實驗設計經常被用來研究設計參數與反應之間的關係，參數的設計會影響產品品質或作業流程，也是能夠被控制的因子。在理想狀況下參數的設定使反應與目標值的差異最小化，也是大部分研究的目標。過去的研究大多針對單一反應做研究，然而現在實務上需要考慮的品質或製程特性都不只一個，而是多反應問題。因此本篇要針對多反應問題做最佳化之研究。
目前的多反應最佳化方法大多有著繁瑣的統計相關運算或是實務運作困難等缺點，故本研究擬提出新的方法於多反應最佳化問題之解決上。首先將針對採用類神經網路方法及轉換多反應值為單一目標值的望想函數（desirability function）方法進行研究。在類神經網路方法方面，本方法採用一未曾被應用於多反應最佳化問題之廣義迴歸類神經網路（general regression neural network, GRNN），取代傳統的統計技術－反應曲面方法，由實驗設計所得的資料直接映射出多輸入與多輸出間的關係。接著使用文獻中提出的望想函數模型以幫助廣義迴歸類神經網路求解多反應問題之最佳目標值。接著，本研究對所提出的方法進行文獻中範例的求解最佳解的驗證，並與倒傳遞網路方法做比較與分析。經由實例驗證結果證明本研究所提出方法可以有效的求出多反應問題最佳解，且廣義類神經網路較倒傳遞網路適用於多反應最佳化問題。

The design of experiment was used to study the relationship between the design parameters responses frequently. Parameter design could influence the quality of the products or operation procedure, and it is the factor that can be controlled. Parameter estimation makes the difference of response value and target value minimize under ideal state. The past researches were mostly studied to the single response, but it does net conform to practice. The quality or process characteristic should be considered not merely one now, but multiple response problems. So this study aims to research multiple response optimization problems.
This study presents a new approach to optimize multiple response problems. First, neural networks and desirability function which transform multiple values into single value are briefly described is made. In neural networks methods, this research adopts the general regression neural network (GRNN) to replace response surface methods. The relationship of multiple inputs and multiple outputs could be mapping by the data of design of experiment. Then integrate desirability function and GRNN to solve optimal value. Finally, the proposed method is evaluated by a real case, and compared with the method that combines the desirability function with backpropagation network. The evaluation shows that the proposed approach effectively solves multiple response problems, and better than the method that combines the desirability function with backpropagation network.

1.姜台林，整合式智慧型最適化參數設計之研究，國立交通大學工業工程研究所博士論文，2001。
2.徐立章，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，義守大學管理科學研究所碩士論文，1999。
3.陳明佑，利用模糊目標規劃法求解田口式多品質特性最佳化問題，國立成功大學工業管理研究所碩士論文，2002。
4.劉亭宜，GRNN在晶圓製造裡良率模式之建構與分析，元智大學工業工程研究所碩士論文，2000。
5.蔡旻熹，多變量反應值最佳化，國立成功大學統計學研究所碩士論文，2005。
6.蕭鈺(金原)，應用多變量變異數分析與類神經網路於多品質實驗設計之研究，明志科技大學工程管理研究所碩士論文，2005。
7.Ames, A. E., Mattucci, N., MacDonald, S., Szonyi, G., Hawkins, D. M., Quality loss function for optimization across multiple response surfaces. Journal of Quality Technology, 29, 339-346, 1997.
8.Antony, J., Multi-response optimization in industrial experiments using Taguchi’s quality loss function and principal component analysis. Quality and Reliability Engineering International, 16, 3-8, 2000.
9.Castillo, E. D, Montgomery, D. C., McCarville, D. R., Modified desirability functions for multiple response optimization. Journal of Quality Technology, 28(3), 337-345, 1996.
10.Chang, H. H., Dynamic multi-response experiments by backpropagation networks and desirability functions. Journal of the Chinese Institute of Industrial Engineers, 23(4), 280-288, 2006.
11.Chang, P. R., Lee, C. H., Lee, S. Y., A cost-effective multi-response off-line quality control for plasma etching. The 26th Republic of China Conference on Quality Control, 79-86, 1990.
12.Chen, L.-H., Designing robust products with multiple quality characteristics. Computers and Operations Research, 24(10), 937-944, 1997.
13.Ch'ng, C. K., Quah, S. H., Low, H. C., A new approach for multiple-response optimization. Quality Engineering, 17, 621-626, 2005.
14.Derringer, G., A balancing act: Optimizing a product's properties. Quality Progress, 27(6), 51-58, 1994.
15.Derringer, G., Suich, R., Simultaneous optimization of several response variables. Journal of Quality Technology, 12(4), 214-219, 1980.
16.Harrington, E. C., Jr., The desirability function. Industrial Quality Control, 21, 494-498, 1965.
17.Himmel, C., May, G., Advantage of plasma etch modeling using neural networks over statistical techniques. IEEE Transactions on Semiconductor Manufacturing, 6, 103-111, 1993.
18.Hsieh, K. L., Parameter optimization of a multi-response process for lead frame manufacturing by employing artificial neural networks. International Journal of Advanced Manufacturing technology, 28, 584-591, 2006.
19.Hsu, C. M., Solving multi-response problems through neural networks and principal component analysis. Journal of the Chinese institute of industrial engineers, 18(5), 47-54, 2001.
20.Hsu, C. M., Su, C. T., Liao, D., A novel approach for optimizing the optical performance pf the broadband tap coupler. International Journal of Systems science, 34(3), 215-226, 2003.
