signaling interface. GEMBO agents can be additive to an existing in-the-loop controller, such as a PLC, they can be integrated into the in-the-loop-controller, or they can include the in-the-loop controller.

GEMBO agent technology IP is application-agnostic and can be deployed in any industrial or consumer application. In addition, GEMBO has developed market leading subject matter experience in particular in smart manufacturing, with focus on semiconductor and electronics manufacturing.

GEMBO Precare agents seamlessly connect manufacturing equipment to the GEMBO Precare Industry 4.0 IIoT platform, which provides manufacturers literally overnight with an upgrade to smart manufacturing without the cost of overhauling their factory floors with new equipment. The solution provides manufacturers with important KPIs, such as OEE, availability, performance, quality, MTBF, MTBA as well as the ability to predict when to conduct equipment maintenance.

How GEMBO Precare IIoT Platform Decreases OpEx and Increases Customer Satisfaction for Industrial and Commercial Use HVAC Systems

Sun, 27 Feb 2022 00:08:06 GMT

Abstract

Customers of industrial and commercial use HVAC systems place high expectations on the quality, performance and availability of these systems. They expect them to perform at configured ambient settings with little or no interruption. The same OEE KPI and predictive maintenance principles used in the manufacturing industry apply to industrial and commercial use HVAC systems. With GEMBO Precare, HVAC OEMs and their service partners can achieve significant reductions in operational expenses and see significant increases in customer satisfaction.

Negative Impacts on OPEX and Customer Satisfaction

Industrial and commercial use HVAC systems are complex systems which serve users that just want them to work at their ambient preferences without interruption. Like with any complex system any number of things can go wrong and will go wrong, no matter the level of planning and preparation. The challenge is therefore to minimize the financial and psychological cost of any malfunction or suboptimal functioning of the system. The following equipment related events negatively impact operational cost and customer satisfaction:

Equipment breakdown.
Equipment downtime, regardless of maintenance, repair, out of fuel or other reasons.
Reduced power output.

What if you could minimize the probability of any of these events and hence reap the fruits of reduced OpEx and increased customer satisfaction?

The GEMBO PRECARE Solution

GEMBO Precare uses the power of data, analytics and machine learning to mitigate and minimize the impact of equipment related adverse events through the following:

Predictive maintenance . Avoid costly unscheduled and unnecessary scheduled downtime. Instead determine when precisely to schedule maintenance.
Catastrophic failure prevention . Avoid costly catastrophic failures, for instance by early detection of abnormal vibrations in rotating parts.
Maintenance/repair time reduction . Avoid expensive maintenance/repair crew hours with prior knowledge of the kind of maintenance or repair and which spare parts are needed.
Truck-roll reduction . Avoid unnecessary truck rolls by minimizing planned and unplanned downtime while simultaneously having sufficient information upfront to determine what needs maintenance and/or repair.
Overall Equipment Effectiveness & customer satisfaction optimization . Maximize OEE and customer satisfaction by eliminating unnecessary and unplanned downtime by keeping any downtime at a minimum and by keeping customer premise equipment running at optimal performance.

Predictive Maintenance

GEMBO Precare collects failure data and uses machine learning to construct models that can accurately predict when a failure has the highest probability of happening. An example is shown below.

OEE

OEE is expressed as OEE = availability x performance x quality. Each of these components is measured as follows:

Availability; measured in terms of the amount of time the equipment is producing during a given time window.

Performance; measured in terms of the rate at which the equipment is producing. In case of an HVAC system this can be expressed in a number of ways, including the amount of time it takes to deliver one gallon of air into the space or room for which it controls the ambient. In other words, one unit of product is equal to one gallon of released air and each space or room is the equivalent of a production line.

Quality; measured in terms of the total volume of air produced with the right ambient settings, relative to the total volume produced within a specified period of time.

At the top level the OEE KPIs are shown for the complete building. Each OEE KPI lists also the details. For instance, for the Availability KPI the hours of unplanned, planned and total run time are shown.

Since the number of unplanned downtime hours is very high, the next step is to find out which equipment is experiencing high levels of unplanned downtime. Examining the floor plan shows that the lobby chiller is in the red zone.

At the same time the bar graph below shows that the main reason for the downtime is due to number of assist hours.

Clicking on the assist bar shows that the lobby chiller contributes to nearly 100% of the assist hours.

