| Summary: | 碩士 === 明新科技大學 === 精密機電工程研究所 === 97 === This study analyzed variation of warpage and tensile properties depended on injection molding parameters during production of thin-shell plastic components. A hybrid method integrating artificial neural network and simulated annealing (ANN/SA) method is proposed to determine an optimal parameter setting of the injection-molding process. The specimens were prepared under different injection-molding conditions by changing melt temperature, mold temperature, injection speed, and the packing pressure. Eighteen experimental runs, based on a Taguchi orthogonal array table, were utilized to train the ANN and then the SA method was applied to search for an optimal setting. The trained ANN was capable of predicting warpage and tensile properties at various injection-molding conditions. In addition, the analysis of variance (ANOVA) was implemented to identify significant factors for the molding process and the proposed algorithm was compared with traditional schemes like the Taguchi method. The results show that the combining ANN/SA method is an effective tool for the process optimization on injection molding.
The combining ANN/SA optimization method is proposed that optimal setting can be obtained for the appropriate combinations of the injection molding parameters. Additionally, the proposed algorithm of SA approach has better prediction result than the RSM method.
|
|---|
