Authors: Andreas Kuhn, Toni Palau, Gerolf Schlager, Helmut Böhm, Sergio Nogales, Victor Oancea, Ritwick Roy, Andrea Rauh, Jürgen Lescheticky
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.