Further drill-down from here is possible into the exact reason(s) for the high number of assist hours, depending on the number of drill-down levels for assists configured in GEMBO Precare

GEMBO PRECARE Agents

GEMBO Precare deploys agents which can talk directly to equipment controllers over a host of different physical interfaces and protocols. The key agent features are listed below:

Real-time data acquisition . GEMBO Precare agents collect any equipment vital data in real-time for overall equipment health analysis and trends.
Any equipment vitals. Whichever is needed to be monitored, including abnormal power supply voltage fluctuations, unusual fan noise, abnormal vibrations caused by fan blades and other moving parts, leakages of oils, refrigerants, etc. camera images of objects obstructing fans, corrosion of critical elements, etc
Any connectivity . Equipment vitals may be collected through sensors on GEMBO Precare agent hardware, from the equipment’s own programmable logic controllers or through a combination of both.
Low latency . GEMBO Precare agents run on microprocessors which reside in the same location as the equipment, performing on the spot anomaly detection, complex event processing and other latency-sensitive tasks.
Machine learning . GEMBO Precare agents stream data to the GEMBO Precare cloud platform, where machine learning models are trained for predictive maintenance. .

GEMBO Precare agents connect to your choice of private, public or hybrid cloud, where the data can be used to train machine learning models, visualize KPIs and other data, issue alarms and periodic reports.

Conclusions

GEMBO Precare has a set of powerful data acquisition, analytics, predictive and OEE tools for industrial and commercial HVAC systems. GEMBO Precare gathers, analyzes and presents critical and actionable data plus key performance indicators (KPIs) before a system, subsystem or component reaches its breaking point. In addition GEMBO Precare collects important data which can significantly reduce maintenance and repair time, as well as truck rolls. HVAC OEMs and service partners using GEMBO Precare have a set of powerful tools at their fingertips to minimize OpEx and boost customer satisfaction. And last but not least, GEMBO provides flexible hosting options with your choice of private, public or private/public hybrid cloud hosting options.

Cloud vs. On Premise

Sun, 27 Feb 2022 00:08:05 GMT

Introduction

Corporations have a choice these days of hosting their IT infrastructure and services on premise or in the cloud. Companies providing IT infrastructure hosting services in the cloud have come a long way since the early days. Among the big players are well-known names such as Amazon AWS, IBM Cloud, Microsoft Azure, Google Cloud, Rackspace, Alibaba Cloud, TenCent Cloud and Baidu Cloud to name a few. Today the major players offer exceptional levels of availability, performance, quality and elasticity at price levels that are hard to compete with compared to on premise servers.

The GEMBO PRECARE Platform supports both cloud and on premise installations. This white paper discusses the pros and cons of both approaches.

Cloud and on Premise Pros and Cons

KPI Cloud On-Premise

Elasticity/Scalabilty ✔ Pay only for the amount of compute power,storage and bandwidth you consume at any moment in time. Grow as you need and pay based on what you use. ✘ Difficult to forsee compute,storage and bandwidth needs with fixed cost regardless of usage levels. Need to invest upfront

Supportability/Quality ✔ Get instant access to new products and services and to software updates with bug fixes and new features. Either no administration costs or significantly reduced. ✔-- Upfront costs and delays for bug fixes, new features, new products and new services is high and requires lengthy justifications. Personnel & maintenance costs.

Availability ✔ Get at least 99.99% uptime through redundancy and a continuous push for 99.999% and higher (Premium features). ✘ Achieving 4 or 5-nines availability is possible, but comes at a high cost for redundancy and man power.

Performance ✔ Get required throughput instantly, regardless of traffic loads at any period in time through dynamic load balancing. ✘ Require significant pre investment, hard to scale up instantly, requires new CapEx outlays with lengthy justifications.

Security ✔ Get high levels of protection against hackers with multi-factor authentication, latest threat detection and protection against ransomware. In Some cases leave the data on Premise and exchange only Metadata. ✔ Data Stays On Premise. Get high levels of protection against hackers, but requires extra investments in software (and hardware) and man power. Ransomware can wreak havoc.

Backups ✔ Get the same level of backup functionality and flexibility as on-premise, but with added advantage of not having to worry to run out of storage. ✔- Same as for the cloud, but there is the possibility that more storage is needed than available.

Control ✔- Control based on the permissions allowed by the cloud provider and application provider. ✔ Complete Control, limited only to the specific organization department restrictions.

Manageability & Access ✔ Manage compute, storage and bandwidth resources from anywhere from any device ✘ Usually restricted to on premise management of compute, storage and bandwidth resources.

