隨著可攜式資訊電子產品與行動通訊產品朝著輕薄短小、多功能、高可靠度與低價化的發展趨勢，在電子產品的電路中佔據最多面積與數量的被動元件（Passive Components）也正進行一場積體化、整合化的革命；而積層陶瓷電容（Multi-layer Ceramic Capacitor, MLCC）有體積小、電容量可以隨著陶瓷堆疊的層數而增加及生產速度快的優點，便成為組成行動電話的必要被動元件產品。
在極端複雜的MLCC生產製程中有許多不確定的生產變數，如何控管製程變因以穩定產品品質成為一大課題。在MLCC製程中電性為一重要的品質指標，根據過去的生產數據資料顯示及業界資深工程師的經驗得知，MLCC製程的電性品質不良率達5% ~ 40%，而其不良要因有70% ~ 80%是來自於Pd/Ag膏印刷製程。
本研究針對Pd/Ag膏印刷製程機器參數設定，首先進行田口實驗以找出穩健的參數設定；然而田口方法（Taguchi’s Methods）所找之解為一局部最佳解，故利用田口實驗的資料建立Metamodel模式，而此Metamodel將分別運用兩種方式建立並最佳化，其一為反應曲面法（Response Surfaces Method），另一為類神經網路（Neural Network, NN）結合基因演算法（Genetic Algorithms, GA）。

Due to the mobile information and communication electronic products are much more functional, higher reliability, lower cost and smaller volume than the before. A revolution to integrate the passive components, the most widely used components in the circuit of the electronic products is processing. Multi-layer Ceramic Capacitor, MLCC, which have advantages such as small volume, adjustable capacity and faster fabrication procedure. According to these advantages, MLCC becomes the most important passive component to construct of mobile phone.
In the seriously complicated manufacturing process of MLCC, we have lots of uncertainly fabrication parameters. So how to control the parameters to maintain the stable quality of products is a serious question. As we know, the electric property is a important indication of quality in MLCC fabrication procedure. According to the statistics of the past fabricate information and the experience of engineers, we have a result about the failure rate of MLCC fabrication procedure is about 5% to 40%, and the factor of failure is almost formed in the process of Pd/Ag film printing.
In this research, we setup the parameters of Pd/Ag film printing procedure machines, first find out the stable parameters by Taguchi’s experiment, then establish Matamodel by the information of Taguchi’s experiment. There are two manners to establish and optimum in Matamodel, one is Response Surfaces Method, and the other is Neural Network combine with Genetic algorithms.

上品企業管理顧問有限公司，Available: http://www.qtdc.com.tw/Index-knowhow.htm

中時電子報，(民91， 12月4日)，
Available:http://forums.chinatimes.com.tw/dictionary/passive.asp

李輝煌，(民89)，田口方法：品質設計的原理與實務，高立出版。

技術尖兵，(民91，6月4日)，Available: http://www.st-pioneer.org.tw/news/910604-3.htm

被動元件產業分析, Available:
http://www.esunsec.com.tw/z/zh/zhb/zhb_23060.asp.htm

許正源，(民89)，「積體被動元件與模組技術專題/清淨鋼專題國內專刊文章--積體被動元件與模組技術」，工研院材料所工業材料月刊 第165期 2000年 9月出刊Available: http://como.org.tw/domstic_indtl.asp?recno=1

許正源，(民88)，「輕金屬特刊：具環保性的陶瓷電容器」，工業材料月刊第152期1999年8月出刊，Available: http://www.mrl.itri.org.tw/info/industrial/152.htm

黃筱潔，(民88，8月21日)，「我國被動元件產業前景-被動元件系列專題之一」，Available: http://www.barits.com.tw/Research/01/01-880821-00059.html

葉怡成，(民89)，類神經網路模式應用與實作，儒林圖書公司。

葉怡成，(民91)，應用類神經網路，儒林圖書有限公司

經濟部工業局新聞稿，(民89，5月26日). Available:
http://www.moeaidb.gov.tw/news/news/n89/n890526.htm

劉仲明，(民89)，「積體被動元件模組專題/電容器關鍵技術及應用專題: 高頻無線通訊元件模組化的關鍵─陶瓷積體被動元件技術」，工研院材料所工業材料月刊 第176期 2001年 8月出刊，
Available:http://itisdom.itri.org.tw/_l2ajve4leoo_/materials.nsf/49bf132b4
3a14f49482569c1002e1898/a8b01641a11a7ae548256aab00378925?OpenDocument

