Zoek in de site...

Multivariate sensor lag identification for chemical production plants

Supervisor: Dr. Tim Offermans

The focus of the internship is to improve current methodology for data-driven localization of sensors in an industrial production stream to benefit multivariate process analysis. Multivariate modelling of data from sensors in a production stream can provide unprecedented process monitoring and control opportunities, but the data has to be adequately preprocessed. One relevant preprocessing step is to correct the data for delays in the production stream. This to make sure that the measurements from the different sensors analyzed all relate to the same portion of product, rather than the same production time. If for instance the production time between sensor A and B is 10 minutes, then the data from sensor A should be shifted 10 minutes forward with respect to sensor B. Detecting these shifts automatically for multiple sensors is a non-trivial task that requires dedicated methodology. In this case study, current methods for such shifts are explored and improved for a demonstrator case, with the explicit goal of improving multivariate statistical (path) models that can be readily used for automated process control and monitoring, and that will facilitate better process understanding. The study specifically focuses on a food processing facility owned by, and is performed in close collaboration with, Unilever.

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.