Generalised hardening plasticity approximated via anisotropic elasticity: A neural network approach Original Research Article

The present paper deals with a method which replaces an anisotropic hardening plasticity problem through an appropriate sequence of anisotropic elasticity problems. The developed method is a parameter identification method realized in an appropriate neural network environment via supervised and unsupervised learning algorithms. Numerical examples concerning the prediction and/or the correction of interpolated or extrapolated yield surfaces in accordance to given experimental data to the elliptic paraboloid failure surface illustrate the method developed.