六標準差已經廣泛的應用在全球不同的企業，並儼然成為在品質的範疇中最重要的議題。六標準差是一具有完整架構的方法論，其透過持續的改善協助企業達到長期目標。然而，在推行六標準差活動時仍會遭遇到許多的困難，例如，如何有效產生可行的六標準差專案、在有限的資源情況下如何選取最重要的專案。另一方面，半導體產業在國內政府倡導下蓬勃發展，這類產業具有分工細密、組織架構複雜，在導入六標準差時會有缺乏效率且無法確實達到營運目標的困擾。因此一套有系統、有架構的六標準差導入方案對於半導體業的幫助必然有其助益。
本研究發展出一套六標準差方法論，包括macro模式與micro 模式。Macro model主要探討的是六標準差策略方面，期許透過此模式將方案進行分類，以找出對企業本身具有高度利益與可行的專案。Macro model主要是透過風險及利益兩方面建構整個評估模式。另一方面，micro model是針對六標準差專案的執行層面，利用六標準差有效的執行步驟來達到預期的專案目標。本研究也導入用以解決複雜問題的計算智慧技術，更進一步的協助企業解決專案的問題。
本研究以半導體廠為例透過所提出的macro model，為個案公司快速的篩選有用的專案，並成功的將專案分成黑帶、綠帶及無效益的專案種類。此外，運用micro model的問題解決過程以及計算智慧(computational intelligence)的技術，本研究有效地降低個案公司的不良問題點，並大大的提昇了良率。

Six Sigma has been widely adopted in a variety of industries in the world and it has become one of the most important subjects of debate in quality management. Six Sigma is a well-structured methodology that can help a company achieve expected goal through continuous project improvement. Some challenges, however, have emerged with the execution of the Six Sigma. For examples, how are feasible projects generated? How are critical Six Sigma projects selected given the finite resources of the organization? On the other hand, semiconductor manufacturing industries in Taiwan have had significant growth over the last decade in the world and also make up for the bulk of economic benefits. Semiconductor foundries are multi-layer organizations with complex systems and complicated division of labor. Due to the organization structure is huge; when a semiconductor foundry executes the Six Sigma methodology is ineffective and difficult to achieve the organization objectives. A completely and system procedure for implementing the Six Sigma methodology into semiconductor manufacturing industries is necessary and beneficial.
This study aims to develop the knowledge based Six Sigma methodology which is involved macro model and micro model. The macro model is focus on the strategy of Six Sigma which is including project generation, project evaluation, project selection and so on. The objective of macro model is to effectively identify the vital project. In addition, the micro model is aimed at the practical of Six Sigma. The micro model is to implement the DMAIC cycle to achieve the objective of each project. Furthermore, we conduct the computational intelligence approach to resolve the complex project problem.
This proposed procedure of macro model was successfully help the case company divided project into Black belt project, green belt project and profitless project. In addition, the micro model which is conducting the computational intelligence approach is effectively decrease the waste of manufacturing process and reaches the optimization situation.

摘要 i
ABSTRACT iii
誌謝 v
CONTENTS vi
LIST OF TABLES vii
LIST OF FIGURES viii
CHAPTER 1 INTRODUCTION 1
1.1 Overview 1
1.2 Research Motivations 4
1.3 Research Objectives 5
1.4 Organization 6
CHAPTER 2 REVIEW OF RELATED RESEARCH 7
2.1 Six Sigma 7
2.2 Failure Mode and Effects Analysis 9
2.3 Analytic Hierarchy Process 12
2.4 Response Surface Method 13
2.5 Desirability Function 15
2.6 Neural Networks 16
2.7 Genetic algorithms 19
2.8 Multi-objective problem and computational intelligence 22
CHAPTER 3 PROPOSED APPROACH 25
3.1 Overview 25
3.2 Macro model 28
3.3 Micro model 31
CHAPTER 4 CASE STUDY: MACRO MODEL 38
4.1 Background of the case company 38
4.2 Implementation 38
4.3 Concluding remarks 46
CHAPTER 5 CASE STUDY: MICRO MODEL 48
5.1 Introduction 48
5.2 Improving the IMD process by using Six Sigma DMAIC methodology 50
5.3 Improving the IMD process by a computational intelligence approach 66
5.4 Comparison and discussions 69
CHAPTER 6 CONCULSIONS 71
REFERENCES 73
Appendix A 81

