Plasticity including the Bauschinger effect, studied by a neural network approach

In the present paper the influence of the Bauschinger effect on the subsequent yield surfaces is investigated. The developed method replaces an anisotropic hardening plasticity problem through an appropriate sequence of anisotropic elasticity problems. The arising parameter identification problem is treated in an appropriate neural network environment via supervised and unsupervised learning algorithms. Numerical examples concerning the prediction and/or the correction of interpolated yield surfaces in accordance to given experimental data and to the elliptic paraboloid failure surface illustrate the theory.