塑膠射出成型製程時間最佳化設計

Optimization Design for Plastic Injection Molding Process Time

魏綸群(Lun-Chun Wei)

指導教授 ： 徐業良

元智大學/工程學院/機械工程學系/碩士(2008年)

https://doi.org/10.6838/YZU.2008.00261

摘要

本論文之目的在考量成型不良現象下，透過模糊比例微分控制器演算法求解最短塑膠射出製程時間。由於塑膠射出成型不良現象難以以外顯形式方式表示，若將其作為限制條件，一般傳統之最佳化演算法將無法處理。而模糊比例微分控制器最佳化演算法之特徵，在處理：(1)設計變數在目標函數與限制條件具有單調性；且(2)目標函數與限制條件為內隱式函數，正可用以解決此問題。本論文中同時考量充填不足、凹塌、流痕、氣泡等四種成型不良狀況，並以射出充填時間及冷卻靜置時間之和為目標。由本論文之實驗結果可以清楚得知藉由模糊比例微分控制器演算法的應用，使射出充填時間及冷卻靜置時間之和，在經過21次迭代後，快速由初始值11秒下降至1.85秒，且所得之射出成品完全符合品質標準。

關鍵字

射出成型 ； 模糊比例微分控制器

並列摘要

This paper demonstrates the result of using fuzzy PD　controller optimization engine to the plastics injection manufactory process under product quality constraints. Because of the difficulty in expressing the product quality explicitly in terms of design variables, traditional numerical optimization algorithm is hard to be used to solve plastics injection optimization problem with product quality constraints. The fuzzy PD controller optimization engine is developed to deal with the engineering design problems with two characteristics: (1) the design variables are monotonic in the objective function and constraints; (2) the objective function and constraints are implicit functions. It is certainly to use fuzzy PD controller optimization engine as the solver to solve the plastics injection optimization problem. In this paper, 4 quality defects, short shot, sink mark, flow mark and blister, are considered as design constraints. The objective function is set as the sum of the injection time and cooling time. After 21 iterations, the objective function value is reduced from 11 sec to 1.85 sec and the quality requirements are all satisfied.

並列關鍵字

plastic injection molding ； Fuzzy PD controller

參考文獻

1. Shen C., Wang L., Li Q., 2007, “Optimization of injection molding process parameters using combination of artificial neural network and genetic algorithm method,” Journal of Materials Processing Technology, Vol. 183, pp. 412-418.

2. Liao, X.P., Xie, H.M., Zhou, Y.J., Zia, W., 2007, “Adaptive adjustment of plastic injection processes based on neural network,” Journal of Materials Processing Technology, Vol. 187-188, pp. 676-679.

3. Chen,W. C., Tai, H., Wang, M. W., Deng, W. J., Chen, C. T., 2007, “A neural network-based approach for dynamic quality prediction,” Expert systems with Applications, doi:10.1016/j.eswa.2007.07.037.

4. Shie, J. R., 2007, “Optimization of injection molding process for contour distortions of polypropylene composite components by a radial basis neural network,” International journal of advanced manufacturing technology, doi:10.1007/s00170 -007-0940-0.

5. Kwak, T. S., Suzuki T., Bae, W. B., Uehara Y., Ohmori, H., 2005, “Application of neural network and computer simulation to improve surface profile of injection molding optic lens,” Journal of Materials Processing Technology, Vol. 170, pp. 24–31.