臺灣博碩士論文加值系統

智慧型控制理論在現代被廣泛的研究與應用在各領域中，且在各領域中都有令人激賞的表現，但隨著科技日新月異的進步，現今智慧型控制系統越趨複雜及目標難以精確化的問題就此產生，此時模糊理論的誕生解決了此相關方面的問題。
由於模糊理論擁有能夠處理複雜與目標難以精確化的特性，現今己活躍在各種領域當中，但是在建置模糊系統的過程中將會遇到兩個主要的困難點，第一點為定義模糊IF-THEN規則庫中適當歸屬函數；第二點為找尋最佳的模糊歸屬函數個數組合，這兩點是在模糊系統建置過程中一定會遇到的困難，故本研究將針對模糊建置上會遇到的兩個主要困難做有效及正確的改善，運用迴歸分析建立廻歸模組來輔助定義出模糊IF-TEHN規則庫，與田口法優化模糊歸屬函數個數，找出最佳歸屬函數個數組合，並且將兩者結合於模糊預測系統中，建置一套更有效且更準確的模糊預測系統。
為證明本研究所提出之方法的有效性與準確性，將所發展之結合迴歸模糊與田口法導入至表面粗糙度預測的實例中，建置出表面粗糙度預測系統，證明出此預測系統能有效且準確的預測出表面粗糙度，並且提升了原模糊系統的準確性。最後運用迴歸分析做表面粗糙度的預測，來驗證出結合迴歸模糊與田口法所發展的預測系統比迴歸預測方法還具有效性及準確性。

Intelligent control theory has been studied in modern research and widely applied in various fields. With the rapid technological advances, however, intelligent control system becomes more complex and is difficult for researchers to define accurately. As a result, fuzzy theory is proposed to solve problems in the relevant areas.
Although the fuzzy theory can be used to solve complex issues and make accurate definitions, two main issues occur in the process of the building fuzzy systems including defining appropriate membership functions in the fuzzy IF- THEN rule bank and searching the best combined number pairs in the fuzzy membership functions. In order to handle these two issues, the current study adopted regression analysis to define the fuzzy IF-TEHN rule bank, and membership functions of Taguchi Method to search the best combined number pairs in the fuzzy system. Then the two are combined to build an effective and accurate fuzzy prediction system.
The fuzzy prediction system proposed in the study was used to predict surface roughness for verifying its effectiveness and accuracy. The method composed of fuzzy regression and Taguchi Method was developed, and was proved to accurately predict surface roughness and improve predictions of the original fuzzy system. Finally, the study testified that the method composed of fuzzy regression and Taguchi Method has a better and more accurate prediction compared to regression analysis.

中文摘要 i
Abstract ii
誌謝 iii
目錄 iv
圖目錄 vi
表目錄 vii
第一章 緒論 1
1.1研究動機與背景 1
1.2研究目地 3
1.3研究範圍與假設 4
1.3.1 研究範圍 4
1.3.2 研究假設 4
1.4研究架構 4
第二章 文獻探討 6
2.1 模糊理論 6
2.1.1 模糊集合 8
2.1.2 模糊控制 10
2.2 田口法 12
2.2.1 田口法於原理 13
敘述完田口基本原理後，可知在田口法的基本觀念，運用這些觀念於本研究參數最佳化程序中，在此介紹本研究最佳參數化程序。 15
2.2.2 參數最佳化程序 16
2.3 迴歸分析 18
2.3.1 基本假設： 19
2.3.2 複迴歸模式： 19
2.3.3 母體分配參數之點估計 20
2.4 表面粗糙度 21
2.4.1表面粗糙度概況 21
2.4.2影響表面粗糙度之重要因子 22
第三章 研究方法 23
3.1 田口法優化模糊歸屬函數 23
3.1.1 定義目標函數與品質特性 24
3.1.2 因子選擇與參數水準配置 25
3.1.3 決定直交表配置 28
3.1.4 最佳參數水準組合 29
3.1.5 確認實驗 31
3.2 廻歸輔助模糊IF-THEN規則庫 33
3.2.1 定義資料輸出入變數 34
3.2.2 建立迴歸模組 34
3.2.3 迴歸模組輔助IF-THAN規則庫的建置 36
3.3迴歸模糊與田口優化預測系統 39
