Quantitative Relationship Analysis of Mechanical Properties with Mg Content and Heat Treatment Parameters in Al–7Si Alloys Using Artificial Neural Network

In this paper, an artificial neural network (ANN) model with high accuracy and good generalization ability was developed to predict and optimize the mechanical properties of Al⁻7Si alloys. The quantitative correlation formulas of the mechanical properties with Mg content and heat treatment parameters were established based on the transfer function and weight values. The relative importance of the input variables, Mg content and heat treatment parameters, on the mechanical properties of Al⁻7Si alloys were identified through sensitivity analysis. The results indicated that the mechanical properties of Al⁻7Si alloys were sensitive to Mg content and aging temperature. Then the individual and the combined influences of these input variables on the properties of Al⁻7Si alloys were simulated and the process parameters were optimized using the artificial neural network model. Finally, the proposed model was validated to be a robust tool in predicting the mechanical properties of the Al⁻7Si alloy by conducting experiments.