PhD Positions Sparse Data Driven Methods for Prognosis of Electric Vehicles

The introduction of next generation heavy electric vehicles, such as electric trucks, is seen as an important contribution to worldwide efforts to curb greenhouse gases emission levels. Still, to deliver their promised performances, such novel electric vehicles should be robust to faults and be designed to optimize their maintenance.

While advanced diagnosis and prognosis algorithms that are suitable for fleets of complex vehicles are model-based, their design, tuning and validation require considerable amounts of data. Large and densely populated data sets, unfortunately, may not always be available, especially during the design phase of such vehicles. The challenge of tuning and validating diagnosis and prognosis algorithms using datasets that are sparse over time and over the vehicles’ population is precisely the motivation for the two PhD openings.

The successful candidates will carry out research as part of the project “SPARSITY: using data from sparse measurements for predictive maintenance”, which is an academic-industrial collaboration between Dr. Ferrari’s group at Delft Center for Systems and Control (TU Delft, The Netherlands) and Volvo Group, a world-leading automotive company based in Gothenburg (Sweden). Research topics will include, but will not be limited to:

adapting state-of-the-art system identification algorithms to use sparse datasets;
uncertainty quantification and propagation in complex nonlinear systems;
probabilistic methods for diagnosis and prognosis thresholds design and validation;
sensitivity analysis of diagnosis and prognosis performances with respect to data sparsity.