KPI	Cloud	On-Premise
Elasticity/Scalabilty	✔	Pay only for the amount of compute power,storage and bandwidth you consume at any moment in time. Grow as you need and pay based on what you use.	✘	Difficult to forsee compute,storage and bandwidth needs with fixed cost regardless of usage levels. Need to invest upfront
Supportability/Quality	✔	Get instant access to new products and services and to software updates with bug fixes and new features. Either no administration costs or significantly reduced.	✔--	Upfront costs and delays for bug fixes, new features, new products and new services is high and requires lengthy justifications. Personnel & maintenance costs.
Availability	✔	Get at least 99.99% uptime through redundancy and a continuous push for 99.999% and higher (Premium features).	✘	Achieving 4 or 5-nines availability is possible, but comes at a high cost for redundancy and man power.
Performance	✔	Get required throughput instantly, regardless of traffic loads at any period in time through dynamic load balancing.	✘	Require significant pre investment, hard to scale up instantly, requires new CapEx outlays with lengthy justifications.
Security	✔	Get high levels of protection against hackers with multi-factor authentication, latest threat detection and protection against ransomware. In Some cases leave the data on Premise and exchange only Metadata.	✔	Data Stays On Premise. Get high levels of protection against hackers, but requires extra investments in software (and hardware) and man power. Ransomware can wreak havoc.
Backups	✔	Get the same level of backup functionality and flexibility as on-premise, but with added advantage of not having to worry to run out of storage.	✔-	Same as for the cloud, but there is the possibility that more storage is needed than available.
Control	✔-	Control based on the permissions allowed by the cloud provider and application provider.	✔	Complete Control, limited only to the specific organization department restrictions.
Manageability & Access	✔	Manage compute, storage and bandwidth resources from anywhere from any device	✘	Usually restricted to on premise management of compute, storage and bandwidth resources.

Conclusion

It’s no surprise that cloud computing has grown in popularity as much as it has, as its allure and promise offer newfound flexibility for enterprises, everything from saving time and money to improving agility and scalability. On the other hand, on-premise software – installed on a company’s own servers and behind its firewall – was the only offering for organizations for a long time and may continue to be so in cases where a static IT infrastructure environment serves the organization adequately.

Often on-premise advocates cite a sense of security in favor of on-premise over cloud because of the level of control they profess to maintain. Truth is that actually Cloud today has top and up to date security measures, in many cases superior to any organization. Finally, leveraging the benefits of the cloud as laid out in this white paper, for on-premise, is only feasible when the business itself is large enough to sustain the cost that is inherent with running a large IT infrastructure. For all other use cases, the cloud is a clear winner over on-premise.

The GEMBO PRECARE Platform supports both cloud and on premise Installations. Customers must weigh the pros and cons of both and decide based on which pros carry the most weight for them.

GEMBO Complex Event Processing for Industry 4.0 Applications

Sun, 27 Feb 2022 00:08:03 GMT

The GEMBO PRECARE platform enables manufacturers to seamlessly make the transition to Industry 4.0, while keeping their investments in legacy machines; thus, being able to tap into the potential of real-time access to sensor data in order to improve efficiency, productivity and quality.

Real-time access to process data is made possible through the deployment of sensors and is crucial in process control and monitoring. Complex event processing, or CEP in short, at the edge of the cloud or at the machine itself requires hardware platforms with adequate processing power. GEMBO Precare supports edge processing of sensor data through the use of powerful GEMBO Agents. These agents support a wide variety of embedded hardware platforms based on ARM, MIPS and x86 embedded processors, as well as embedded OSes, such as various Linux flavors and real-time OSes. Furthermore, GEMBO Agents can also take advantage of programmable hardware, such as FPGAs, and accelerators, such as DSPs.

Another important benefit derived from real-time access to machine performance data is the ability to perform data analytics and to apply machine learning techniques to spot trends which can predict when to schedule maintenance. The benefit of predictive maintenance over planned maintenance is that the former reduces the amount of down-time of the machine, since it’s no longer being serviced at regular intervals regardless of the actual performance or condition of the machine, but only in case of reaching a preset maximum tolerance level, the timing of which can be predicted from trends over time in the data patterns of the machine.Thus, predictive maintenance increases overall equipment effectiveness, or OEE in short.

Motors used in machines and production processes are very common and the ability to monitor them in real-time is understandably of crucial importance. GEMBO has developed an end-to-end motor control and monitoring solution in collaboration with Intel and B&R Automation, that takes advantage of the versatile and powerful GEMBO Agents for CEP at the edge and the GEMBO Precare cloud platform for monitoring and predictive maintenance. The process diagram shown below depicts a flow control application example. Control of a pump controls the flow rate in a pipe, and a safety valve prevents overpressure inside the pip

The system diagram for the monitoring of these parameters and controlling the motor and the safety valve is shown below.

