Multi-fidelity surrogate modelling of multispeed transmissions for fast and accurate e-powertrain design and control optimization

am Institut für Mechatronische Systeme im Maschinenbau


The joint design and control optimization issue of electric powertrains is a highly complex one, which we typically try to solve using mathematical models. On the one hand, we want to have accurate models of the components, but this comes at the price of a higher computational cost. On the other hand, convex models are more easily scalable, but have higher modeling errors. Surrogate models, which predict the influence of the design on the behavior of a system based on a small number of samples in the design space, have the potential of combining the best of those two worlds.

Bild: IMS