Predicting equipment maintenance to improve industrial production efficiency

Supervisor: Dr. Tim Offermans

To improve industrial production efficiency, idle periods during which production lines are turned on but are not producing need to be minimal. Predicting breakdowns that require irregular maintenance can greatly aid in this, as this reduces waiting times for maintenances as well as energy waste. This internship will focus on the development of a new strategy by which the time until a specific maintenance can be predicted, from equipment sensor data and in real-time. The study specifically focuses on a microchip assembly line owned by, and is performed in close collaboration with, Nexperia. The envisioned strategy includes advanced methods for data importation, cleaning, preprocessing, modelling and validation that have to be carefully configured and combined. Note that some work has already been done on the development of maintenance prediction strategy, and that the internship will focus on improving this strategy on different aspects. These aspects will be clearly defined at the start of the internship.

This internship will help to increase your:

  • Experience with both fundamental and advanced chemometrics models
  • Ability to practically handle large datasets
  • Programming experience (in Matlab)
  • Ability to critically review scientific literature
  • Skill in communicating research in both spoken and written word

Moreover, it will offer you unique chance to work on a project that is on the interface of university and industry.

The length and specific objectives of the internship can be adapted to both bachelor’s and master’s internships of various lengths, in consultation with the supervisor at the start of the internship.