隨著光電產業的製造系統日趨複雜，為求系統能夠穩定運作，避免製程中發生不正常的運作卻無法即時偵測，造成生產線停機和嚴重的損失，所以製造系統異常之診斷變成相當重要的課題。

　　TFT-LCD產業為一資本與技術密集的產業，其結合了前段Array半導體製程技術，中段Cell液晶製程技術與後段Module組裝製程技術。在預期未來面板有供過於求的現象下，如何壓低整體製造成本將是獲利與否的關鍵因素。因此生產品質的良率與提高設備使用率等方法，是降低成本，提昇產業競爭力的不二法門。

　　本研究將以台南科學園區某光電廠商之濺鍍製程為例子，從現場蒐集到的資料利用主成份分析法來對製程參數作一篩選的動作，並以各主成份得點作為輸入變數，將工程製程管制的觀念結合模糊類神經網路和類神經網路來發展一套以人工智慧為基礎的膜厚診斷系統，最後並利用統計方法的區別分析來驗證本研究之績效，實驗中發現利用類神經來建立膜厚診斷模式的績效為最佳。

　　With the optical electrical industry’s manufacturing systems being more complicated, we try to make the systems stable, prevent the abnormal working in the manufacturing process from being detected at once and make the production lines stop working and a serious loss. In order to make the systems stable, it is very important to diagnose where the manufacturing system is wrong.

　　TFT-LCD is an industry of capital and high technology. It combines Array semiconductor production-process technology in front part, Cell transistor-liquid production-process technology in middle part, and Module assembly production-process technology in back part. We predict that the panel will be in more supply than demand in the future. We will face how to make lower the price of the panel and less the profit in the market. The key factor of the profit is how to get lower the net cost of manufactions. So the high quality of productions and good equipment will be the only way to get lower the net cost and increase the industry competition.

　　This study is a sputter process of light and electricity manufactures in Tainan Science-based Industrial Park. The search collected data on the spot to use Principal Component Analysis for screening, get loading from every element to be input parameters, the idea of Engineering Process Control combines Nourofuzzy and Neural Network to develop a thick diagnosis system using Artificial Intelligent. Finally, use Discriminant Analysis to prove this study. Finally, the performance using neural network to develop the diagnoise system is better.

鼎新電子報，(民92，4月)，Available：http://www.dsc.com.tw/newspaper/42/42index.asp

光電產業分析，(民92，10月4日)，Available： http://bludebser.adsldns.org/cgi-bin/MT/mt-tb.cgi/30

鄭春生，(民 89)，品質管理，三民書局。

陳順宇，(民 89)，多變量分析 (二版)，華泰書局。

陳順宇，(民 87)，統計學 (三版)，華泰書局。

王淑珍，(民92)，台灣邁向液晶王國之秘密，中國生產力中心。

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，儒林書局有限公司。

黃俊英，(民89)，多變量分析，華泰書局。

顧鴻壽，(民91)，光電液晶平面顯示器技術基礎及應用，新文京開發
出版有限公司。

Altrock, C. V., 1995, Fuzzy Logic & Neurofuzzy Application Explained, Prentice Hall, New Jersey.

Arafeh, L., Singh, H. and Putatunda, S. K., 1999, A neuro fuzzy approach to material processing, IEEE Transactions on Systems, Man, and Cybernetics — Part C： Applications and Reviews, 29, 362-370.

Box, G. E. P. and Kramer T., 1992, Statistical process monitoring and feedback adjustment-a discussion, Technometrics, 34, 251-267.

Boyles, R. A., 1991, The Taguchi Capability Index, Journal of Quality Technology, 23, 17-26.

Bregler, C. and Omohundro, S. M., 1994, Surface learning with applications to lipreading, Morgan Kaufmann Publishers, 43-50.

Chang, S. I. and Aw, C. A., 1996, A neural fuzzy control chart for detecting and classifying process means shifts, International Journal of Production Research, 34, 2265-2278.

Chen, K. S., Huang, M. L. and Li, R. K., 2001, Process capability analysis for an entire production, International Journal of Production Research, 39, 4077-4087.

Chen, J. and Liao, C. M., 2002, Dynamic process fault monitoring based on neural network and PCA, Journal of Process Control, 12, 277-289.

Chen, Y. M. and Lee, M. L., 2002, Neural networks-based scheme for system failure detection and diagnosis, Mathematics and Computers in Simulation, 58, 101-109.

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

Cherian, R. P., Smith, L. N. and Midha, P. S., 2000, A neural network approach for selection of power metallurgy materials and process parameters, Artificial Intelligence in Engineering, 14, 29-44.

Elsayed, E. A., Ribeiro J. L. and Lee M. K., 1995, Automated process control and quality engineering for process with damped controllers, International Journal of Production Research, 33, 2923-2932.

Figuiredo, M. and Gomide, F., 1999, Design of fuzzy system using neurofuzzy networks, IEEE Transaction on Neural Network, 10, 815-827.

Fuzzytech user’s manual, 2001, Inform Software Corporation, Aachen, Germany.

Fuller, R., 1999, Introduction to Neuro-Fuzzy Systems, Physical-Verlag Heidelberg, New York.

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

Ishibuchi, H., Nozaki, K., Yamamoto, N. and Tanaka, H., 1995, Selecting fuzzy if-then rules for classification problems using genetic algorithms, IEEE Transactions on Fuzzy Systems, 3, 260-270.

Ishibuci, H., Nakashima, T. and Murata, T., 1995, A fuzzy classifier system that generates fuzzy if-then rules for pattern classification problems, IEEE International Conference on Evolutionary Computation, 2, 759-764.

