本研究利用實驗設計法（Design of Experiment，DOE），分析射出成形控制因子中對產品重量影響較顯著之重要製程參數，找出各因子之相關性。藉由探討系統中的速度、壓力、時間、料管溫度，來評估多個操作變數對系統性能的影響效應，以及各變數間的交互影響效益；再透過實驗找出初始最佳的操作變數並利用實驗設計法來建立製程模型，然後利用遞迴式最小平方法（Recursive Least Squares，RLS）做製程模型的即時調變，以適應製程變異之變化及干擾，再將調變完之模式帶入最小變異控制器（Minimum Variance Controller，MVC），讓輸出變數迅速達到我們所設定的目標值，以提高產品品質。結果顯示，藉由反應曲面法可以建立重量與速度、壓力、時間與料管溫度之間準確製程模型，並可透過製程模型進行產品製程控制，來提高產品品質。

In this research, design of experiment (DOE) method is employed to analyze the more eminent and crucial process parameters of control factors with respect to the weight of product in injection molding system (IMS) and further locate their dependences. The effect of multi-variables vs. system performance and the interacted impact benefits among process parameters are assessed by the various sets of injection velocity, injection pressure, injection time and material temperature. In addition, the study identifies the initial optimal operational variables via IMS experiments to develop the process model using design of experiment method, and adopts the recursive least squares (RLS) algorithm to create on-line adjustments of process model which can control the process shifts and drifts. Moreover, the adjusted model enables the output variables promptly to reach our setting target and increase the product quality as applying the minimum variance controller (MVC). Finally, the research represents the response surface model to generate the precise process model through the injection velocity, injection pressure, injection time and material temperature, and exploits the above process model to conduct the process control and raise the quality of product.

目 錄
摘 要 i
Abstract ii
誌 謝 iii
目 錄 iv
圖標題 vi
表標題 viii
第一章 緒論 1
1.1 研究背景與動機 1
1.2 研究目的 2
1.3 研究架構 2
1.4 文獻回顧 3
1.5 研究方法 4
第二章 射出成形簡介 5
2.1 射出成形加工程序 5
2.2 射出成形機 6
2.3 塑膠製品不良及處理 7
第三章 研究方法 9
3.1 實驗設計 10
3.1.1 部分因子實驗 11
3.1.2 反應曲面法 11
3.2 預先一步的預測 12
3.3 遞迴最小平方法 13
3.4 最小變異控制器 17
第四章 實驗設計及資料分析 20
4.1 實驗前的準備 20
4.1.1 實驗設備簡介 20
4.1.2 實驗前的準備 23
4.1.3 產品的規格目標 23
4.2 部份因子實驗 23
4.3 反應曲面法 28
第五章 製程控制與模式驗證 37
5.1 製程控制器之架構 37
5.2 控制器之建立 38
5.3 遞迴最小平方法驗證結果 40
5.4 最小變異控制器測試實驗 44
5.4.1 模擬驗證 44
5.4.2 實際實驗驗證 60
第六章 結論與未來研究建議 63
6.1 結論 63
6.2 未來研究建議 64
參考文獻 65

參考文獻
1.洪志明(2005)，「應用動態模式最小變異控制於先進微影製程控制」，交通大學精密與自動化工程學系碩士論文。
2.唐麗英、王春和(2005)，「STATISTICA 6.0版與基礎統計分析」，儒林圖書有限公司。
3.賴世明、謝美君、陳瑞龍(2003)，「以實驗設計法選取最佳提取銀杏葉中活性成分的條件」，技術學刊，第一十七卷，第一期，第129-136頁。
4.張榮語(1995)，「射出成形模具設計：模具設計」，高立圖書有限公司
5.范樂陽(1987)，「塑膠加工實務」，高立圖書有限公司。
6.黎正中譯，Montgomery著(2003)，「實驗設計與分析」，高立圖書有限公司。
7.Box, G. E. P. and Behnken, D. W.(1960), “Some new three level designs for the study of quantitative variables,” Technometrics, Vol. 2, pp. 455-475.
8.Choi, G. H., Lee, K. D., Chang, N. and Kim, S. G.(1994), “Optimization of Process Parameters of Injection Molding With Neural Network Application in a Process Simulation Environment,” Annals of the CIRP, Vol. 43, pp. 449-452.
9.Chris, M. S., Alan, A. D. and George, F.(1994), “Multiobjective Optimization of a Plastic Injection Molding Process,” TEEE Transaction on Control Systems Technology, Vol. l2, No. 3, pp. 157-168.
10.Dowlatshahi, S.(2004), “An application of design of experiments for optimization of plastic injection molding processes,” Journal of Manufacturing Technology Management, Vol. 15, No. 6, pp. 445-454.
11.Helps, C. R., Strong, A. B., Zubi, R. A., Hawks, V. D. and Kohkonen, K. E. (1999), “The Use of artificial Neural Networks in the Prediction of Machine Operational Settings for Injection Molded Parts,” Journal of Injection Molding Technology, Vol. 3, No. 4, pp. 201-211.
12.Ibar, J. P.(1998), “Control of Properties by Melt Vibration Technology：A Review,” Polymer Engineering and Science, Vol. 38, No.1, pp. 1-20.
13.Karmal, M. R., Varela, A. E. and Patterson, W. I.(1996), “Control of Part Weight in Injection Molding of Amorphous Thermoplastics,” Polymer Engineering and Science, Vol. 39, No. 5, pp. 940-952.
14.Lee, A. C.(1990), “Minimum-variance controller for a class of non-linear system,” Int. J. Systems Science, Vol. 21, No. 11, pp. 2091-2101.
15.Ljung, L.(1987), System identification: Theory for the User, Prentice-Hall.
16.Min, B. H. and Shin, B. C.(2001), “A Study on Volumetric Shrinkage of Injection Molded Parts Based on Neural Networks,” Journal of Injection Molding Technology, Vol. 5, No. 4, pp. 201-207.
17.Park, K. and Ahn, J. H.（2004）, “Design of experiment considering two-way interactions and its application to injection molding processes with numerical analysis,” Journal of Materials Processing Technology, Vol. 146, pp. 221–227
18.Rao, S. S.(1996), Engineering Optimization：Theory and Practice. No. 3, John Wiley & Sons Inc.
19.Sanschagrin, B.(1983), “Process Control of Injection Molding,” Polymer Engineering and Science, Vol. 23, No. 8, pp. 431-438.
20.Turng, L. S. and Kharbas, H.(2003), “Effect of Process Condition on the Weld-Line Strength and Microstructure of Microcellular Injection Parts,” Polymer Engineering and Science, Vol. 43, No. 1, pp. 157-168.
21.Yang, Y. and Gao, F.(2006), “Injection molding product weight：Online prediction control based on a nonlinear principal component regression model,” Polymer Engineering and Science, Vol. 46, No. 4, pp. 540-548.
22.Zhao, C. and Gao, F.(1999), “Melt Temperature Profile Perdition for Thermoplastic Injection Molding,” Polymer Engineering and Science, Vol. 39, No. 9, pp. 1787-1801.
23.Zzcelik, B. and Erzurumlu, T.(2006), “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, pp. 437-445.