Material characterization based on simulated spherical-Berkovich indentation tests

Abstract

Material properties can be extracted from load-displacement indentation curves via appropriate reverse data analysis. This reverse analysis can, however, be conveniently carried out using neural networks. We propose an artificial neural network model to extract material properties based on a simulated spherical and Berkovich indentation database. The proposed model can predict accurately the elastoplastic properties of a new set of materials. © 2009 Acta Materialia Inc.