Abstract
This paper describes an approach based on artificial neural networks to identify the material parameters of a stainless steel material. The experimental method of the bulge test is used to determine the material response under loading. The resulting pressure–displacement curve is transferred to a neural network, which was trained using pressure–displacement curves generated by finite element simulations of the bulge test and the corresponding material parameters. During a training process the neural network generates an approximated function for the inverse problem relating the material parameters to the shape of the pressure–displacement curve of the bulge test. The bulge test with a circular die is used to identify the strain-hardening curve, the one with an elliptical die for an off axis angle of 0° is used to identify the Lankford's coefficients and the one with an elliptical die for an off axis angle of 45° is used for the validation of the material parameters’ identification.