Proceedings of the 10th International Conference on Modeling and Applied Simulation (Eds. A.G.Bruzzone, C.Frydman, M.Masei, M.McGinnis, M.A.Piera, G.Zacharewicz), pp. 80-89, Universitá di Genova, Genoa, Italy, 2011
A. Kuhn1, T. Palau1, G. Schlager1, H.J. Böhm2, S. Nogales2, V. Oancea3, R. Roy3, A. Rauh4, J. Lescheticky4>BR>
1ANDATA GmbH, Hallein, Austria
2Institute of Lightweight Design and Structural Biomechanics,
TU Wien, Vienna, Austria
3ABAQUS SIMULIA, Providence, RI, USA
4BMW AG, Munich, Germany
Due to the increasing usage of complex materials in lightweight design the
development of proper material models for the prediction of damage and failure
within Finite Element simulations has become an extensive task.
Other fields of application already have shown that the introduction of Soft
Computing and Machine Learning methods can be very beneficial for getting the
complexity under control.
The contribution aims at sketching a systematic approach to the application of
machine learning methods in the field of material modelling.
The focus is put not only on the definition of well performing mathematical
models, but also on process aspects of generating and maintaining the
mathematical models within reproducible, requirement-driven and controlled
iterative environments for Computer Aided Engineering.