The TU/e offers a PhD position with the DIGITAL TWIN research program. This NWO AES Perspectief programme is a five-year comprehensive research programme on the development of digital twin and digital twinning methods, financed by the Dutch Research Council (NWO) within the domain of Applied and Engineering Sciences (AES). This collaborative programme involves six universities: University of Groningen, Eindhoven University of Technology, TU Delft, University of Twente, Leiden University and Tilburg University and ten industrial partners and two research institutes.
The development of reliable and agile digital twins of high-tech systems and materials is key to enabling shorter time-to-market, zero-defect and flexible manufacturing systems with accurate predictive maintenance. This crucial development is currently hampered by the lack of synergy between model-based engineering and data-driven/artificial intelligence approaches. The DIGITAL TWIN program will develop key-enabling technologies for full digitization of the value chain of high-tech systems and materials by the integration of data-driven learning approaches and model-based engineering methods.
One of the projects (involving three PhD projects) within the DIGITAL TWIN program focusses on Technology Health Management. In this scope, the open PhD position at TU/e is
on Hybrid model-data approach for machine level anomaly detection and isolation.
The reliable functioning of high-tech systems relies on the predictive maintenance technologies. In support of predictive maintenance, techniques for fault detection (is a fault occurring?) and fault isolation (what is source of the fault?) are key prerequisites. Therefore, this project aims to develop novel techniques for detection and isolation of anomalies in high-tech system behaviour. Existing approaches typically either take 1) a model-based approach in which model behaviours of a healthy system are compared to measured data to detect the fault or 2) a purely data-based approach, in which correlation between system degradation and measured performance data is based on past data. Neither is suitable to guarantee accurate anomaly detection for complex systems operating in uncertain and changing environments.
This project envisions to develop a hybrid approach combining the strengths of both models and data. The strength of the model ingredient is that physics-based insight is firmly embedded in the detection strategy warranting the validity of the approach, also in scenarios in which system parameters may change. The strength of using data is twofold: 1) using learning techniques employing measured machine data, the healthy model parameters can be tuned online and/or 2) the design of the detection mechanisms can be tuned online based on data to secure reliable detection.
Within this PhD project a collaboration with the high-tech companies ASML (developing lithography machines), Canon Production Printing (developing industrial printers) and VDLETG (developing, a.o., robotic equipment) will be fostered.
People involved in supervision:
The starting dates are flexible but before January 2021.
Moreover, the project will offer to the students an extensive training program on Systems and Control in the scope of the Dutch Institute for Systems and Control (http://disc.tudelft.nl/). Moreover, a training program focusing on more generic and transferable skills required by professional researchers is offered. This provides the students with a solid background for their research and future careers.
The candidate should have
Interviews with the selected PhD-candidates will take place on-site at TU/e in theNetherlands (if restrictions associated to the Covid-19 situation permit).
Do you recognize yourself in this profile and would you like to know more?
Please contact prof.dr.ir. Nathan van de Wouw (n.v.d.wouw[at]tue.nl)
More information about terms of employment can be found here.
Please visit www.tue.nl/jobs to find out more about working at TU/e!
We invite you to submit a complete application by using the 'solliciteer nu'-button on this page. The application should include a:
We look forward to your application and will screen it as soon as we have received it. Screening will continue until the position has been filled.
We do not respond to applications that are sent to us in a different way. Please keep in mind you can upload only 5 documents up to 2 MB each. If necessary please combine files.