{"id":3912,"date":"2022-03-18T13:18:03","date_gmt":"2022-03-18T05:18:03","guid":{"rendered":"https:\/\/ascendas-asia.com\/?page_id=3912"},"modified":"2025-01-06T11:32:22","modified_gmt":"2025-01-06T03:32:22","slug":"mondi-pdm-using-machine-learning","status":"publish","type":"page","link":"https:\/\/ascendas-asia.com\/th\/customer-stories\/mondi-pdm-using-machine-learning\/","title":{"rendered":"Mondi Implements Statistics-Based Health Monitoring and Predictive Maintenance for Manufacturing Processes with Machine Learning"},"content":{"rendered":"
\n

Mondi Implements Statistics-Based Health Monitoring and Predictive Maintenance for Manufacturing Processes with Machine Learning<\/span><\/p>\n

\n

\u201cMathWorks Consulting\u2019s support is among the best I\u2019ve seen; the consultants are fast and exceptionally knowledgeable. We\u2019ve already seen a positive return on investment from cost savings, and now we have more budget and time to complete more machine learning projects that will provide similar benefits.\u201d<\/span><\/em><\/span><\/p>\n

\u200b<\/span><\/span> – Dr. Michael Kohlert, Mondi<\/span><\/span><\/span><\/em>\u200b<\/span><\/span><\/span><\/p>\n

\n

\"https:\/\/www.mathworks.com\/videos\/mondi-gronau-develops-a-predictive-maintenance-and-process-monit-1481048845257.html\"<\/span><\/p>\n

Watch Video<\/span><\/a><\/p>\n

Mondi Gronau is a leading international manufacturer of packaging and paper products. The company\u2019s plastic production plant delivers about 18 million tons of plastic and thin film products annually. The plant\u2019s 900 workers operate approximately 60 plastic extrusion, printing, gluing, and winding machines 24 hours a day, 365 days a year. \u200b<\/span><\/span><\/p>\n

Machine failures that result in downtime and wasted raw materials cost Mondi millions of euros each month. To minimize these costs and maximize plant efficiency, Mondi developed a health monitoring and predictive maintenance application. The application uses advanced statistics and machine learning algorithms to identify potential issues with the machines, enabling workers to take corrective action and prevent serious problems.<\/span><\/p>\n

\u200b<\/span>Mondi developed the application in MATLAB\u00ae with support from MathWorks Consulting and Prof. Dr.-Ing. Andreas K\u00f6nig, holder of the Chair for Integrated Sensor Systems (Department of Electrical Engineering and Computer Engineering at the Technical University of Kaiserslautern).<\/span><\/p>\n

\u201cAs a manufacturing company we don\u2019t have data scientists with machine learning expertise, but MathWorks provided the tools and technical know-how that enabled us to develop a production preventative maintenance system in a matter of months,\u201d says Dr. Michael Kohlert, head of information management and process automation at Mondi.<\/span><\/p>\n<\/div>\n

\n
\"mondi.jpg\"<\/span><\/div>\n<\/div>\n
\n

One of Mondi Gronau\u2019s plastic production machines, which deliver about 18 million tons of plastic and thin film products annually.<\/span><\/p>\n

<\/span><\/div>\n

\n

Challenge\u200b<\/span><\/span><\/p>\n

The extrusion and other machines at Mondi\u2019s plant are large and complex, measuring up to 50 meters long and 15 meters high. Each machine is controlled by up to five programmable logic controllers (PLCs), which log temperature, pressure, velocity, and other performance parameters from the machine\u2019s sensors. Each machine records 300\u2013400 parameter values every minute, generating 7 gigabytes of data daily.<\/span><\/p>\n

\u200b<\/span>Mondi faced several challenges in using this data for predictive maintenance. First, the plant personnel had limited experience with statistical analysis and machine learning. They needed to evaluate a variety of machine learning approaches to identify which produced the most accurate results for their data. They also needed to develop an application that presented the results clearly and immediately to machine operators. Lastly, they needed to package this application for continuous use in a production environment.<\/span><\/p>\n

Solution<\/span><\/p>\n

Mondi worked with MathWorks Consulting and Prof. Dr.-Ing. Andreas K\u00f6nig to develop and deploy health monitoring and predictive maintenance software in MATLAB.The Mondi team had previously set up an Oracle\u00ae database to collect data from all the machines in the plant via an Ethernet network. They used Database Toolbox\u2122 to access this database from within MATLAB. <\/span><\/p>\n

Next, the team developed MATLAB scripts to clean the data by removing outliers and invalid values. They developed an application in MATLAB to query the database and present the results graphically. For example, an operator can use the application interface to plot the pressure measured by a particular sensor over a period of minutes, hours, or weeks. \u200b<\/span>To enhance the application, they added statistical process control (SPC) capabilities that alert operators to sensor values that are outside normal operating ranges. Using Statistics and Machine Learning Toolbox\u2122 and Deep Learning Toolbox\u2122, Mondi and MathWorks consultants evaluated several machine learning techniques, including neural networks, k-nearest neighbors, bagged decision trees, and support vector machines (SVMs). For each technique, they trained a classification model using logged machine data and then tested the model\u2019s ability to predict machine problems. <\/span><\/p>\n

The tests showed that an ensemble of bagged decision trees was the most accurate model for their data. The team further enhanced the MATLAB application by updating the interface to incorporate predictions from the machine learning model. <\/span><\/p>\n

These predictions enable equipment operators to receive warnings about potential failures before they occur. Mondi then used MATLAB Compiler\u2122 to create a standalone executable version of the application, which is now used in production at the plant.<\/span><\/p>\n

\u200b<\/span><\/span>\"mondi-fault<\/p>\n

A MATLAB based HMI that enables equipment operators to receive warnings about potential failures before they occur.<\/span><\/p>\n<\/div>\n

\n

 <\/p>\n

Results\u200b<\/span><\/span><\/p>\n