導光板為使背光模組提供液晶顯示器充分光源的關鍵組件。而射出成型是生產 三維複雜形狀成品的最佳方式之一，因此也是製造導光板的的重要關鍵技術。然而射出成型加工參數的設定一直存在造成導光板收縮變形而影響品質好壞的問題。冷卻時間、模具溫度、融膠溫度、射出速度、射出壓力、保壓壓力、保壓切換點、保壓時間等射出成型加工參數的改變對於導光板的 V-cut 微結構尺寸有直接的影響。所以，本研究主要探討精密射出成型加工參數與LCD導光板的品質特性之間的關係。應用田口方法、灰色關聯分析與倒傳遞類神經網路來尋找導光板的最佳加工條件與建構導光板於精密射出成型之品質預測系統。
首先，決定導光板的品質特性，其為V-cut微結構的深度與角度以及導光板的輝度均勻度，然後利用田口方法規劃加工參數之水準值，再依照直交表進行實驗。但是，由於田口方法大多使用於單一品質特性之最佳化，然而決定單一品質特性之最佳化加工參數，常常是無法完全表示整體品質的加工參數最佳化。因此本文利用灰色關聯分析來整合多重品質特性，以決定導光板的最佳加工條件。並且進行變異數分析，以對實驗結果進行探討。從變異數分析可以得到對導光板品質特性影響較大的顯著因子，亦即控制這些因子，便可以有效控制導光板的品質特性。經由確認實驗以95%信心區間驗證其實驗具有可靠性與再現性。
本文所建構的預測系統為倒傳遞類神經網路，其為具有輸入層、隱藏層與輸出層的類神經網路。射出成型的八個加工參數做為倒傳遞類神經網路的輸入變數，而導光板V-cut的深度與角度以及導光板的輝度均勻度作為輸出變數，以建立倒傳遞類神經網路架構。再以田口方法來規劃倒傳遞類神經網路的學習參數，可以改善傳統試誤法的缺點，使網路更有效率的快速收斂，進而快速的找出較佳的學習參數組合。實驗結果顯示，本文所建構的預測系統可以準確的預測導光板的品質特性。

A light guide plate is a key component that enables backlight modules to provide sufficient light source for LCDs (Liquid Crystal Displays). Injection molding is one of the best methods for producing a complex-shaped three dimensional product, and is therefore a crucially important core technology for the production of light guide plates. However, the specification and setting of the injection molding processing parameters has always possessed the problem of resulting in the deformation of the light guide plate because of shrinkage and contraction, causing variations in the quality of the light guide plates produced. Hence, this study aims to investigate the relationship between precision injection molding process parameters and light guide plate properties using Taguchi method, grey relational analysis, and back-propagation neural network to determine the optimal processing parameters for light guide plates and to establish a quality prediction system for injection molding of light guide plates.
Firstly, the quality characteristics of this experiment are the depth and angle of the V-cut microstructure as well as luminance uniformity. It then designs the level of processing parameters using the Taguchi method and moves on to conduct orthogonal array experiments. Nonetheless, since the Taguchi method is mostly used to optimize single quality characteristic, which often fail to represent processing parameters optimization of the overall quality. This study takes advantage of grey relational analysis and integrates multiple quality characteristics to determine the optimal processing parameters for light guide plates. Analysis of variance (ANOVA) will be performed to look into the results obtained from the experiment. From ANOVA the significant factors can be obtained which have the greatest effect on the light guide plate quality characteristics, in other words, by controlling these factors, the quality characteristics of the LCD light guide plate can be effectively controlled. Then, the reliability and reproducibility of the experiment were verified by confirming a confidence interval (CI) of 95%.
Additionally, the back-propagation neural network adopted in this study is a neural network that contains input layers, hidden layers, and output layers with a structure that is established by using eight injection molding process parameters as input variables and the depth, angle and luminance uniformity of light guide plates V-cuts as output variables. Here, the Taguchi method is employed to design the learning parameters for the back-propagation neural network, which is free of the deficiencies of the traditional trial-and-error method and speeds up network convergence to determine preferable combinations of learning parameters. As the experiments reveal, the prediction system established in this study is effective in accurate prediction of the qualities of light guide plates.

1.Gu, H.S.; Chou, B.D.; Chen, M.; Chang, T.A.; Fan, Y.S.; Chou, Y.H. An Introduction to Flat Panel Display, Gau Lih, Taiwan, 2005.
2.Sanchagrin, S. Process Control of Injection Molding, Polymer Engineering and Science, 1983, 23 (8), 431-438.
3.Siegmann, A.; Buchman, A.; Kenic, S. Residual Stresses in Injection-Molded Amorphous, Polymers, Polymer Engineering and Science, 1987, 27 (14), 1069-1078.
4.Siegmann, A.; Buchman, A.; Kenic, S. Residual Stresses in Polymers III: The Influence of Injection-Molding Process Conditions, Polymer Engineering and Science, 1982, 22 (9), 560-568.
