About this position
In the world of modern high-tech manufacturing, increasing demand on system performance translates into an increasing need for flexibility and precision on all levels, including robotic control and machine logistics, and leads to increased complexity. With the old methods of hand-crafted modelling of machine logistics struggling to keep up with such requirements, formal modelling frameworks of machine logistics such as LSAT or dataflow graphs have become a valuable tool for design engineers. Yet, current models do not account for the inherent uncertainty of real-world processes, e.g. timing variations or unplanned maintenance, which forces designers to rely on heuristics and make compromises such as designing for worst case scenario. Significant performance could thus be gained by accounting for the system’s uncertainty sources and tracking how this uncertainty propagates, for example, by computing how unexpected delays affect the timing of successive actions and the length of the production cycle.
What will be your role?
In a model-based design of a machine’s logistics, such as those captured as LSAT or dataflow models, the scheduling of actions within given activities links closely to activity graphs found in standardized modeling languages like UML/SysML. Computing the start and end-times of nodes in such activity graphs is a key step towards analyzing the overall productivity of a flexible manufacturing system. In this project, the student will adapt and extend the modelling frameworks of LSAT and/or dataflow graphs to the computation of timings with stochastic machine behavior.
The student will be encouraged to explore different approaches to compute the stochastic timing behavior of activity graphs such as MCMC sampling, extreme value theory or variational message passing on factor graphs.
Along with theory development, the project will include implementation in code and validation on test-cases inspired by real-world cases from the Dutch high-tech industry. This master’s project will be part of the WLSAT-NG project in collaboration with TU/e, TNO-ESI, ASML and VDL-ETG.
What we expect from you
A background in electrical engineering, applied mathematics or computer science is preferable. Knowledge of probability theory, stochastic processes and/or model-based design is also strongly suggested.
The project will take place at TNO-ESI under a TNO internship contract and will be co-supervised by the Model-Based Design Lab of the Technical University of Eindhoven (TU/e) and the LSAT team at TNO-ESI.
What you'll get in return
You want an internship opportunity on the precursor of your career; an internship gives you an opportunity to take a good look at your prospective future employer. TNO goes a step further. It’s not just looking that interests us; you and your knowledge are essential to our innovation. That’s why we attach a great deal of value to your personal and professional development. You will, of course, be properly supervised during your work placement and be given the scope for you to get the best out of yourself. Furthermore, we provide: