Optimization of Process Parameters of Preparing Foamed Al-Si Alloy Based on Ga-Based BP Neural Network

Abstract

This paper analyses the dependence of the structures of foamed Al-Si alloy on the process parameters. It takes the aid of back propagation (BP) neural network theory to build the nonlinear mapping relations between the crucial process variables and the quality of pores. Then by the integrating BP neural network and genetic algorithm (GA), the optimized process parameters for high porosity of foamed Al-Si alloy can be searched. The comparisons between experiment results and neural network simulation results show that GA-based on BP method can predict the porosity with higher prediction accuracy. The effects of viscosity on the foam ability are also important. The mechanism of thickening agent has been analyzed theoretically.