A PCIe add-on card with an Intel Cyclone V SoC FPGA performs the actual motor control and sensing of motor current consumption, RPM and temperature. An X20CP PLC from B&R Automation monitors vibration and acoustic noise. An Intel Skylake x86-based computer runs the GEMBO Agent and provides the communication link over Ethernet with the GEMBO PRECARE platform running in the cloud. This computer functions at the same time as a gateway and communicates over Ethernet with the B&R Automation X20CP PLC.

A GEM Agent runs on the embedded ARM processor in the the Cyclone V FPGA, collecting the motor parameters. An other GEMBO Agent runs in OPC-UA client mode on the computer based on the Intel Skylake CPU. This agent collects the sensor data coming from the GEMBO Agent on the FPGA and from the B&R Automation X20CP PLC. This PLC runs in OPC-UA server mode. The OPC-UA client/server model adds the benefit that all communication between the different entities in the network conform to open industry standards.

The complex event processing (CEP) rules implemented for the control of the motor are as follows:

If motor temperature exceeds temperature threshold level 1 and motor RPM exceeds RPM threshold, then the GEMBO Agent will start reducing the RPM; the GEMBO PRECARE platform will display a high temperature alarm and the action undertaken by the GEMBO Agent to prevent a catastrophic failure, until the temperature has dropped again below temperature threshold level 1.
If motor temperature exceeds temperature threshold level 2 and motor RPM exceed RPM threshold, then the GEMBO Agent will immediately reduce the motor RPM to zero and simultaneously open the safety valve to relieve pressure in the pipe; the GEMBO PRECARE platform will display a catastrophic high temperature alarm and the action undertaken by the GEMBO Agent, until the temperature has dropped again below temperature threshold level 1.
If motor RPM exceeds RPM threshold and pipe pressure exceeds pressure threshold 1, then the GEMBO Agent will start reducing the RPM; the GEMBO PRECARE platform will display a high pressure alarm and the action undertaken by the GEMBO Agent to prevent a catastrophic failure, until the pressure has dropped again below pressure threshold level 1.
If motor RPM exceeds RPM threshold and pipe pressure exceeds pressure threshold 2, then the GEMBO Agent will immediately reduce the motor RPM to zero; the GEMBO PRECARE platform will display a catastrophic high pressure alarm and the action undertaken by the GEMBO Agent, until the pressure has dropped again below pressure threshold level 1.

Transition to Industry 4.0 with GEMBO Precare

Sun, 27 Feb 2022 00:08:01 GMT

The GEMBO PRECARE platform offers manufacturers the ability to easily access critical operational data in real-time from the production floor. GEMBO PRECARE can be used in a private, public or hybrid cloud setting and combines powerful, best-in-manufacturing edge processing, analytics and predictive and preventive maintenance capabilities with versatile and user-friendly dashboards. These give operators a unified presentation across all machines instead of having to deal with different man-machine interfaces for each machine. GEMBO PRECARE’s machine learning, analytics and predictive and preventive maintenance features help manufacturers drastically reduce machine downtime, hence positively affecting quality control, productivity and revenues.

Unified Interface for all Machines Across the Factory Floor

Digital Twins (Cyber Physical Systems)

GEMBO agents provide operators with a digital twin of their machines on the production floor. These are equivalent to cyber physical systems in Industry 4.0 parlance. GEMBO agents interface upstream with the GEMBO PRECARE platform through Ethernet and downstream with production floor machinery. The downstream interface can be over different physical connections, not just Ethernet, but for instance UART or any other serial or parallel connection. Agent downstream connections can be with a machine, a PLC which controls the machine, or with physical sensors. Any combination of these is supported as well. GEMBO agents define sensors as any port they receive factory data from. This can be for instance from a physical sensor, but also from a data file on a PLC or a networked data store on the factory floor.

Hardware, OS and Protocol Agnostic

GEMBO agents support a wide choice of different hardware platforms, including PCs, mobile devices, custom hardware, CPUs, FPGAs, etc., Linux and Microsoft Windows operating systems, as well as a large number of different protocols, legacy and new, such as RS-485/232,IEEE 1284, SCADA, SECS/GEMBO , OPC-UA, MQTT, etc. This means that GEMBO is able to support any production machine in use, legacy or new. This is a huge benefit to manufacturers, since they can extend the life of their legacy machines as they transition to Industry 4.0 compliant manufacturing systems. In addition, GEMBO agent hardware platforms support high-speed data acquisition and enhanced, complex processing at the edge, including sensor signal processing, machine learning and complex event processing, hence rising to the challenge of meeting the most demanding customer requirements.