Modeling of high temperature rheological behavior of AZ61 Mg-alloy using inverse method and ANN

Abstract

Inverse method and artificial neural network were employed in modeling the rheological behavior of the AZ61 Mg alloy. The hot deformation behavior of these alloys was investigated by compression tests in the temperature range 250–350 °C and strain rate range 0.0005–0.1 s −1. Investigation of stress–strain curves and microstructure of the compression specimen illustrate occurrence of dynamic recrystallization. To determining parameters of two suggested constitutive equations global optimization technique, genetic algorithm, was used. The predicted results by inverse method and ANN depicted a good agreement with the experimental data even if the ANN results has shown the best predicted capability.