本研究使用近視400度隱形眼鏡殼模模具，探討隱形眼鏡殼模射出成形參數多目標最佳化之研究。研究目的為應用AI導入射出成形製程，使品質預測模型更為準確並得到最佳射出成形參數，提高產品良率。研究方法影響因子為射速、保壓壓力、保壓時間、模溫、融膠溫度、冷卻時間，品質特性為同時滿足最小Z軸翹曲與最小成形週期時間，比較田口法、期望函數、多目標基因演算法、模擬退火演算法。實驗結果，多目標基因演算法，可得到同時滿足最小Z軸翹曲16.080 mm*10-2與最小成形週期時間28.476 sec。本研究使用非接觸型的量測方法，把實際射出隱形眼鏡殼模尺寸與標準模仁外形尺寸比較的方法，與先前研究，使用模擬數據或是使用接觸型的量測方法進行尺寸補償明顯不同。量測濕片度數結果，田口法最佳化參數製作之隱形眼鏡鏡片為近視425度，期望函數為近視450度，多目標基因演算法、模擬退火演算法為近視425度。本研究使用類神經網路建立品質預測模型，並運用基因演算法最佳化類神經網路GA-ANN。另本研究自行撰寫MATLAB類神經網路程式，根據輸入，輸出項目與資料的多寡，使用MSE均方誤差值之大小判斷，自動得到最佳隱藏層與神經元之數量，達到最快收斂結果，也避免過擬合。
關鍵字：隱形眼鏡殼模、射出成形、類神經網路、多目標基因演算法、模擬退火演算法、基因演算法最佳化類神經網路

This research develops a Multi-objective optimization method with the myopia of 400 degrees contact lens shell mold for obtaining the optimized injection parameters of injection molding. This research is to integrate Artificial Intelligence (AI) into the injection molding process to increase the accuracy of the prediction model and obtain the optimal injection molding parameters for improving the product yield rate. Research methods include the Taguchi method, Desirability Function Analysis, Multi-objective Genetic Algorithm (MOGA) and Simulated Annealing (SA) Algorithm. The control factors include Injection Speed, Packing Pressure, Packing Time, Mold Temperature, Melt Temperature and Cooling Time. Experimental result of MOGA achieves the minimum warpage of Z-axis as 16.080 mm*10-2 and the minimum cycle time as 28.476 sec. This research develops a non-contact measurement method to compare with the shell mold dimension and mold core dimension. It is different from previous research of only simulation analysis or using contact measurement method for compensation. The soft contact lens and measurement results are shown that, the contact lens made by Taguchi method is myopia 425 degrees, the Desirability Function Analysis method is 450 degrees, and the MOGA and SA is 425 degrees. This research develops a Neural Network to establish prediction model, with GA to optimize the Neural Network (GA-ANN). The goal of GA-ANN is to achieve a better prediction model and obtain the optimization of injection parameters. Finally, this research develops a MATLAB Neural Network program, based on mean square error value, that can achieve the optimized hidden layer to obtain the fastest convergence and avoid overfitting.
Keywords: Contact Lens Shell Mold, Injection Molding, Neural Network, Multi objective Genetic Algorithm, Simulated Annealing Algorithm, Genetic Algorithm-Artificial Neural Network (GA-ANN).

[1] 陳建銘, "曲線近似法在非球面鏡片射出模仁之形狀誤差分析研究," 碩士, 機械工程系, 國立臺灣科技大學, 台北市, 2003.
[2] 曾淑玲, "非球面塑膠鏡片收縮誤差補償之研究," 碩士, 機械工程系, 國立臺灣科技大學, 台北市, 2005.
[3] 楊力權, "光學追跡應用於塑膠非球面鏡片收縮誤差補償分析," 碩士, 機械工程系, 國立臺灣科技大學, 台北市, 2008.
[4] 邱鈺婷, "非球面軟式隱形眼鏡之殼模射出成形研究," 碩士, 機械工程系, 國立臺灣科技大學, 台北市, 2016.
[5] 武氏蓮, "NURBS多焦隱形眼鏡設計及殼模射出成形之收縮分析研究," 博士, 機械工程系, 國立臺灣科技大學, 台北市, 2018.
