Artificial Neural Network Modeling to Evaluate and Predict the Deformation Behavior of ZK60 Magnesium Alloy During Hot Compression

Abstract

Compression tests for ZK60 magnesium alloy were carried out in the temperature range of 200 ∼400°C and strain rate range of 0.001–1s−1. A feed-forward back propagation artificial neural network with single hidden layer was established to investigate the flow behavior of ZK60 alloy. The input parameters of the model are temperature, strain rate, and strain while flow stress is the output. A network with 23 neurons in hidden layer and Levenberg–Marquardt (L-M) training algorithm has been employed. The results show that flow stress of ZK60 magnesium alloy decreases with the increase of deformation temperature and the decrease of strain rate. The flow stress curves obtained from experiments are composed of four different stages, i.e., work hardening stage, transition stage, softening stage, and steady stage, while for the relatively high temperature and low strain rate, transition stage and softening stage are not very obvious. The proposed model can delineate the flow behavior of ZK60 magnesium alloy precisely, very good agreement between experimental and predicted result has been obtained. The effect of deformation temperature and strain rate on the flow behavior of ZK60 alloy has also been investigated, and the predicted results are consistent with what is expected from fundamental theory of hot compression deformation.