Modeling the Mechanical Properties of Heat-Treated Mg-Zn-RE-Zr-Ca-Sr Alloys with the Artificial Neural Network and the Regression Model

In this study, an artificial neural network approach and a regression model are adopted to predict the mechanical properties of heat-treated Mg-Zn-RE-Zr-Ca-Sr magnesium alloys. The dataset for (ANN) modeling is generated by investigating microhardness alloys using Vickers hardness tests. A back-propagation (BP) established experimental data that enable prediction as function composition heat treatment process. input variables BP Ca Sr contents, ageing temperature time. output variable corresponds microhardness. optimal acquired optimizing number hidden layer nodes. results indicate reliable correlation coefficient above 0.95 architecture (4-8-1), which has high level accuracy prediction. addition, second-order polynomial developed based on least squares method. determination coefficients Fisher’s criterion capable Furthermore, supplemental experiments conducted check model, suggesting predictions well in accordance with results. Therefore, both models have predicting