鄧世輝，(民76)，漫談傳統型品質工程與田口型品質工程，品質管制月刊，第二十三卷，第一期，第34-44頁，

鄭燕琴，(民82)，田口品質工程技術理論與實務，中華民國品質管制學會發行。

顏明賢，(民80)，「2002年全球手機產業需求概況」，寶來證券，Available:
http://www.moneydj.com/z/zh/zhd/zhdz/zhdz_BB83658C-828E-4534-A479-ED70147
64C3C.asp.htm

蘇木春、張孝德，(民86)，「機械學習：類神經網路、模糊系統以及基因演算法則」，全華科技圖書股份有限公司。

蘇朝墩，(民91)，品質工程，中華民國品質學會。

鍾清章，(民83)，品質工程，中華民國品質管制學會。

羅錦興，(民90)，品質工程設計指引，中國生產力中心。

April, J., Glover, F., Kelly, J. and Laguna, M., 2001,Simulation/optimization using "real-world" applications., Proceedings of the 2001 Winter Simulation Conference, 1, 134-138.

Badiru, A.B. and Sieger, D.B.,1998, Neural network as a simulation metamodel in economic analysis of risky projects. European Journal of Operation Research, 105,130-142.

Baker, J. E., 1985, Reducing bias and inefficiency in the selection algorithm. In Proc. 2nd International Conference Genetic Algorithm.14-21.

Box, D.E.P., Hunter, W.G. and Hunter, J.S., 1978, Statistics for Experimenters. An Introduction to Design, Data Analysis, and Model Building, New York: Wiley.

Chambers, M. and Mount-Campbell, C.A.,2002, Process optimization via neural network metamodeling. International Journal of Production economics, 79, 93-100.

Chaveesuk, R. and Smith, A. E., 1999, A neural network metamodel approach to capital investment decision analysis. IEEE Neural Networks, 1999. IJCNN '99. International Joint Conference, 6, 3844-3849.

Cheng, C.S., 1995, A multi-layer neural network model for detecting changes in the process mean. Computers and Industrial Engineering, 28, 51-61.

Choudhury, I.A. and El-Baradie, M.A., 1990, Machinability assessment of inconel 718 by factorial design of experiment coupled with response surface methodology. Journal of Materials Processing Technology, 95,30-39.

Coleman, D. E. and Montgomery, D. C., 1993, A systematic approach to planning for a designed industrial experiment ( with discussion ). Technometrics, 35, 1-27.

Cook, D. and Chiu, C.C., 1998, Using radial basis function neural networks to recognize shifts in correlated manufacturing process parameters. IIE Transactions, 30 227-234.

Drias, H., Khabzaoui, M.,2001, Scatter search with random walk strategy for SAT and MAX-W-SAT problems. Lecture Notes in Computer Science, 2070, 35-44.

Eshelman, L. J., Caruanu, R.A. and Schaffer. J.D., 1989, Biases in crossover landscape. In Proc. 3rd International Conference Genetic Algorithms, 10-19.

Evolver, 1998, Palisade Corporation, Newfield NY.

Farrington, P.A., Nembhard, H.B., Sturrock, D.T. and Evant, G.W., 1999, The development of a methodology for the use of neural networks and simulation modeling in system design. Proceedings of the 1999 Winter Simulation Conference, 537-542.

Friedman, L. W. and Pressman, I., 1988, The metamodel in simulation analysis: can it be trusted?, Journal of the Operational Research Society, 39, 939-948.

Goldberg, D. E., 1989, Genetic algorithm in search, optimization and machine learing. Addison-Wesley. New York.

Glover, F., 2001, A template for scatter search and path relinking. Lecture Notes in Computer Science, 1363, 3-51.

Guest editorial, 2000, Ant algorithms, Future feneration computer systems, 16, 5-6.

Hamiez, J.P. and Hao, J.K., 2002, Scatter search for graph coloring. Lecture Notes in Computer Science, 2310, 168-179.

Harris, J. M. and Roesch, E.B., 2001, US Passive Component Suppliers, UBS

Holland, J., 1975, Adaptation in natural and artificial system. University of Michigan Press, Ann Arbor.