[6] C.-C. Chen and S.-W. Chang, "Shrinkage Analysis on Convex Shellby Injection Molding," International Polymer Processing, vol. 23, no. 1, pp. 65-71, 2008.
[7] 史維克, "菲涅爾隱形眼鏡設計與殼模射出成形之 體積收縮分析研究," 碩士, 機械工程系, 國立臺灣科技大學, 台北市, 2020.
[8] S. Liao, W. Hsieh, J. T. Wang, and Y. Su, "Shrinkage and warpage prediction of injection‐molded thin‐wall parts using artificial neural networks," Polymer Engineering & Science, vol. 44, no. 11, pp. 2029-2040, 2004.
[9] C. Shen, L. Wang, and Q. Li, "Optimization of injection molding process parameters using combination of artificial neural network and genetic algorithm method," Journal of materials processing technology, vol. 183, no. 2-3, pp. 412-418, 2007.
[10] M. Altan, "Reducing shrinkage in injection moldings via the Taguchi, ANOVA and neural network methods," Materials & Design, vol. 31, no. 1, pp. 599-604, 2010.
[11] S. Kitayama and S. Natsume, "Multi-objective optimization of volume shrinkage and clamping force for plastic injection molding via sequential approximate optimization," Simulation Modelling Practice and Theory, vol. 48, pp. 35-44, 2014.
[12] R. Ramakrishnan and K. Mao, "Minimization of shrinkage in injection molding process of acetal polymer gear using Taguchi DOE optimization and ANOVA method," Int. J. Mech. Ind. Technol., vol. 4, no. 2, pp. 72-79, 2017.
[13] R. J. Bensingh, R. Machavaram, S. R. Boopathy, and C. Jebaraj, "Injection molding process optimization of a bi-aspheric lens using hybrid artificial neural networks (ANNs) and particle swarm optimization (PSO)," Measurement, vol. 134, pp. 359-374, 2019.
[14] S. F. Syed, J. C. Chen, and G. Guo, "Optimization of tensile strength and shrinkage of talc-filled polypropylene as a packaging material in injection molding," Journal of Packaging Technology and Research, vol. 4, no. 1, pp. 69-78, 2020.
[15] J. Heinisch, Y. Lockner, and C. Hopmann, "Comparison of design of experiment methods for modeling injection molding experiments using artificial neural networks," Journal of Manufacturing Processes, vol. 61, pp. 357-368, 2020.
[16] O. Kayabasi, "Optimization of plastic injection process using optimization techniques," Journal of Engineering Research and Applied Science, vol. 9, no. 1, pp. 1366-1373, 2020.
[17] S. Kitayama, M. Yokoyama, M. Takano, and S. Aiba, "Multi-objective optimization of variable packing pressure profile and process parameters in plastic injection molding for minimizing warpage and cycle time," The International Journal of Advanced Manufacturing Technology, vol. 92, no. 9-12, pp. 3991-3999, 2017.
[18] S. Kitayama, Y. Yamazaki, M. Takano, and S. Aiba, "Numerical and experimental investigation of process parameters optimization in plastic injection molding using multi-criteria decision making," Simulation Modelling Practice and Theory, vol. 85, pp. 95-105, 2018.
[19] 丹尼Denni, "運用田口方法、倒傳遞類神經網路、基因演算法及混合粒子群演算法與基因演算法於塑膠射出成形最佳化系統之研究," 博士, 科技管理博士學位學程, 中華大學, 新竹市, 2014.
[20] Y. Ryu, J. S. Sohn, C.-S. Yun, and S. W. Cha, "Shrinkage and Warpage Minimization of Glass-Fiber-Reinforced Polyamide 6 Parts by Microcellular Foam Injection Molding," Polymers, vol. 12, no. 4, p. 889, 2020.
[21] J. Sreedharan, A. Jeevanantham, and A. Rajeshkannan, "Multi-objective optimization for multi-stage sequential plastic injection molding with plating process using RSM and PCA-based weighted-GRA," Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, vol. 234, no. 5, pp. 1014-1030, 2020.
