Determination of ductile material properties by means of the small punch test and neural networks

This paper compares two different methods for the identification of ductile properties of materials using the small punch test to measure the material response under loading. The finite element method is used to calculate the load displacement curve of the punch depending on the parameters of a hardening law. Via systematical variation of the material parameters a data base is built up, which is used to train neural networks. The second method allows the indentification of material parameters by using a conjugate directions algorithm, which minimizes the error between an experimental load displacement curve and one calculated by the network function.