臺灣博碩士論文加值系統

安全帽的鏡片不只可以在雨天用來擋雨，更可以保護騎士在騎乘時，免受路上飛來的空中物體（沙礫、石頭、昆蟲等）對臉部或是眼睛造成傷害，因此本研究針對安全帽鏡片進行模流分析的成形最佳化，並探討各成形參數對安全帽鏡片之影響。
本研究以現有市售鏡片為參考，以逆向工程技術進行安全帽鏡片掃描建模，搭配實物測繪建立3D模型，利用Moldex3D模流分析進行射出成形加工參數模擬，再使用田口實驗方法，求得最佳化方法的成形參數組合與控制因子的貢獻度，最後再使用倒傳遞類神經網路結合基因演算法，求得最佳成形參數，並於最佳組附近再次進行倒傳遞類神經網路結合基因演算法，嘗試找出更好的最佳組。
本研究利用Moldex3D模流分析後得出：使用田口實驗方法獲得其最佳參數之模流分析結果：最大翹曲3.0580 mm、最大體縮2.7863%；使用倒傳遞類神經網路結合基因演算法之模流分析結果：最大翹曲2.9554 mm、最大體縮2.7878%，由結果可得知本研究利用倒傳遞類神經網路結合基因演算法的最佳化品質優於田口實驗方法。
。

The lenses of the helmet can be used to block the rain in rainy days, and can also protect the user's face or eyes from flying objects such as sand, gravel or insects. Accordingly, this study will focus on the molding optimization of mold flow analysis, and discuss the effects of each molding parameter to the helmet lens.
This study references a commercially available helmet lens, conducting scanning modeling by reverse engineering technology to build up a model, and then conducting mold flow analysis simulation of injection molding with Moldex3D mold flow analysis software, and then use Taguchi method to find out the optimized molding parameters and the contribution of the controlling variables. Finally discover the optimized molding parameters by utilizing Back Propagation Neural Network and Genetic Algorithm. And conduct Back Propagation Neural Network and Genetic Algorithm combination again nearby the optimized molding parameters, attempt to find the better optimized molding parameters.
Through Moldex3D mold flow analysis, the best result of optimized molding parameters from Taguchi method is 3.0580 mm max. warpage, 2.7863% max. shrinkage, while the best result of optimized molding parameters is 2.9554 mm max. warpage, 2.7878% max. shrinkage by Back Propagation Neural Network and Genetic Algorithm combination. Based on this consequent, employing Back Propagation Neural Network and Genetic Algorithm combination obtains a better result of injection molding parameters optimization than Taguchi method.

摘要 iii
ABSTRACT iv
誌 謝 vi
目 錄 vii
圖 目 錄 viii
表 目 錄 x
第一章　緒論 1
1.1前言 1
1.2射出成形 3
1.3研究動機與目的 5
1.4研究方法 6
第二章　相關理論與文獻回顧 8
2.1逆向工程 8
2.2田口實驗方法 10
2.2.1信號雜訊比 10
2.3類神經網路 12
2.4基因演算法 14
2.4文獻回顧 17
2.4.1逆向工程領域文獻回顧 17
2.4.2射出成形與田口實驗方法文獻回顧 18
2.4.3射出成形與類神經網路文獻回顧 20
第三章　實驗規劃及設計 23
3.1逆向工程掃描機 24
3.2實驗材料 25
3.3實物測繪及修改設計 28
3.4模流分析 33
3.4.1　模具設計 34
第四章　田口實驗方法與類神經網路最佳化 40
4.1選擇因子與水準 40
4.2田口實驗分析 44
4.3以倒傳遞類神經網路結合基因演算法最佳化實驗 55
4.3.1多品質預測器建立 57
4.3.2倒傳遞類神經網路結合基因演算法最佳化成形參數 63
4.4修訂參數範圍再次最佳化成形參數 66
4.4.1第二版多品質預測器建立 69
4.4.2第二版倒傳遞類神經網路結合基因演算法最佳化成形參數 74
第五章　實驗結果與討論 77
5.1逆向工程 77
5.2模流分析 78
5.3最佳化 78
第六章　結論與未來展望 80
6.1結論 80
6.2未來展望 80
參考文獻 81

[1]交通部統計查詢網，https://stat.motc.gov.tw/mocdb/stmain.jsp?sys=100，Accessed Nov. 2022。
[2]交通部道安資訊查詢網，https://roadsafety.tw/AccOrder?Order=Age&type=機車#，Accessed Nov. 2022。
[3]UNITED NATIONS, The United Nations Motorcycle Helmet Study, 2016, New York and Geneva.