3.3.1. 定義選擇輸出入變數 40
3.3.2 田口法輔助定義歸屬函數個數 40
3.3.3. 依照輸出入變數的論域值設定適當範圍 41
3.3.4 模糊化 42
3.3.5. 廻歸模組輔助IF-THEN規則庫的建立 43
3.3.6 模糊推論 44
3.3.7. 解模糊化 47
3.3.8. 最佳模糊系統 48
第四章 表面粗糙度預測系統建置與測試 49
4.1表面粗糙度預測系統之田口配置實驗 50
4.1.1目標函數與品質特性 50
4.1.2參數水準配置 50
4.1.3直交表 52
4.2.1 資料輸出入變數 53
4.2.2 建立迴歸模組 54
4.2.3. 迴歸模組輔助IF-THAN規則庫建置 54
4.3 表面粗糙度的最佳預測系統建置 55
4.3.1 第一次實驗 55
4.3.2 第二次實驗 59
4.3.3 最佳表面粗糙度預測系統 61
4.4 系統測試結果與分析 68
第五章 結論與未來研究方向 72
5.1研究結論 72
5.2 未來研究方向 73
參考文獻 74
附錄A：170筆表面粗糙度資料 79
表A-1 1-64表面粗糙度資料 79
表A-2 65-128表面粗糙度資料 80
表A-3 129-170表面粗糙度資料 81
附錄B：表面粗糙度之模糊IF-THEN規則庫 82
附錄C：最佳表面粗糙度預測系統IF-THEN規則庫 94
附錄D：隨機50筆表面粗糙度實際值與預測值 97
附錄E：隨機50筆表面粗糙度實際值與預測值 99

圖1.1-1 智慧型控制示意圖 1
圖1.4-1 研究架構流程圖 5
圖2.1-1 A、B集合的文氏圖 9
圖2.1-2 模糊控制運作四大模式 10
圖2.2-1田口最佳參數流程圖 16
圖2.3-1 散佈圖與迴歸線之示意圖 18
圖2.4-1 表面粗糙度預測系統的輸出入 22
圖3.1-1田口法優化模糊歸屬函數流程圖 23
圖3.1-2 三角形歸屬函數 25
圖3.1-3 歸屬函數分割3個空間 26
圖3.1-4 歸屬函數分割5個空間 26
圖3.1-5 歸屬函數分割7個空間 26
圖3.1-6 歸屬函數分割9個空間 27
圖3.1-7 歸屬函數分割11個空間 27
圖3.1-8 平均值回應示意圖 30
圖3.1-9 信號雜音比回應示意圖 30
圖3.2-1廻歸輔助模糊IF-THEN規則庫流程圖 33
圖3.2-2 迴歸模組輔助 IF-THAN規則庫示意圖 36
圖3.2-3 規則庫之歸屬函數示意圖 37
圖3.2-4 迴歸模組輔助IF-THEN規則庫 38
圖3.2-5 Rule2所對應y之歸屬函數 38
圖3.3-1 結合迴歸模糊與田口方法協助建置模糊系統流程圖 39
圖3.3-2 兩輸入單輸出模糊系統 40
圖3.3-3 三個變數歸屬數語言的定義 42
圖3.3-4 IF-THEN規則庫建置 43
圖3.3-5 Min-Min-Max推論法運算過程 44
圖3.3-6 歸屬函數對應示意圖 46
圖3.3-7 重心法解模糊 47
圖4.1-1 表面粗糙度預測系統流程 49
圖4.3-1 第一次實驗平均值回應圖 57
圖4.3-2 第一次實驗信號雜音比回應圖 57
圖4.3-3 第二次實驗平均值回應圖 59
圖4.3-4 第二次實驗信號雜音比回應圖 60
圖4.3-5 最佳表面粗糙度預測系統示意圖 61
圖4.3-6 表面粗糙度預測示意圖 67

表2.1-1 各學者所提出關於模糊理論之研究 7
表2.2-1 各學者所提出關於田口法之研究 12
表2.2-2 田口直交表 15
表2.2-3 內側與外側直交表配置圖 15
表2.3-1 各學者所提出關於迴歸分析之研究 19
表3.1-1 參數水準配置 27
表3.1-2 直交表配置實驗 28
表3.1-3 參數設計實驗結果 29
表3.1-4歸屬函數最佳組合 30
表3.1-5 ANOVA table 32
表3.1-6 SN ratio ANOVA table 32
表 3.2-1 資料表 34
表3.2-2收集實驗資料 34
表3.3-1 因子水準配置 41
表3.3-2 直交表配置實驗 41
表3.3-3 各變數歸屬函數論域範圍 42
表3.3-4 田口法參數設計實驗結果 48
表4.1-1 表面粗糙度預測系統參數水準配置 51
表4.1-2 各因子的歸屬函數個數與分割空間範圍 51
表4.1-3 直交表與各項目組合規則數 52
表4.2-1 170筆中部份表面粗糙度資料 53
表4.2-2 影響表面粗糙度因子變數迴歸 54
表4.3-1 50筆中部份表面粗糙度資料 55
表4.3-2 直交表配置實驗觀測值與SN值 56
表4.3-3 信號雜音比影響表 58
表4.3-4 信號雜音比 ANOVA table(原始) 58
表4.3-5 信號雜音比 ANOVA table(合併後) 58
表4.3-6 最佳參數水準組合 58
表4.3-7 第二次配置實驗與觀測值 59
表4.3-8 信號雜音比影響表 60
表4.3-9 信號雜音比 ANOVA table(原始) 60
表4.3-10 信號雜音比 ANOVA table(合併後) 60
表4.4-1 部份表面粗糙度實際值與模糊系統預測值 68
表4.4.2 各實驗項目與最佳表面粗糙度系統的RMSE 69
表4.4-3 假設檢定表 71

1.Ahmed, M. A., Saliu, M. O., AIGhamdi, J., Adaptive fuzzy logic-based framework for software development effort prediction, Information and Software Technology, 47, pp. 31–48, 2005.
2.Akira, K., Suzuki, A., Takahama, Y., Prediction of coronal size of third molars by factor and multiple regression analyses, American Journal of Orthodontics and Dentofacial Orthopedics, 109(1), pp.79-85, 1996.
