Optimization of Die-casting Process of AlSi7Mg Aluminum Alloy for Automobile Based on Artificial Neural Network

An artificial neural network model of die-casting process with high precision and universal AlSi7Mg aluminum alloy was established, and the casting properties of the AlSi7Mg alloy were optimized. The correlation of input variables on mechanical properties of AlSi7Mg alloy was determined by correlation analysis. The results show that the mechanical properties of as-cast AlSi7Mg alloy are most sensitive to Mg element content. The order of correlation of different die-casting parameters on the mechanical properties of the alloy is Mg element content ＞＞ casting temperature ＞ die preheating temperature ＞ fast filling speed. Finally, the influence of Mg element content on the mechanical properties of as-casting AlSi7Mg alloy is predicted, and it is concluded from the results that the optimal Mg element content should be 0.35wt%-0.45wt%.