[4]CMM雜誌：塑膠光學-特定射出成型塑膠光學元件，http://www.caemolding.org/cmm/optical-plastic/，Accessed Nov. 2022。
[5]D. Krevor, G. McNelly, J. Skubon and R. Speirs, 2004, “Development and Manufacture of Visor for Helmet Mounted Display”, Proceedings of the SPIE, Volume 5180, pp. 135-144.
[6]Emco Industrial Plastics, https://www.emcoplastics.com/pc-optical-grade/, Accessed Nov. 2022.
[7]M.P. Singh and A. Jaguri, 2015, “Gating System Design Optimization for Injection Moulding”, International Journal of Mechanical and Industrial Technology, Volume 3, Issue 1, pp. 156-163.
[8]黃聖智，2015，“模仁補償於口內掃描器透鏡射出成形研究”，國立高雄應用科技大學機械工程系碩士論文。
[9]A.M. Darekar, T.S. Venkatesh, B.T Patil and Y.N. Doctor, 2015, “Review of Optimization Aspects for Plastic Injection Molding Process”, Engineering Science and Technology: An International Journal, Volume 5, pp. 2250-3498.
[10]N. Divya, Ch.V.S.Parameswara Rao and S.S.N.MalleswaraRao, 2017, “Design and Analysis of Hot Runner Injection Mould for Water Bottle Caps”, International Journal of Scientific and Research Publications, Volume 7, Issue 3, pp. 44-48.
[11]Automatic Plastics Limited, http://www.automaticplastics.com/the-cycles-of-the-injection-moulding-process/, Accessed Nov. 2022.
[12]林建志，2017，“類神經網路最佳化於藍光讀取頭透鏡射出成形研究”，國立高雄應用科技大學機械工程系碩士論文。
[13]黃俊諺，2015，“雙凹球面結構之射出成形研究”，國立高雄應用科技大學碩士機械工程系論文。
[14]L. Xie, L. Shen and B. Jiang, 2011, “Modelling and Simulation for Micro Injection Molding Process”, in book：Computational Fluid Dynamics Technologies and Applications, pp. 317.
[15]SHOEI 台灣大橋總代理CWR-1鏡片，https://www.ydcmotor.com.tw/collections/cwr-1-z-7，Accessed Dec. 2022。
[16]SHOEI 台灣大橋總代理Z-7安全帽，https://www.ydcmotor.com.tw/collections/z-7，Accessed Dec. 2022。
[17]S. Dey, 2022, “Reverse Engineering in Mechanical Engineering”, Bachelor of Technology Project Report, Department of Mechanical Engineering, Future Institute of Engineering and Management, pp. 5-18.
[18]V. Raja, 2007, “Introduction to Reverse Engineering”, In book: Reverse Engineering, pp. 1-9.
[19]Creaform3d’s product MetraSCAN 3D, https://www.creaform3d.com/en/optical-3d-scanner-metrascan, Accessed Dec. 2022.
[20]蕭坤佑，2017，“自由曲面鏡片射出成形補償技術研究”，國立高雄應用科技大學機械工程系碩士論文。
[21]李輝煌，2011，“田口方法：品質設計的原理與實務”，第四版，高立圖書有限公司。
[22]何智遠，2006，“應用灰色理論與田口實驗方法於記憶體模組除料製程之品質改善與化學機械拋光參數分析”，國立臺灣科技大學機械工程系碩士論文。
[23]W.S. McCulloch and W. Pitts, 1943, “A Logical Calculus of the Ideas Immanent in Nervous Activity”, The Bulletin of Mathematical Biophysics, Volume 5, pp. 115–133.