3.Akinbinu, V. A., Prediction of fracture gradient from formation pressures and depth using correlation and stepwise multiple regression techniques, Journal of Petroleum Science and Engineering, 72, pp.10–17, 2010.
4.Alvarez, G. M., Babuska, R., Fuzzy model for the prediction of unconfined compressive strength of rock samples, International Journal of Rock Mechanics and Mining Sciences, 36, pp. 339-349, 1999.
5.Benardos, P. G., Vosniak, G.. C., Prediction of surface roughness in CNC face milling using neural networks and Taguchi’s design of experiments, Robotics and Computer Integrated Manufacturing, 18, pp. 343–354, 2002.
6.Carman, K., Prediction of soil compaction under pneumatic tire a using fuzzy logic approach, Journal of Terramechanics , 45, pp. 103-108, 2008.
7.Casalino, G., Curcio, F., Memola Capece Minutolo, F., Investigation on Ti6Al4V laser welding using statistical and Taguchi approaches, Journal of Materials Processing Technology, 167, pp. 422–428, 2005.
8.Chen, J.C., Black, J.T., A fuzzy-nets in-process (FNIP) system for tool-breakage monitoring in end-milling operations, Int. J. Mach.Tool Manuf, 37 (6), pp. 783–800, 1997.
9.Chen, J.C., M.S. Lou, Fuzzy-nets based approach to using an accelerometer for an in-process surface roughness prediction system in milling operations, Int. J. Comput. Integr. Manuf, 13 (4), pp. 358–368, 2000.
10.Cliff, M. A., Dever, M. C., Hall, J. W., Girard, B., Development and evaluation of multiple regression models for prediction of sweet cherry liking, Journal of Fermentation and Bioengineering, 86(1), pp.141-143, 1996.
11.Degormo E.P. , Black, JT., Kohser R. A., Materials and processes in manufacturing 10th, Wiley, 2008.
12.El-Sonbaty, I. A., Khashaba, U. A., Selmy, A. I., Ali, A. I., Prediction of surface roughness profiles for milled urfaces using an artificial neural network and ractal geometry approach, journal of materials processing technology, 200, pp. 271-278, 2008.
13.Fang, Y. C., Tzeng, Y. F., Li, S. X., A Taguchi PCA fuzzy-based approach for the multi-objective extended optimization of a miniature optical engine, journal of physics D: applied physics, J. Phys. D: Appl. Phys. 41(175108), pp. 1-16, 2008.
14.Gadoue, S. M., Giaouris, D., Finch, J. W., Artificial intelligence-based speed control of DTC induction motor drives—A comparative study, Electric Power Systems Research, 79, pp. 210–219, 2009.
15.Ghani, J. A., Choudhury, I. A., Hassan, H. H., Application of Taguchi method in the optimization of end milling parameters, Journal of Materials Processing Technology ,145, pp. 84–92, 2004.