Ishibuchi, H., Nozaki, K., Yamoto, N. and Tanaka, H., 1995, Selecting fuzzy if-then rules for classification problems using genetic algorithm, IEEE Transactions on Fuzzy Systems, 3, 260-270.

Ishibuchi, H., Nakashima, T. and Murata, T., 1996, Genetic-algorithm-based approaches to the design of fuzzy systems for multi-dimensional pattern classification problems, Proceedings of IEEE International Conference on Evolutionary Computation, 229-234.

Jackson, J. E., 1980, Principal components and factor analysis: part Ⅰ－ principal components, Journal of Quality Technology, 12, 201-213.

Jackson, J.E., and Mudholkar, G. S., 1979, Control procedures for residuals associated with principal component analysis, Technometrics, 21, 341-349.

Janakiram, M. and Keats, J. B., 1998, Combing SPC and EPC in a hybrid Industry, Journal of Quality Technology, 30, 189-199.

Jang, J. S., 1992, Neuro-fuzzy modeling：architecture, analysis and applications, Ph.D dissertation, University of California, Berkeley.

Jang, J. S., Sun, C. T. and Mizutani, E., 1997, Neural-Fuzzy and Soft Computing, Prentice Hall, New Jersey.

Johnson, R. A. and Wichern, D. W., 2002, Applied Multivariate Statistical Analysis, 5th ed., Prentice Hall, New Jersey.

Kane, V. E., 1986, Process capability indices, Journal of Quality Technology, 18, 41-52.

Kano, M., Hasebe, S., Hashimoto, I. and Ohno, H., 2001, A new multivariate statistical process monitoring method using principal component analysis, Computers and Chemical Engineering, 25, 1103-1113.

Kim, J. C., Kim, D. H., Kim, J. J., Ye, J. S. and Lee, H. S., 2000, Segmenting the Korean housing market using multiple discriminant analysis, Construction Management and Economics, 18, 45-54.

Ko, K. W. and Cho, H. S., 2000, Solder joint inspection using a neural network and fuzzy rule-based classification method, IEEE Transactions on Electronics Packing Manufacturing, 24, 93-103.

Lin, C. T. and Lee, C. S., 1996, Neural fuzzy systems, Prentice Hall, New Jersey.

MacGregor, J. F., 1990, A different view of the funnel experiment, Journal of Quality Technology, 22, 255-259.

MacGregor, J. F., Jaeckle, C., Kiparissides, C. and Koutoudi, M., 1994, Process monitoring and diagnosis by multiblock methods, American Institute of Chemical Engineering Journal, 40, 826-838.

Medsker, L. R. and Liebowitz, J., 1994, Design and Development of Expert Systems and Neural Networks, Macmillan, New York.

Meesad, P. and Yen, G. G., 2000, Pattern classification by a neurofuzzy network:application to vibration monitoring, ISA Transactions, 39, 293-308.

Misra, M., Yue, H. H.,Qin, S. J. and Ling, C., 2002,
Multivariate process monitoring and fault diagnosis by multi-scale PCA, Computers and Chemical Engineering, 26, 1281-1293.

Mongomery, D. C., 2001, Introduction to Statistical Quality Control, 4th ed., John Wiley & Sons, New York.

Montgomery, D. C., Keats, J. B., Runger, G. C. and Messina, W. S., 1994, Integrating statistical process control and engineering process control, Journal of Quality Technology, 26, 79-87.

Nauck, D., Klawonn, F. and Kruse, R., 1997, Foundations of Neuro-Fuzzy Systems, John Wily & Sons, New York.

Nauck, D., 2000, Adaptive rule weights in neuro-fuzzy systems, Neural Computing & Applications, 9, 60-70.

Nozaki, K., Ishibuchi, H. and Tanaka, H., 1996, Adaptive fuzzy rule-based classification systems, IEEE Transactions on Fuzzy Systems, 4, 238-250.

Patton, R. J., Chen, J. and Benkhedda, H., 2000, A study of neuro-fuzzy systems for fault diagnosis, International Journal of Systems Science, 31, 1441-1448.

Pearn, W. L., Yang, S. L., Chen, K. S. and Lin, P. C., 1992, Distributional and inferential properties of process capability indices, Journal of Quality Technology, 24, 216-233.

Raich, A. and Cinar, A., 1996, Statistical process monitoring and disturbance diagnosis in multivariable continuous process, American Institute of Chemical Engineering Journal, 42, 995-1009.

Roverso, D., 2000, Soft computing tools for transient classification, Information Sciences, 127, 137-156.

Sachs E., Hu A. and Ingolfsson A., 1995, Run by run process control combining SPC and Feedbacck Control, IEEE
Transactions on Semiconductor Manufacturing, 8, 26-43.

Smith, T. H., Boing, D. S., Stefani J. and Butler, S. W., 1998, Run by run advance process control of mental sputter deposition, IEEE Transactions on Semiconductor Manufacturing, 11, 276-284.

Statistica The small book, 2002, StatSoft Inc., USA.

Trevino, L. J. and Daniels, J. D., 1995, FDI theory and foreign direct investment in the United Ststes: a comparison of investors and non-investors, International Business Review, 4, 177-194.

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

Yanger, R., 1992, Implementing fuzzy logic controllers using a neural network framework, Fuzzy Sets and Systems, 48, 53-64.

Zedeh, L. A., 1965, Fuzzy Sets, Information Control, 8(3), 338-353.

Zhao, W., Chellappa, R. and Krishnaswamy, A., 1998, Discriminant analysis of principal components for face recognition, In 3rd International Conference on Automatic Face and Gesture Recognition, 336-341.