[22] 吳昇達, "混合物最佳配方之研究：以舒腦膠囊為例," 碩士, 工業管理研究所, 南台科技大學, 台南市, 2007.
[23] 黃騰毅, "應用資料探勘技術解決多品質混合參數實驗問題," 碩士, 商學研究所, 國立臺北商業技術學院, 台北市, 2008.
[24] D. Devarajaiah and C. Muthumari, "Evaluation of power consumption and MRR in WEDM of Ti–6Al–4V alloy and its simultaneous optimization for sustainable production," Journal of the Brazilian Society of Mechanical Sciences and Engineering, vol. 40, no. 8, p. 400, 2018.
[25] G. Derringer and R. Suich, "Simultaneous optimization of several response variables," Journal of quality technology, vol. 12, no. 4, pp. 214-219, 1980.
[26] Q. M. U. Jan, T. Habib, S. Noor, M. Abas, S. Azim, and Q. M. Yaseen, "Multi response optimization of injection moulding process parameters of polystyrene and polypropylene to minimize surface roughness and shrinkage’s using integrated approach of S/N ratio and composite desirability function," Cogent Engineering, vol. 7, no. 1, p. 1781424, 2020.
[27] 黃靖雅, "以複迴歸分析結合資料包絡法最佳化射出成形作業之翹曲、收縮與頂出時體積收縮比," 碩士, 工業工程與經營資訊學系, 東海大學, 台中市, 2010.
[28] 劉朋熹, "運用混合演算法於塑膠射出成形製程參數最佳化系統之研究," 博士, 科技管理博士學位學程, 中華大學, 新竹市, 2014.
[29] J. C. Chen, G. Guo, and W.-N. Wang, "Artificial neural network-based online defect detection system with in-mold temperature and pressure sensors for high precision injection molding," The International Journal of Advanced Manufacturing Technology, vol. 110, no. 7, pp. 2023-2033, 2020.
[30] B. Ozcelik and T. Erzurumlu, "Comparison of the warpage optimization in the plastic injection molding using ANOVA, neural network model and genetic algorithm," Journal of materials processing technology, vol. 171, no. 3, pp. 437-445, 2006.
[31] 范揚志, "應用類神經網路與基因演算法於射出成形製程參數最佳化之研究," 碩士, 科技管理研究所, 中華大學, 新竹市, 2006.
[32] W.-R. Jong, Y.-M. Huang, Y.-Z. Lin, S.-C. Chen, and Y.-W. Chen, "Integrating Taguchi method and artificial neural network to explore machine learning of computer aided engineering," Journal of the Chinese Institute of Engineers, vol. 43, no. 4, pp. 346-356, 2020.
[33] Z. Song, S. Liu, X. Wang, and Z. Hu, "Optimization and prediction of volume shrinkage and warpage of injection-molded thin-walled parts based on neural network," The International Journal of Advanced Manufacturing Technology, vol. 109, no. 3, pp. 755-769, 2020.
[34] K.-M. Tsai and H.-J. Luo, "An inverse model for injection molding of optical lens using artificial neural network coupled with genetic algorithm," Journal of Intelligent Manufacturing, vol. 28, no. 2, pp. 473-487, 2017.
[35] D. Kumar, G. Dangayach, and P. Rao, "An experimental investigation to optimise injection moulding process parameters for plastic parts by using Taguchi method and multi-objective genetic algorithm," International Journal of Process Management and Benchmarking, vol. 9, no. 1, pp. 1-26, 2019.
[36] Q. Feng, L. Liu, and X. Zhou, "Automated multi-objective optimization for thin-walled plastic products using Taguchi, ANOVA, and hybrid ANN-MOGA," The International Journal of Advanced Manufacturing Technology, vol. 106, no. 1-2, pp. 559-575, 2020.
[37] 陳姿伶, "應用模擬退火法進行普通蒸餾程序最適啟動研究," 碩士, 化學工程系, 國立臺灣科技大學, 台北市, 2014.
[38] 周鈞彥, "以模擬退火法實現太陽能最大功率追蹤系統," 碩士, 電機工程系, 國立臺灣科技大學, 台北市, 2015.