Material Modelling for the Simulation of Microforming Processes at Elevated Temperature

The main objectives of this paper are investigations on the usability of artificial neuronal networks for the calculation of material properties at elevated temperatures in case of microforming processes. Modelling of the rheological behaviour of diverse materials subjected to hot forging is attempted through a parallel distributed processing paradigm based on artificial neural network prediction of the metal material response. The evaluation of different feed-forward back-propagation neural networks for flow stress prediction was carried out on the basis of laboratory data of the stress-strain behaviour of nickel base superalloys and mild steel subjected to compression tests with different temperature and strain rate conditions. The results obtained displayed a good agreement with the experimental data, showing that the neural network approach can accurately describe the material flow stress under the considered processing conditions.