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. Both methods use the small punch test to measure the material response under loading. The resulting load displacement curve contains information about the deformation behavior of the tested material. The finite element method is used to calculate the load displacement curve of the punch depending on the parameters of a material law. Via a systematical variation of the material parameters a data base is built up, which is used to train neural networks. This networks can be used either as an inverse function for the determination of material parameters from a measured load displacement curve or as a function approximating directly the finite element solution. 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. Both methods are described in detail and results are discussed.
small punch test, neural networks, ductile materials, finite elements, parameter identification
M. Abendroth, M. Kuna, Determination of ductile material properties by means of the small punch test and neural networks, Advanced Engineering Materials, 6(7), 536-540, 2004