Study on Injection Molding Parameters for Thin-Shell Plastic Parts Using a Neural Network–Based Approach

Abstract

This study analyzed variation of warpage and tensile properties depending on injection molding parameters during production of thin-shell plastic components. A hybrid method integrating back-propagation neural network (BPNN), genetic algorithm (GA), and simulated annealing algorithm (SAA) are proposed to determine an optimal parameter setting of the injection-molding process. The results of 18 experimental runs were utilized to train the BPNN predicting warpage and tensile properties at various injection-molding conditions and then the GA and SAA approaches were applied to individual search for an optimal setting. The results show that the combinations of BPNN/GA and BPNN/SAA methods are effective tool for the optimization of injection molding parameter.

Keywords:

• Genetic algorithm
• Neural network
• Optimization
• Simulated annealing
• Tensile strength
• Warpage

ACKNOWLEDGMENT

The authors would like to thank the National Science Council of the Republic of China, for financially supporting this research (Contract No. NSC97–2221–E–159–006) and Ming Hsin University of Science and Technology (Contract No. MUST–97–ME–009).