A systematic optimization approach in the MISO Plastic Injection molding process

In this research, Taguchi method, back-propagation neural networks (BPNN), and genetic algorithms (GA) are applied to the problem of process parameter settings for multiple-input single-output (MISO) plastic injection molding. Taguchi method is adopted to arrange the number of experimental runs. Injection time, velocity pressure switch position, packing pressure, and injection velocity are engaged as process control parameters, and product weight as the target quality. Experimental data from Taguchi method are used to train and test BPNN. Engineering optimization concepts are employed to establish the fitness function for using in GA. Then, BPNN and GA are applied for searching the final optimal parameter settings. Two confirmation experiments are performed to verify the effectiveness of the proposed approach. Experimental results reveal that the proposed approach not only can avoid shortcomings inherent in the commonly used Taguchi method but also can result in significant quality and cost advantages.