Hou, T.H., Lin, L. and Scott, P.D., 1993, A neural network-based automated inspection system with an application to surface mount devices. International Journal of Production Research, 31, 1171-1187.

Horng, H. C. and Cochran, J.K., 2001, Project surface regions: a decision support methodology for multitasking workers assignment in JIT systems. Computers & Industrial Engineering, 39, 159-171.

Huang, S. and Zhang, H., 1993, Neural networks in manufacturing: a survey. IEEE/CPMT International Electronics Manufacturing Technology Symposium, 177-190.

Huang, Y.L., Thomas, F.E. and David, M.H., 1994, Constructing a reliable neural network model for a plasma etching process using limited experimental data. IEEE Transactions on Semiconductor Manufacturing, 7, 333-344.

Hush, D. R., and Horne, B. G., 1993, Progress in supervised neural networks: what’s new since lippmann. IEEE Signal Processing Magazine, January, 8-39.

Kim, B. and May, G.S., 1994, An optimal neural network process model for plams etching. IEEE Transactions on Semiconductor Manufacturing, 7, 12-21.

Kleijnen, J. P. C., 1979, Regression metamodels for generalising simulation results, IEEE Transactions on Systems, Man and Cybernetics, 2, 93-96.

Kleijnen, J. P. C., 1988, Experimental design and regression analysis in simulation: an FMS case study, European Journal of Operational Research, 33, 257-261.

Kleijnen, J. P. C. and Rotmans, J., 1992, Techniques for sensitivity analysis of simulation models: a case study of CO2 greenhouse effect, Simulation, 58, 410-417.

Laguna, M. and Marti, R.,2002, Neural network prediction in a system for optimizing simulations. IIE Transactions, 34, 273-282.

Law, A. M., 1990, Simulation model's level of detail determines effectiveness, Industrial Engineering, 10, 16-18.

Lee, S.F. and Spanos, C.J., 1995, Prediction of wafer state after plasma processing using real-time tool data. IEEE Transactions on Semiconductor Manufacturing, 8, 252-261.

Lee, K.K., Brown, G., Dagnall, R., Bicknell, T.R. and May, G.S., 2000, Using neural networks to construct model of the molecular beam epitaxy process. IEEE Transactions on Semiconductor Manufacturing, 13, 34-45.

Lewis, C. D., 1982, Industrial and Business Forecasting Method, Butterworth Scientific, London.

Lippmann, R. P., 1987, An introduction to computing with neural nets. IEEE ASSP Magazine, April, 4-22.

Lo, Y. and Tsao, C.C., 2002, Integrated Taguchi method and neural network analysis of physical profiling in the wirebonding process. IEEE Transactions on Components and Packaging Technologies, 25, 270-277.

Lingo, 2001, Lindo Inc., Chicago, Illinois.

Madu, C. N. and Chanin, M. N., 1992,Regression metamodel of a maintenance float problem with Erlang-2 failure distribution, International Journal of Production Research, 30, 871-885.

Malik, Z. and Rashid, K., 2000, Comparison of optimization by response surface methodology with neuofuzzy methods. IEEE Transactions on Magnetics, 36,241-257.

Marco, D., Eric, B. and Guy, T., 2000, Ant algorithms and stigmergy. Future feneration computer systems, 16, 851-871.

Martinez, G.S., Forbes, H. C., Hussain, N. and Charles, A., 1994, Reducing waste in casting with a predictive neural model. Journal of Intelligent Manufacturing, 5, 277-286.

May, G.S., Forbes, H.C., Hussain, N. and Charles, A., 1998, Modeling component placement error in surface mount technology using neural networks. IEEE Transactions on Components, Packaging, and Manufacturing Technology-Part C, 21 , January.

Meidt, G. J., and Bauer, K. W. 1992, PCRSM: A decision support system for simulation metamodel construction. Simulation, 59, 183-191.

Michale-wicz, Z., 1996, Genetic algorithms + data structures = evolution programs. 3rd Edition, Springer, Berlin.
Minitab user's guide, 2000, Minitab Inc., State College, PA, U.S.A.

Monmarche´, N., Venturini, G. and Slimane, M., 2000, On how Pachycondyla apicalis ants suggest a new search algorithm. Future feneration computer systems, 16, 937-946.

Montgomery, D.C. and Bettencount, V.N., 1977, Multiple response surface methods in computer simulation. Simulation Conuncils, Inc.October, 113-121.