21.Hsu, C. M., Su, C. T., Liao, D., Simultaneous of the broadband tap coupler optical performance based on neural works and exponential desirability functions. International Journal of Advanced Manufacturing Technology, 23, 896-902, 2004.
22.Jin, R., Chen, W. and Simpson, T. W., Comparative Studies of Metamodeling Techniques under Multiple Modeling Criteria, 8th AIAA/NASA/USAF/ISSMO Symposium on Multidisciplinary Analysis and Optimization, 2000.
23.Khuri, A. I., Conlon, M., Simultaneous optimization of multiple responses represented by polynomial regression functions. Technometrics, 23, 363-375, 1981.
24.Kim, K. J., Lin, D. K. J., Simultaneous optimization of mechanical properties of steel by maximizing exponential desirability function. Applied Statistics, 49(3), 311-325, 2000.
25.Lai, Y. J., Chang, S. I., A fuzzy approach for multiresponse optimization: An off-line quality engineering problem, Fuzzy Sets and Systems, 63(2), 117-129, 1994.
26.Leon, N. A., A pragmatic approach to multiple-response problems using loss functions. Quality Engineering, 9(2), 213-220, 1996.
27.Liao, H. C., A data envelopment analysis method of optimizing multi-response problem with censored data in the Taguchi method. Computers & Industrial Engineering, 46, 817-835, 2004.
28.Liao, H. C., Chen, Y. K., Optimizing multi-response problem in the Taguchi method by DEA based ranking method. International Journal of Quality & Reliability Management, 19(7), 825-837, 2002.
29.Liao, H. C., Multi-response optimization using weighted principal component. International Journal of Advanced Manufacturing technology, 27, 720-725, 2006.
30.Liao, H. C., Using N-D method to solve multi-response problem in Taguchi. Journal of Intelligent Manufacturing, 16, 331-347, 2005.
31.Liao, H. C., Using PCR-TOPSIS to optimise Taguchi's multi-response problem. International Journal of Advanced Manufacturing Technology, 22, 649-655, 2003.
32.Lin, C. L., Lin, J. L., Ko, T. C., Optimisation of the EDM process based on the orthogonal array with fuzzy logic and grey relational analysis Method. International Journal of Advanced Manufacturing Technology, 19(4), 271-277, 2002.
33.Lin, J. L., Lin, C. L., The use of the orthogonal array with grey relational analysis to optimize the electrical discharge machining process with multiple performance characteristics. International Journal of Machine Tools and Manufacture, 42(2), 237-244, 2002.
34.Lin, J. L., Tarng, Y. S., Optimization of the multi-response process by the Taguchi method with grey relational analysis. Journal of Grey System, 10(4), 355-370, 1998.
35.Logothetis, N., Haigh, A., Characterizing and optimizing multi-response processes by Taguchi method, Quality and Reliability Engineering International, 4(2), 159-169, 1988.
36.Lu, D., Antony, J., Optimization of multiple responses using a fuzzy-rule based inference system. International Journal of Production Research, 40(7), 1613-1625, 2002.
37.Marquez, L., Hill, T., Function approximation using backpropagation and general regression neural networks. Proceeding of the Twenty-Sixth Hawaii international conference on system science, 4, 607-615, 1993.
38.Parzen, E., On Estimation of a Probability Density Function and Mode, Annals of Math. Statistics, 33, 1065-1076, 1962.
39.Phadke, M. S., Quality Engineering Using Robust Design, Prentice-Hall, Englewood Cliffs, NJ, 1989.
40.Pignatiello, J. J. Jr., Strategies for robust multiresponse quality engineering. IIE Transactions, 25(3), 5-15, 1993.
41.Specht, D. F., Probabilistic neural networks for classification, mapping, or associative memory. Proceeding IEEE International Conference on Neural Networks, 525-532, 1988.
42.Specht, D. F., A general regression neural network. IEEE transactions on Neural Network, 26(6), 568-576, 1991.
43.Su, C. T., Chiang, T. L., Optimal design for a ball grid array wire bonding process using a neuron-genetic approach. IEEE Transaction on Electronics Packaging Manufacturing, 25(1), 13-18, 2002.
44.Su, C. T., Tong, L. I., Multi-response robust design by principal component analysis. Total Quality Management, 8(6), 409-416, 1997.
45.Tong, L. I., Hsieh, K. L., A novel means of applying neural networks to optimize the multiresponse problems. Quality engineering, 13(1), 11-18, 2000.
46.Tong, L. I., Su, C. T., Optimizing multi-response problems in the Taguchi method by fuzzy multiple attribute decision making. Quality and Reliability Engineering International, 13(1), 25-34, 1997.
47.Tong, L. I., Su, C. T., Wang, C. H., The optimization of multiresponse problems in the Taguchi method. International Journal of Quality & Reliability Management, 14(4), 367-380, 1997.
48.Tong, L. I., Wang, C. H. Chen, H. C., Optimization of multiple responses using principal component analysis and technique for order preference by similarity to ideal solution. International Journal of Advanced Manufacturing Technology, 27, 407-414, 2005.
49.Vining, G. G., A compromise approach to multiple optimization. Journal of Quality Technology, 30, 309-313, 1998.
50.Yang, T. H., Chou, P. H., Solving a multiresponse simulation-optimization problem with discrete variables using a multiple-attribute decision-making method. Mathematics and Computers in Simulation, 68, 9-21, 2005.