[24]張斐章，黃浩倫，張麗秋，2001，“回饋式類神經網路於河川流量推估之應用”，農業工程學報，第47卷第2期，pp. 32-39。
[25]P.S. Othman, R.R. Ihsan and R.M. Abdulhakeem, 2022, “The Genetic Algorithm (GA) in Relation to Natural Evolution”, Academic Journal of Nawroz University, Volume 10, No 3, pp. 243-250.
[26]K. Höschel and V. Lakshminarayanan, 2018, “Genetic Algorithms for Lens Design a Review”, Journal of Optics, Volume 48, pp. 134–144.
[27]V. Raja and K. Fernandes, 2008, “Reverse Engineering: An Industrial Perspective”, Springer-Verlag London Limited.
[28]F. Menna and S. Troisi, 2010, “Low Cost Reverse Engineering Techniques for 3D Modelling of Propellers”, Conference: International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, Volume 38, part 5, pp. 452-457.
[29]M. Kainat, C. Cakiroglu, S. Adeeb and J.J.R. Cheng, 2014, “Geometric Analysis of Pipeline Elbows Through Reverse Engineering and Their Associated Imperfections”, Conference: 2014 10th International Pipeline Conference.
[30]M. Sneha, S. Reddy and L.M.A Kumar, 2019, “Reverse Engineering on Jet Engine Turbine Blade Based on 3D Printing Design Intent”, International Journal of Innovative Technology and Exploring Engineering, Volume 8, Issue 12, pp. 5806-5810.
[31]D. Palka, 2020, “Use of Reverse Engineering and Additive Printing in the Reconstruction of Gears”, Multidisciplinary Aspects of Production Engineering, Volume 3, Issue 1, pp. 274-284.
[32]A. Baručija, J. Kačmarčik, S. Lemeš and F. Unkić, 2020, “An Example of CMM and CAD Application in Reverse Engineering”, Mašinstvo, Volume 17, Issue 1-2, pp. 35-43.
[33]M. Hawryluk, J. Ziemba, M. Zwierzchowski and M. Janik, 2021, “Analysis of a Forging Die Wear by 3D Reverse Scanning Combined with SEM and Hardness Tests”, Wear, Volume 476, Article 203749, pp. 1-9.
[34]N. Čatipović, N. Gjeldum, A. Basic and A. Turković, 2021, “Using Reverse Engineering for Optimization and Modeling of Motorcycle Brake Caliper Brackets”, Conference: MTSM 2021-10th International Conference Mechanical Technogies and Structural Materials, pp. 23-24.
[35]R.H. Helle and H.G. Lemu, 2021, “A Case Study on use of 3D Scanning for Reverse Engineering and Quality Control”, Materials Today: Proceedings, Volume 45, Part 6, pp. 5255-5262.
[36]劉昭宏，2005，“非等厚塑膠光學元件收縮補償之模流分析”，國立臺灣科技大學機械工程系碩士論文。
[37]C.H. Wu and W.S. Chen, 2006, “Injection Molding and Injection Compression Molding of Three-beam Grating of DVD Pickup Lens”, Sensors and Actuators A: Physical, Volume 125, Issue 2, pp. 367-375.
[38]S.H Tang, Y.J. Tan, S.M. Sapuan, S. Sulaiman, N.Ismail and R.Samin, 2007, “The use of Taguchi Method in the Design of Plastic Injection Mould for Reducing Warpage”, Journal of Materials Processing Technology, Volume 182, Issues 1-3, pp. 418-426.
[39]M.M. Alam and D. Kumar, 2013, “Reducing Shrinkage in Plastic Injection Moulding using Taguchi Method in Tata Magic Head Light”, International Journal of Science and Research, Volume 2, Issue 2, pp. 107-110.
[40]X. Wang, G. Zhao and G. Wang, 2013, “Research on the Reduction of Sink Mark and Warpage of the Molded Part in Rapid Heat Cycle Molding Process”, Materials and Design, Volume 47, pp. 779-792.
[41]F. Hentati and M. Neila, 2020, “Influence of Injection Molding Parameters on the Mechanical Properties of Injected PC/ABS Parts”, In book: Robust Design Methods, pp. 1-13.
[42]J. Zhu, Z. Qiu, Y. Huang and W. Huang, 2021, “Overview of Injection Molding Process Optimization Technology”, Journal of Physics: Conference Series, Volume 1798, Issue 1, pp. 1-5.
