A combined FE-ANN approach for multiscale numerical modeling of composites

In this paper we show some different concepts for the use of Artificial Neural Networks (ANNs) in modelling of composites and hierarchical structures. By using virtual testing, a proper set of corresponding input-output data can be created to train neural networks to identify the effective properties. Furthermore, ANN based procedures can be exploited in a multiscale analysis as a tool for the stress recovery at lower levels of the hierarchical structure and/or to estimate the state of yielding of the materials. Finally, ANNs may be used to define the homogenized properties for a class of parameterized unit cells or when material characteristics depend upon a parameter (e.g. temperature, damage etc.).