16.Huang, B. P., A neural networks-based in-process adaptive surface roughness control (NN-IASRC) system in end-milling operations, Doctor of Philosophy, 2002.
17.Hong, S. P., Jung, E. S., Choe, J., Kim, J. H., Design of a Menu Structure for the Instrument Cluster IVIS using Taguchi Method, Proceedings of the International MultiConference of Engineers and Computer Scientisis 2010 Vol III, IMECS2010, Hong Kong, pp. 1-5, 2010.
18.Hossein, S., Najmeh D., Presented a fuzzy system to determine Barberry product quality based on average color spectra by image processing, Journal of King Saud University – Science, S1018-3647(10)00081-9, pp. 1-5, 2010.
19.Hsiang, S. H., Lin, Y. W., Optimization of the Extrusion Process for Magnesium Alloy Sheets Using the Fuzzy Bsed Taguchi Method, The Arabian Journal for Science and Engineering, 34, pp. 1-11,2009.
20.Hsiang, S. H.,Optimization of the Extrusion Process for Magnesium Alloy Sheets Using the Fuzzybased Taguchi Method, The Arabian Journal for Science and Engineering, 34(1C), pp. 175-185, 2009.
21.Hsu, T. J., Lai, W. H.,Manufacturing Parts Optimization in the Three-Dimensional Printing Process by the Taguchi Method, Journal of the Chinese Institute of Engineers, 33(1), pp. 121-130, 2010.
22.Huang, B.P., Chen, J.C., An in-process neural network-based surface roughness prediction system using a dynamometer in end milling operations, Int. J. Adv. Manuf. Technol., 21, pp. 339–347, 2003.
23.Huang, B. P., Chen, J. C., Li, Y., Artificial-neural-networks-based surface roughness Pokayoke system for end-milling operations, Neurocomputing, 71, pp. 544-549, 2008.
24.Hwang, G. Y., Hwang, S. M., Lee, H. J., Kim, J. H., Hong, K. S., Lee, W. Y., Application of Taguchi Method to Robust Design of Acoustic Performance in IMT-2000 Mobile Phones, IEEE Transactions on Magnetics, 41(5), pp. 1900-1903 ,2005.
25.Jahanshahi, M., Najafpour, G., Rahimnejad, M., Applying the Taguchi method for optimized fabrication of bovine serum albumin (BSA) nanoparticles as drug delivery vehicles, African Journal of Biotechnology, 7(4), pp. 362-367, 2008.
26.Jiao, Y., Lei, S., Pei, Z. J., Lee, E. S., Fuzzy adaptive networks in machining process modeling: surface roughness prediction for turning operations, International Journal of Machine Tools & Manufacture, 44, pp.1643–1651, 2004.
27.Joo, Y. K., Zhang, S. H., Yoon, J. H., Cho, T. Y., Optimization of the Adhesion Strength of Arc Ion Plating TiAlN Films by the Taguchi Method, Materials, 2, pp. 699-709, 2009.
28.Kim, M., Sohn, Y. J., Lee, W. Y., Kim, C. S., Fuzzy control based engine sizing optimization for a fuel cell/battery hybrid mini-bus, Journal of Power Sources, 178(2), pp. 706-710, 2008.
29.Lee, J., Um, K.,A comparison in a back-bead prediction of gas metal arc welding using multiple regression analysis and artificial neural network, Optics and Lasers in Engineering, 34, pp.149-158, 2000.
30.Lu, S. M., Li, Y. C. M., Tang, J. C., Optimum design of natural-circulation solar-water-heater by the Taguchi method, Energy, 28, pp. 741–750, 2003.
31.Wang, J., Qiao, C. D., Deng, B., Observer-based robust adaptive variable universe fuzzy control for chaotic system, Chaos, Solitons and Fractals, 23, pp.1013–1032, 2005.
32.Ozcelik ,B., Bayramoglu ,M, The statistical modeling of surface roughness in high-speed flat end milling, International Journal of Machine Tools & Manufacture , 46, pp. 1395–1402, 2006.
33.Qiu, Y., Fu, B., Wang, J., Chen, L., Meng, L., Zhang, Y., Spatial prediction of soil moisture content using multiple-linear regressions in a gully catchment of the Loess Plateau, Journal of Arid Environments, 74, pp. 208–220, 2010.
