An integrated parameter optimization system for MIMO plastic injection molding using soft computing

This study proposes an integrated optimization system to find out the optimal parameter settings of multi-input multi-output (MIMO) plastic injection molding (PIM) process. The system is divided into two stages. In the first stage, the Taguchi method and analysis of variance (ANOVA) are employed to perform the experimental work, calculate the signal-to-noise (S/N) ratio, and determine the initial process parameters. The back-propagation neural network (BPNN) is employed to construct an S/N ratio predictor and a quality predictor. The S/N ratio predictor and genetic algorithms (GA) are integrated to search for the first optimal parameter combination. The purpose of this stage is to reduce the process variance. In the second stage, the quality predictor is combined with particle swarm optimization (PSO) to find the final optimal parameters. The quality characteristics, product length and warpage, are dedicated to finding the optimal process parameters. After the numerical analysis, the optimal parameters can meet the lowest variance and the product quality requirements simultaneously. Experimental results show that the proposed optimization system can not only satisfy the quality specification but also improve stability of the PIM process.