Machine Learning and Optimisation Applied to Sensorial Data

The aim of this project is to develop predictive maintenance models based on sensor data recorded from Tata Steel equipment. These models should be able to identify faulty behaviors in the steel pickling line’s equipment and predict failures. This way, the maintenance actions can take place at the right time.

The project is guided by the following research questions:

-Which sensors provide more relevant information for failure detection?
-How to detect a faulty behavior given the current and recent states of the equipment?
-How to predict when a failure will occur, or what is the “health” state of the equipment?

Partner

Team

Luis Pedro Silvestrin
PhD Student

Luis Pedro Silvestrin

Dr. Mark Hoogendoorn
Assistent Professor

Dr. Mark Hoogendoorn

Prof. dr. Guszti Eiben
Head of the Group

Prof. dr. Guszti Eiben