Optimization of injection conditions for a thin-walled die-cast part using a genetic algorithm method

Abstract

The primary objective of this research is to investigate the effect of injection parameters on porosity formation for a commercial thin-walled die-cast part of aluminium alloy. The amount and distribution of porosity in die-cast parts were examined in relation to the slow shot velocity, the fast shot set point, the gate velocity, the pressure rise time, and the intensification pressure. The effect of injection parameters on porosity formation was investigated, using multivariate linear regression (MVLR) and genetic algorithm (GA) analyses in the pressure die-casting process. The experiments were conducted using the L27 orthogonal array of the Taguchi method. The experimental results from the orthogonal array were used as the training data for the MVLR model to map the relationship between injection parameters and porosity formation. With the fitness function based on this model, the GA method was used for optimization of the injection parameters. The predicted optimum injection conditions by GA were compared with the Taguchi design results and validated with experimental measurements.