[43]W.C. Chen, G.L. Fu, P.H. Tai, W.J. Deng and Y.C. Fan, 2007, “ANN and GA-Based Process Parameter Optimization for MIMO Plastic Injection Molding”, Conference: Machine Learning and Cybernetics, Volume 4, pp. 1909-1917.
[44]W.C Chen, M.W. Wang, G.L. Fu, C.T. Chen, 2008, “Optimization of Plastic Injection Molding Process via Taguchi’s Parameter Design method, BPNN, and DFP”, Conference: Machine Learning and Cybernetics, Volume 6, pp. 3315-3321.
[45]W.C. Chen, H.C. Tsai and T.T. Lai, 2010, “Optimization of MIMO Plastic Injection Molding Using DOE, BPNN, and GA”, 2010 IEEE 17Th International Conference on Industrial Engineering and Engineering Management, pp. 676-680.
[46]M.S. Meiabadi, A. Vafaeesefat and F. Sharifi, 2013, “Optimization of Plastic Injection Molding Process by Combination of Artificial Neural Network and Genetic Algorithm”, Journal of Optimization in Industrial Engineering, Volume 13, pp. 49-54.
[47]K. Li, S.L. Yan, W.F. Pan and G. Zhao, 2017, “Optimization of Fiber-orientation Distribution in Fiber-reinforced Composite Injection Molding by Taguchi, Back Propagation Neural Network, and Genetic Algorithm–Particle Swarm Optimization”, Advances in Mechanical Engineering, Volume 9, Issue 9, pp 1-11.
[48]P. Nagorny, M. Pillet, E. Pairel, R.L. Goff, J Loureaux and M. Wali, 2017, “Quality Prediction in Injection Molding”, 2017 IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications, pp. 141-146.
[49]C.T. Huang, Y.H. Hsu and B.S. Chen, 2019, “Investigation on the Internal Mechanism of the Deviation between Numerical Simulation and Experiments in Injection Molding Product Development”, Polymer Testing, Volume 75, pp. 327-336.
[50]K.C. Ke and M.S. Huang, 2020, “Quality Prediction for Injection Molding by Using a Multilayer Perceptron Neural Network”, Polymers, Volume 12, Issue 8, Article 1812, pp.1-22.
[51]J. Jung, K. Park, B. Cho and J. Park, 2022, “Optimization of Injection Molding Process using Multi-objective Bayesian Optimization and Constrained Generative Inverse Design Networks”, Journal of Intelligent Manufacturing, DOI: 10.1007/s10845-022-02018-8.
[52]M.H. Tsai, J.C. Fan-Jiang, G.Y. Liou, F.J. Cheng, S.J. Hwang, H.S. Peng and H.Y. Chu, 2022, “Development of an Online Quality Control System for Injection Molding Process”, Polymers, Volume 14, Issue 8, Article 1607, pp.1-19.
[53]Sabic OQ3820, https://www.sabic.com/en/products/polymers/polycarbonate-pc/
lexan-resin, Accessed Aug. 2022.
[54]Design Fan Gate in Injection Molding, https://mechanicalengblog.com/design-fan-gate-in-injection-molding/, Accessed Aug. 2022.
[55]R. Sánchez, J. Aisa, A. Martinez and D. Mercado, 2012, “On the Relationship Between Cooling Setup and Warpage in Injection Molding”, Measurement, Volume 45, Issue 5, pp. 1051-1056.
[56]C. Lotti, M.M. Ueki and R.E.S. Bretas, 2002, “Prediction of the Shrinkage of Injection Molded iPP Plaques using Artificial Neural Networks”, Journal of Injection Molding Technology Volume 6, Issue 3, pp. 157-176.
[57]M2R F2C鏡片密合度的問題，https://forum.jorsindo.com/thread-2336932-1-1.html，Accessed Jan. 2023。
[58]林苡任，2009，“菲涅爾透鏡(Fresnel Lens)之光學設計與精密成形”，國立高雄應用科技大學模具工程系碩士論文。
[59]陳昱廷，2016，“雙面非球面鏡片射出成形之多目標最佳化研究”，義守大學機械與自動化工程學系碩士論文。