Logo Uni Bremen

Center for Industrial Mathematics

ZeTeM > Research and Applications > Projects > HYDAMO - Hybrid data-driven and model-based simulation of complex flow problems in the automotive industry

Contact Sitemap Impressum [ English | Deutsch ]

HYDAMO - Hybrid data-driven and model-based simulation of complex flow problems in the automotive industry

Working Group:WG Industrial Mathematics
Leadership: Prof. Dr. Dr. h.c. Peter Maaß ((0421) 218-63801, E-Mail: pmaass@math.uni-bremen.de )
Funding: BMBF, Mathematik für Innovationen
Project partner: Prof. Dr Axel Klar, Technische Universität Kaiserslautern
Dr. Jörg Kuhnert, Fraunhofer ITWM, Kaiserslautern
Dr.-Ing. Lars Aschenbrenner, Volkswagen AG Wolfsburg
Dr. Matthias Schäfer, ESI Software Germany GmbH, Neu-Ienburg
Time period: 01.04.2020 - 31.03.2023
Bild des Projekts HYDAMO - Hybride datengetriebene und modellbasierte Simulation komplexer Strömungsprobleme in der Fahrzeugindustrie There are essentially two different paradigmatic approaches to mapping complex physical processes: classical physical modelling with associated numerical simulation (model-based) and prognostic methods based on the analysis of large amounts of data (data-driven). In recent years, the efficient combination of both approaches has become a major research topic. However, research is far from an interlocking, problem-adapted application of the principles. The aim of HYDMAO is to integrate data-driven and model-based approaches into a complete solution based on a previously insufficiently understood continuum mechanical problem from the automotive industry. This is intended to significantly improve the computer-aided mapping of the associated process. For this purpose, a prototypical example with great industrial and social importance is considered: The interaction of a vehicle with complex materials like sand, mud or snow. Vehicle stability is not always guaranteed on such surfaces: Collisions or rollover of the vehicle may be unavoidable. These situations must be handled accordingly in the interests of occupant safety. In particular, the question arises as to whether, when and which airbags should be triggered. This problem can only be solved efficiently by a suitable computer-based mapping of the process. Our application partners Volkswagen AG and ESI Software Germany GmbH underline the general relevance of the project, which goes far beyond the prototype example. The sub-project "Parameter Identification of Complex Nonlinear Dependencies" of the University of Bremen aims at reducing the high-dimensional parameters in a generic model to their inherently nonlinear but low-dimensional structure by deep learning approaches and to identify them for the subsequent numerical simulation. The focus here is on stability analysis in addition to machine learning (ML) approaches.