Development and Implementation of an ANN Based Flow Law for Numerical Simulations of Thermo-Mechanical Processes at High Temperatures in FEM Software

Numerical methods based on finite element (FE) have proven their efficiency for many years in the thermomechanical simulation of forming processes. Nevertheless, application these to new materials requires identification and implementation constitutive flow laws within FE codes, which sometimes pose problems, particularly because strongly non-linear character behavior materials. Computational techniques machine learning artificial neural networks are becoming more important development models help codes integrate complex behavior. In this paper, we present development, use an network (ANN) law a GrC15 alloy under high temperature solicitations. The modeling by ANN shows significant superiority terms model prediction quality compared classical approaches widely used Johnson–Cook or Arrhenius models. Once parameters been identified base experiments, code promising results solution respect material