Montgomery, D. C., 1997, Design and Analysis of Experiments, 4thed., John Wiley & Sons, New York.

NeuralWorks Professional II/PLUS user's guide, 2000, NeuralWare, Carnegie, Pennsylvania.

Pierreval, H. 1992,Rule-based simulation metamodels, European Journal of Operational Research, 61, 6-17.

Pierreval, H. and Tautou, L., 1997, Using evolutionary algorithms and simulation for the optimization of manufacturing systems, IIE Trandactions, 29, 181-189.

Phadke, M.S., 1989,Quality Engineering Using Robust Design, Prentice-Hall.

Pongcharoen, P., Hicks, C., Braiden, P. M. and Stewardson, D, J., 2000, Determining optimum gentic algorithm parameters for scheduling the manufacturing and assembly of complex products. International Journal of Production Economics, 78, 311-322.

Pugh and G.A.,1989, Synthetic neural networks for process control. Computers and Industrial Engineering, 17, 24-26.

Pugh and G.A., 1991, A comparison of neural networks to SPC charts. Computers and Industrial Engineering, 21, 253-255.

Rees, L.P., Clayton, E.R. and Taylor, B.W., 1985, Solving multiple response simulation models using modified response surface methodology within a lexicographic goal programming framework. IIE Transactions, March,47-57.

Rotmans, J. and Vrieze, O. J. 1990,Metamodelling and experimental design:Case study of the greenhouse effect , European Journal of Operational Research, 47, 317-329.

Ryu, Y.K. and Cho, H.S., 1996, Visual inspection scheme for use in optical solder joint inspection system. Proceedings of the 1996 IEEE International Conference on Robotics and Automation, 3259-3264.
Sabuncuoglu, I. and Touhami. S., 2002, Simulation metamodelling with neural networks: an experimental investigation. International Journal of Production Research, 11, 2483-2505.

Safizadeh, M. H., and Thornton, B. M. 1984,Optimization in simulation experiments using response surface methodology, Computer and Industrial Engineering, 8, 11-27.

Simon Haykin, 1999, Neural Networks: A Comprehensive Foundation, Prentice Hall.
Shang, J.S. and Tadikamalla, P.R., 1998, Multicruteria design and control of cellular manufacturing system through simulation and optimization. International Journal of Production Research, 36, 1515-1528.

Su, C. and Chiang T., 2002, Optimal design for a ball grid arry wire bonding process using a neuro-genetic approach. IEEE Transactions on Electronics Packaging Manufacturing, 25, 13-18.
Syswerda, G., 1989, Uniform crossover in genetic algorithm. In Proc. 3rd International Conference Genetic Algorithm. 2-9.

Tay, K-M. and Butler, C., 1999, Methodologies for experimental design: a survey, comparison, and future predictions. Quality Engineering, 11, 343-356.

Warburg LLC, New York, June 2001.Copyright © 2001 Darfon Electronic Corp. [Online] Available: http://www.darfon.com.tw/chinese/product/pro3.htm

White, D.A., Boning, D., Butler, S.W. and Barna, G.G., 1997, Spatial characterization of wafer state using principal component analysis of optical emission spectra in plasma. IEEE Transactions on Semiconductor Manufacturing, 10, 52-61.

Williams ,R. J. and Zipser, D., 1989, A learning algorithm for continually running fully recurrent neural networks. Neural Computation, 1, 271-279.

Yang, T., Su, C. and Feng, Y., 2001, In search of a product mix for semiconductor wafer fabrication facilities by a combined simulation/neural network approach. International Journal of Production Research, 8, 142-149.

Yang, T. and Chen, M., 2002, Design of manufacturing systems by a hybrid approach with neural network metamodelling and stochastic local search. International Journal of Production Research, 40, 71-92.

Yang, T. and Tseng, L., 2002, Solving a multi-objective simulation model using a hybrid response surface method and lexicographical goal programming approach－a case study on integrated circuit ink-making machines. Journal of the Operational Research Society, 53, 211-221.

Yu, B. and Popplewell, K., 1994, Metamodels in manufacturing: a review, International Journal of Production Research, 32, 787-796.

Zhang, H.C. and Huang, S.H., 1995, Applications of neural networks in manufacturing, International Journal of Production Research, 33, 705-728.