Virtual vehicle development is continuously gaining importance and will in the near future become the determining path in the product development process. In particular, complex multibody dynamic models play an important role in enhancing the model accuracy and driving experience. However, one of the main challenges consists of deriving models that match well the reality. In this talk I will present some recent ideas and trends for the system identification of high-dimensional multibody dynamical systems, which requires efficient methods that can learn the model parametrization, as well as unmodeled physics functions from data while keeping the model physically consistent.
Zoom-Link: https://rwth.zoom.us/j/94664322223?pwd=YlNMbm5vVlNTOWlnSDNCMVBZdkx3QT09
Die Datenschutzhinweise zur Nutzung von Zoom und eine Handreichung für Teilnehmer (Studierende) können von den Seiten des CLS der RWTH Aachen University heruntergeladen werden.
