基於類神經網路與交叉驗證法之田口方法

Taguchi Method Based on Neural Networks and Cross Validation Methodology

葉怡成(I-Cheng Yeh)；吳沛儒(Pei-Ju Wu)

田口方法 ； 類神經網路 ； 交叉驗證法 ； 敏感性分析 ； Taguchi method ； artificial neural network ； cross-validation ； sensitivity analysis

品質學報

16卷4期（2009 / 08 / 31）

261 - 279

繁體中文

本文爲了克服傳統的田口方法的缺點，提出基於類神經網路與交叉驗證法的田口方法，其要點有：(1)採用交叉驗證法以克服類神經網路必須區隔實驗數據集爲訓練集、測試集，導致訓練集數據不足的缺點。(2)提出敏感性分析與帶狀主效果圖以改善類神經網路黑箱模型的缺點。(3)採用非線性規劃以設計最佳品質因子的組合。爲了證明本法可行，本研究以二個已發表的田口方法的實例進行實證。研究結果顯示：(1)傳統的田口方法的未區隔資料集爲測試集、訓練集之作法，其誤差被嚴重低估。(2)在同樣使用可正確評估模型誤差的交叉驗證法下，本文提出的基於類神經網路的田口方法遠比傳統的田口方準確。(3)本文提出的「敏感性分析」與「帶狀主效果圖」確實可以表現因子與反應間的關係，改善類神經網路的解釋能力。(4)非線性規劃確實可以設計出最佳品質因子的組合。

To overcome the shortcomings of traditional Taguchi method, this study proposed a Taguchi method based on neural networks and cross validation methodology. Its main ideas included that (1) it used cross-validation methodology to overcome the shortcoming that neural networks need to separate the dataset into training set and testing set, which makes training set insufficient, (2) it used sensitive analysis and the main effect diagram to over come the shortcoming that neural networks are black box model, and (3) it used nonlinear programming to find the optimum combination of factor level. Two examples that had been solved by traditional Taguchi method were examined to verify the proposed method. It was demonstrated that (1) the prediction error is seriously underestimated in traditional Taguchi method, which does not separate the dataset into the testing set and training set, (2) under the same cross validation methodology, the proposed neural network-based Taguchi method is much more accurate than the traditional one, (3) the sensitive analysis and the main effect diagram truly can express the relationship between factors and responses, and improve the explanatory capacities of neural networks, (4) the nonlinear programming truly can find the optimum combination of factor level.

1. 陳文欽、蔡志弘、劉康勇(2005)。應用類神經綱路於半導體氧化製程最佳化之研究。品質月刊，41(6)，70-76。
   連結：
2. Lin, J. L.,Wang, K. S.,Yan, B. H.,Tarng, Y. S.(2000).Optimization of the electrical discharge machining process based on the Taguchi method with fuzzy logics.Journal of Materials Processing Technology,102(1),48-55.
3. Miyamoto, M.(2004).Theoretical study on design method combining the Taguchi Method and neural networks for machine systems-combine harvester as a system example.Agricultural Information Research,13(3),247-254.
4. Montgomery, D. C.(1996).Design and Analysis of Experiments.New York:John Wiley & Sons.
5. Myers, R. H.,Montgomery, D. C.(1995).Response Surface Methodology.New York:John Wiley & Sons.
6. Su, C. T.,Chiang, T. L.(2003).Optimizing the IC wire bonding process using a neural networks/genetic algorithms approach.Journal of Intelligent Manufacturing,14(2),229-238.
7. Taguchi, G.(1990).Introduction to Quality Engineering.Tokyo:Asian Productivity Organization.
8. Tarng, Y. S.,Yang, W. H,Juang, S. C.(2000).The use of fuzzy logic in the Taguchi method for the optimization of the submerged arc welding process.International Journal of Advanced Manufacturing Technology,16(9),688-694.
9. Tong, L. I.,Su, C. T.(1998).Optimizing multi-response problems in the Taguchi method by fuzzy multiple attribute decision making.Quality & Reliability Engineering International,13(1),25-34.
10. Tong, L. I.,Su, C. T.,Wang, C. H.(1997).The optimization of multi-response problems in the Taguchi method.International Journal of Quality & Reliability Management,14(4),367-380.
11. Wang, G. J.,Chou, M. H.(2005).A neural-Taguchi-based quasi time-optimization control strategy for chemical-mechanical polishing processes.The International Journal of Advanced Manufacturing Technology,26(7-8),759-765.
12. Wang, G. J.,Tsai, J. C.,Tzeng, P. C.,Cheng, T. C.(1998).Neural-Taguchi method for robust design analysis.Journal of the Chinese Society of Mechanical Engineers,19(2),223-230.
13. Wu, F. C.(2002).Optimization of multiple quality characteristics based on reduction percent of Taguchi's quality loss.International Journal of Advanced Manufacturing Technology,20(10),749-753.
14. Yanga, T.,Linb, H. C.,Chena, M. L.(2006).Metamodeling approach in solving the machine parameters optimization problem using neural network and genetic algorithms: a case study.Robotics and Computer-Integrated Manufacturing,22(4),322-331.
15. 李輝煌(2003)。田口方法－品質設計的原理與實務。台北:高立圖書有限公司。
16. 柑俊晟(2000)。碩士論文(碩士論文)。中華大學土木工程學系。
17. 柑俊晟、陳怡成、葉怡成(2000)。基於類神經網路之反應曲面法在品質設計上之應用。義守大學品質管理技術應用研討會論文集，高雄:
18. 紀勝財、徐立章、饒瑞倫(2004)。電漿電弧銲參數最佳化之研究－田口方法與類神經網路之應用。銲接與切割，14(2)，28-35。
19. 張祥傑(2004)。博士論文(博士論文)。國立成功大學機械工程學系。
20. 葉怡成(2005)。實驗計劃法－製程與產品最佳化。台北:五南書局。
21. 葉怡成(2006)。類神經網路模式應用與實作。台北:儒林圖書公司。
22. 黎正中譯、Montgomery, D. C.著(1998)。實驗設計與分析。台北:高立圖書。
23. 賴懷恩(2004)。碩士論文(碩士論文)。國立清華大學。
24. 簡明德(2004)。應用類神經網路模擬微銲被覆表面之製程發展分析。材料科學與工程，36(4)，210-222。

1. 程瑾文(2017)。泛用型虛實整合系統架構建立─ 以液靜壓節流器之調整為驗證載具。清華大學動力機械工程學系學位論文。2017。1-167。