PLASTICITY INCLUDING THE BAUSCHINGER EFFECT, STUDIED BY A NEURAL-NETWORK APPROACH

In the present paper the influence of the Bauschinger effect on the su bsequent yield surfaces is investigated The developed method replaces an anisotropic hardening plasticity problem through an appropriate seq uence of anisotropic elasticity problems. The arising parameter identi fication problem is treated in an appropriate neural network environme nt via supervised and unsupervised learning algorithms. Numerical exam ples concerning the prediction and/or the correction of interpolated y ield surfaces in accordance to given experimental data and to the elli ptic paraboloid failure surface illustrate the theory.