5.Pham, H.T.; Bosnyak, C.P.; Sehanobish, K. Residual Stresses in Injection Molded Polycarbonate Rectangular Bars, Polymer Engineering and Science, 1993, 33 (24), 1634-1643.
6.Jansen, K.M.; Dijk, D.J.V.; Husselman, M.H. Effect of Processing Conditions on Shrinkage in Injection Molding, Polymer Engineering and Science, 1998, 38 (5), 838-846.
7.Choi, D.S.; Im, Y.T. Prediction of Shrinkage and Warpage in Consideration of Residual Stress in Integrated Simulation of Injection Molding, Composite Structures, 1999, 47 (1-4), 655-665.
8.Tseng, W.J., Statistical analysis of process parameters influencing dimensional control in ceramic injection molding. Journal of Materials Processing Technology, 1998, 79 (1-3), 242-250.
9.Bushko, W.C.; Stokes V.K. Solidification of Thermoviscoelastic Melts. Part 3: Effects of Mold Surface Temperature Differences on Warpage and Residual Stresses. Polymer Engineering and Science, 1996, 36(3), 322-335.
10.Bushko, W.C.; Stokes V.K. Solidification of Thermoviscoelastic Melts. Part 4: Effects of Boundary Conditions on Shrinkage and Residual Stresses. Polymer Engineering and Science, 1996, 36 (5), 658-675.
11.Yoshii, M.; Kuramoto, H.; Kato, K. Experimental Study of Transcription of Minute Width Grooves in Injection Molding. Polymer Engineering and Science, 1994, 34 (15), 1211-1218.
12.Despa, M.S.; Kelly, K.W.; Collier, J.R. Injection Molding of Polymeric LIGA HARMs. Microsystem Technologies, 1999, 6 (2), 60-66.
13.Wu, C.H.; Chen, W.S. Injection molding and injection compression molding of three-beam grating of DVD pickup lens. Sensors and Actuators A, 2006, 125 (2), 367-375.
14.Ji, C.H.; Loh, N.H.; Khor, K.A.; Tor, S.B. Sintering Study of 316L Stainless Steel Metal Injection Molding Parts Using Taguchi Method: Final Density, Materials Science and Engineering A, 2001, 311 (1-2), 74-82.
15.Thian, E.S.; Loh, N.H.; Khor, K.A.; Tor, S.B. Microstructures and Mechanical Properties of Powder Injection Molded Ti-6Al-4V/HA Powder, Biomaterials, 2002, 23 (14), 2927-2938.
16.Chang, T.C. Shrinkage Behavior and Optimization of Injection Molded Parts Studied by the Taguchi Method. Polymer Engineering and Science, 2001, 41 (5), 703-710.
17.Liu, S.J.; Lin, C.H.; Wu, Y.C. Minimizing the Sinkmarks in Injection-Molded Thermoplastics. Advances in Polymer Technology, 2001, 20 (3), 202-215.
18.Chang, T.C. Shrinkage Behavior and Optimization of Injection Molded Parts Studied by the Taguchi Method. Polymer Engineering and Science, 2001, 41 (5), 703-710.
19.Huang, M.C.; Tai, C.C. The Effective Factors in the Warpage Problem of an Injection-Molded Part with a Thin Shell Feature. Journal of Material Processing Technology, 2001, 110 (1), 1-9.
20.Liao, S.J.; Chang, D.Y.; Chen, H.J.; Tsou, L.S.; Ho, J.R.; Yau, H.T.; Hsieh, W.H.; Wang, J.T.; Su, Y.C. Optimal Process Conditions of Shrinkage and Warpage of Thin-Wall Parts. Polymer Engineering and Science, 2004, 44 (5), 917-928.
21.Wu, C.H.; Chen, W.S. Injection Molding and Injection Compression Molding of Three-Beam Grating of DVD Pickup Lens. Sensors and Actuators A, 2006, 125 (2), 367-375.
22.Fung, C.P. Manufacturing Process Optimization for Wear Property of Fiber-Reinforced Polybutylene Terephthalate Composites with Grey Relational Analysis. Wear, 2003, 254 (3-4), 298-306.
23.Ho, M.H.; Hwang, J.R.; Doong, J.L. Optimization of Injection Molding Process in PC/ABS Blends, The Journal of Grey System, 2000, 4, 357-366.
24.Li, T.C.; Fung, C.P.; Jeng, M.C. Injection Molding Process Optimization of Wear Properties in Fiber-Reinforced PBT Composites, The Journal of Grey System, 2003, 1, 9-20.
25.Lau, H.C.W.; Ning, A.; Pun, K.F. and Chin, K.S. Neural Networks for the Dimensional Control of Molded Parts Based on a Reverse Process Model. Journal of Materials Processing Technology, 2001, 117 (1-2), 89-96.
26.Kwak, T.S.; Suzuki, T.; Bae, W.B.; Uehara, Y.; Ohmori, H. Application of Neural Network and Computer Simulation to Improve Surface Profile of Injection Molding Optic Lens. Journal of Materials Processing Technology, 2005, 170 (1-2), 24-31.
