Data Analysis and Predictive Maintenance with MATLAB and Simulink

Predictive Maintenance lets a user estimate the optimum time to do maintenance by predicting a machine’s failure time. It also identifies problems in the machinery and assists in the identification of the exact parts that need attention. This way, downtime is minimised, and the lifespan of machinery is maximised. This maintenance strategy has an overall cost reduction compared to other strategies like reactive and scheduled maintenance. In this webinar, you will learn about the general workflow of predictive maintenance models to understand the key aspects and the critical points aimed at obtaining accurate and robust algorithms. This workflow will be employed for a real case study - a flow pack machine. Using sensors and synthetic data, we will explore importing, pre-processing, and labelling data, as well as selecting features (A.K.A healthy/faulty condition indicators) aimed at training and comparing multiple machine learning models. It will also be demonstrated how MATLAB and Simulink can offer an integrated platform to design a digital twin and implement machine learning algorithms. The MATLAB environment provides dedicated capabilities to help the user to face Predictive Maintenance through a systematic approach, as well as a quick and easy interactive experience. The speaker is Dr. Marco Rossi. He is an EDU Customer Success Engineer at MathWorks. He supports professors and researchers in the use of MATLAB and Simulink for their research and teaching activities. After completing a MSc in Aeronautical Engineering from the Sapienza University of Rome, Italy, he obtained his doctorate in Mechanical Engineering from the Dresden University of Technology, Germany. His research interests are theoretical modeling and numerical simulation (finite elements) of soft materials, such as polymers and smart gels. Marco has taught many courses for the Institute of Solid Mechanics of TU Dresden, including statics and intelligent materials.