Artificial Neural Network Approach for Mechanical Properties Prediction of As-Cast A380 Aluminum Alloy

In this study, the dataset of as-cast A380 aluminum alloy involving chemical composition, processing parameter and mechanical properties was experimentally established. On this basis, the prediction model of back propagation neural network optimized by particle swarm optimization (PSO-BP) was established with four inputs: Fe/Mn ratio, Sr content, cooling rate and porosity content, and two outputs: ultimate tensile strength (UTS) and elongation (EL). The results showed the established PSO-BP artificial neural network (ANN) was able to predict the mechanical properties with low root mean square errors (RMSE), 7.46 MPa for UTS and 0.18% for EL, respectively. The order of relative importance for UTS is Fe/Mn ratio, porosity content, Sr content and cooling rate, while the importance ranking for EL is Sr content, Fe/Mn ratio, cooling rate, and porosity content. The research results and dataset in this work lay a foundation for the control of casting performance in industrial practice and for secondary development of mechanical properties prediction module in commercial casting software