27.Liao, S.J.; Hsieh, W.H.; Wang, J.T.; Su, Y.C. Shrinkage and Warpage Prediction of Injection-Molded Thin-Wall Parts Using Artificial Neural Networks. Polymer Engineering and Science, 2004, 44 (11), 2029-2040.
28.Pötsch, G.; Michaeli, W., Injection Molding: An Introduction, Hanser Gardner Publications, Inc., Cincinnati, 1995.
29.Menges, G.; Mohren, P., How to Make Injection Molds, 2nd ed. Hanser, New York, 1993.
30.Tadmor, Z.; Gogos, C.G., Principles of Polymer Processing, John Wiley & Sons, New York, 1979.
31.Rosato, D.V.; Rosato, D.V. (Eds.), Injection Molding Handbook, Van Nostrand Reinhold, New York, 1986.
32.Johannaber, F., Injection Molding Machines: A User’s Guide, 3rd ed., Hanser, Munich, New York, 1994.
33.Isayev, A.J., Injection and Compression Molding Fundamentals, Marcel Dekker, New York, 1987.
34.Beaumont, J.P.; Nagel, R.; Sherman, R., Successful Injection Molding: Process, Design, and Simulation, Hanser Gardner Publications, Inc., Cincinnati, 2002.
35.Michaeli, W.; Greif, H.; Kretzschmar, G.; Ehrig, F., Training in Injection Molding, Hanser Gardner Publications; 2nd edition, Hanser Gardner Publications, Inc., Cincinnati, 2001.
36.Rees, H.; Catoen, B., Selecting Injection Molds: Weighing Cost vs Productivity, Hanser Gardner Publications, Inc., Cincinnati, 2006.
37.Koppelmann, J.; Fleischmann, E. Nachdruckfreies Spritzgieben Von Polypropylen. Kuntstoffe 1988, 78, 312-315.
38.Greener, J. General Consequences of the Packing Phase in Injection Molding. Polymer Engineering and Science 1986, 26, 886-892.
39.Rees, H., Understanding Product Design for Injection Molding, Hanser Gardner Publications, Inc., Cincinnati, 1996.
40.Cracknell, P.S.; Dyson, R.W., Handbook of Thermoplastics Injection Mould Design, Blackie Academic & Professional, New York, 1993.
41.Rubin, I.I., Injection Molding: Theory and Practice, Wiley Publication, New York, 1973.
42.Taguchi, G., Introduction to Quality Engineering, Asian Production Organization, Tokyo, 1986.
43.Taguchi, G., Elsayed, E.A.; Hsiang, T., Quality Engineering in Production Systems, McGraw-Hill, New York, 1989.
44.Fowlkes, W.Y.; Creveling, C.M. Engineering Methods for Robust Product Design: Using Taguchi Methods in Technology and Product Development, Addison-Wesley, Massachusetts, 1995.
45.Ross, P.J., Taguchi Techniques for Quality Engineering, McGraw-Hill: New York, 1996.
46.Belavendram, N., Quality by Design: Taguchi Techniques for Industrial Experimentation, Prentice Hill, New York, 1995.
47.Taguchi, G.; Konishi, S., Orthogonal Arrays and Linear Graphs: Tools for Quality Engineering, American Supplier Institute Inc., Michigan, 1987.
48.Deng, J.L. Introduction to Grey Systems Theory. The Journal of Grey System, 1989, 1(1), 49-54.
49.Deng, J.L. Grey Informational Spaces. The Journal of Grey System, 1989, 2(1), 103-117.
50.Cao, J.; Hu, W.Y., Grey System: Theory and Practice, Northeastern Forestry University, Harbin City, P.R.C., 1993.
51.Kuo, C.-F.J.; Su, T.L. Gray Relational Analysis for Recognizing Fabric Defects. Textile Research Journal, 2003, 73 (5), 461-465.
52.Alberto, G.D.; Phillips, D.T., Principles of Experimental Design and Analysis, Chapman & Hall, New York, 1995.
53.Lindman, H.R., Analysis of Variance in Experimental Design, Springer-Verlag, New York, 1991.
54.Barker, T.B., Engineering Quality by Design: Interpreting the Taguchi Approach, Marcel Dekker, Inc., New York, 1990.
55.Lochner, R.H.; Matar, J.E., Designing for Quality: An Introduction to the Best of Taguchi and Western Methods of Statistical Experimental Design, ASQC Quality Press, Wisconsin, 1990.
56.Wasserman, P.D., Neural Computing: Theory and Practice, Van Nostrand Reinhold, New York, 1989.
57.Aleksander I.; Morton H., An Introduction to Neural Computing, Chapman and Hall, New York, 1990.
58.Khanna, T., Foundations of Neural Networks, Addison-Wesley, Massachusetts, 1990.
59.Patterson, D.W., Artificial Neural Networks: Theory and Applications, Prentice Hall, Singapore, 1995.
60.Farnum, Nicholas, R., Modern Statistical Quality Control and Improvement, Duxubry Press, Belmont, California, 1994.