PhD in Online Intelligence for Optimal Control in MV Induction Motor Drives

Updated: over 2 years ago
Deadline: 14 Nov 2021

Are you inspired by challenging control problems in the context of high-power applications? Are you eager to apply advanced, computationally intensive control techniques in real-life industrial problems? Are you ready to break the time-scale barriers and perform machine learning and dynamic optimization in the microseconds? If yes, then look no further - this position will challenge you in every aspect.

In the Power Electronics Lab (PEL/e) of the Electromechanics and Power Electronics (EPE) Group, we are looking for an outstanding PhD candidate to work on the application of computational intelligence techniques to enhance the versatility and reliability of Medium Voltage (MV) industrial motor drives. 

The research work contributes to the Real-time Data Driven Reliability research line of our team which aims at using data and computation to enhance the reliability of power electronics systems and thus contribute to a more efficient use of electric energy. The research will be carried out in close collaboration with the R&D team of ABB Motion, System Drives Division.

Specifically, and in the context of the previously established work of applying Model Predictive Control (MPC) for induction motor drives, you will be looking into methods and tools for the online adaptation of MPC-based algorithms to counteract persistent disturbances and modelling uncertainties. The line of investigation will include pattern recognition and machine learning techniques, as well as non-linear optimization problems. This interdisciplinary area of research promises a broad spectrum of challenges, and requires a strong mathematical background, coupled with a solid knowledge of power electronics and motor drives.  

Besides research you will also contribute to education within the department. Apart from supervising BSc and MSc students in their research projects, other assistance in education, e.g. in bachelor courses, is also expected. The overall load usually amounts to around 20% of your contract time.



Similar Positions