34.Saenz de Argandona, E., Aztiria, A., Carcia, C., Arana, N., Izaguirre, A., Fillatreau, P.,Forming processes control by means of artificial intelligence techniques, Robotics and Computer-Integrated Manufacturing, 24 , pp. 773–779, 2008.
35.Sinnakaudan, S. K., Ghani, A. Ab., Ahmad, M. S. S., Zakaria, N. A., Multiple Linear Regression Model for Total Bed Material Load Prediction, J. Hydr. Engrg. 132(5), pp.521-528, 2006.
36.Sohn, S. Y., Kim, H. S., Random effects logistic regression model for default prediction of technology credit guarantee fund, European Journal of Operational Research, 183, pp. 472–478, 2007.
37.Tortum, A., Yayla, N., Celik, C., Gokdag, M., The investigation of model selection criteria in artificial neural networks by the Taguchi method, Physica A 386, pp. 446–468, 2007.
38.Tsao, C. C., Hocheng, H., Evaluation of thrust force and surface roughness in drilling composite material using Taguchi analysis and neural network , journal of materials processing technology, 203, pp. 342–348, 2008.
39.Tseng, F. M., Hu, Y. C., Comparing four bankruptcy prediction models: Logit, quadratic interval logit, neural and fuzzy neural networks, Expert Systems with Applications, 37, pp. 1846–1853, 2010.
40.Tzeng, Y. F., Chen, F. C., Multi-objective optimisation of high-speed electrical discharge machining process using a Taguchi fuzzy-based approach, Materials and Design, 28, pp. 1159–1168, 2007.
41.Wang, Y. M., Luo, Y., Hua, Z., On the extent analysis method for fuzzy AHP and its applications, European Journal of Operational Research, 186(2), pp. 735-747, 2008.
42.Wu, D. H., Chang, M. S., Use of Taguchi method to develop a robust design for themagnesium alloy die casting process, Materials Science and Engineering, A 379, pp. 366–371, 2004.
43.Wong, C. C., Wang, H. Y., Li, S. A., Cheng, C. T., Fuzzy Controller Designed by GA for Two-wheeled Mobile Robots, International Journal of Fuzzy Systems, 9(1), 2007.
44.Xue, Y., Kim, I. S., Son, J. S., Park, C. E., Kim, H. H., Sung, B.S., Kim, I. J., Kim, H. J., Kang, B. Y., Fuzzy regression method for prediction and control the bead width in the robotic arc-welding process, Journal of Materials Processing Technology, 164–165, pp. 1134–1139, 2005.
45.Yilmaz, N. G., Yurdakul, M., Goktan, R. M., Prediction of radial bit cutting force in high-strength rocks using multiple linear regression analysis, International Journal of Rock Mechanics & Mining Sciences, 44, pp.962–970, 2007.
46.Zain, M. F. M., Abd, S. M.,Multiple Regression Model for Compressive Strength Prediction of High Performance Concrete, Journal of Applied Sciences, 9(1), pp. 155-160, 2009.
47.Zadeh, L. A., Fuzzy sets, Inform. Contorl, 8, pp. 338-353, 1965.
48.林俊良，智慧型控制 : 分析與設計，全華科技圖書公司，台灣台北，2008。
49.孫宗瀛，楊英魁，Fuzzy控制：理論、實作與應用，全華科技圖書公司，台灣台北，2005。
50.陳至安等譯，應用線性迴歸模型，華泰出版，台灣台北，2005。
51.陳順宇、鄭碧娥，統計學，華泰出版，台灣台北，2004。
52.黃信銘，機械加工法多重品質特性最佳化製程參數研究，國立高雄第一科技大學機械與自動化工程系碩士論文，2005。
53.黃乾怡、林宜鋒、紀勝財、蘇顏衍，田口方法應用於無鉛迴銲製程參數優化，科學與工程技術期刊，第三卷，第二期，2007。
54.楊英魁，FUZZY控制，中國生產力中心技術引進服務，台灣台北，1993。
55.劉濱達，「灰模型最佳化研究與灰預測模糊控制器之實現」，國立成功大學電機工程學系博士論文，2004。
56.謝坤龍，「台灣公債殖利率預測模型之建構-調適性網路模糊推論系統與灰預測之應用」，東吳大學經濟學系碩士論文，2006。
57.譚墨群，「應用模糊理論於門檻型GARCH模式之建構與預測」，大同大學應用數學研究所碩士論文，2009。
58.蘇朝墩，品質工程，中華民國品質學會，台灣台北，2004。