[1] Abouhamze, M., and Shakeri, M., “Multi-objective stacking sequence optimization of laminated cylindrical panels using a genetic algorithm and neural networks,” Composite Structures, vol. 81, pp. 253-263, 2007.
[2] Adachi, W., and Lodolce, A. E., “Use of failure mode and effects analysis in improving the safety of i.v. drug administration,” American Journal of Health-System Pharmacy, vol. 62, Issue 9, pp. 917-920, 2005.
[3] Alonso, J. M., Alvarruiz, F., Desantes, J. M., Hernández, L., Hernández, V., and Moltó, G., “Combining Neural Networks and Genetic Algorithms to Predict and Reduce Diesel Engine Emissions,” IEEE Transactions on Evolutionary Computation, vol. 11, no.2, pp. 46-54, 2007.
[4] Arita, T. and McCann, P., “The spatial and hierarchical organization of Japanese and US multinational semiconductor firms,” Journal of International Management, vol. 8, pp. 121-139, 2002.
[5] Ashu, J., Sanaga, S., Kumar, B. R., “Determination of an optimal unit pulse response function using real-coded genetic algorithm,” Journal of Hydrology, vol. 303, Issue 1-4, pp. 199-214, 2005.
[6] Bañuelas, R., Antony, J., and Brace, M., “An Application of Six Sigma to Reduce Waste,” Quality and Reliability Engineering International, vol. 21, Issue 6, pp. 553-570, 2005.
[7] Berry, M. J. A., and Linoff, G. S., Data Mining Techniques for Marketing, Sales, and Customer Relationship Management, Wiley Publishing, Inc., 2004.
[8] Box, G., and Wilson, K. B., “The exploitation of response surfaces: some general considerations and examples,” Biometrics, vol. 10, pp. 16-60, 1954.
[9] Chen, F.-L., and Liu, S.-F., “Neural network approach to recognize defect spatial pattern in semiconductor fabrication,” IEEE Transactions on Semiconductor Manufacturing, vol. 13, pp. 366-373, 2000.
[10] Coronado, R. B., and Antony, F., “Critical success factors for the successful implementation of six sigma projects in organizations,” The TQM Magazine, vol. 14, no.2, pp. 92-99, 2002.
[11] Derringer, G. C., and Suich, R., “Simultaneous Optimization of Several Response Variables,” Journal of Quality Technology, vol. 12, pp. 214-219, 1980.
[12] Dutta, J. R., Dutta, P. K., and Banerjee, R., “Optimization of culture parameters for extracellular protease production from a newly isolated Pseudomonas sp using response surface and artificial neural network models,” Process Biochemistry, vol. 39, Issue 12, pp. 2193-2198, 2004.
[13] Fausett, L., Fundamentals of Neural Networks, Prentice-Hall International, 1994.
[14] Goh, T. N., “A strategic assessment of Six Sigma,” Quality and Reliability Engineering International, vol. 18, pp. 403-410, 2002.
[15] Goh, T. N., and Xie, M., “Improving on the Six Sigma paradigm,” The TQM Magazine, vol. 16, no. 4, pp. 235-240, 2004.
[16] Han, S., and May, G., “Using Neural Network Process Models to PECVD Silicon Dioxide Recipe Synthesis via Genetic Algorithms,” IEEE Transactions on Semiconductor Manufacturing, vol. 10, no. 2, pp. 279-287, 1997.
[17] Han, S. M., and Aydil, E., “Structure and chemical composition of fluorinated SiO2 films deposited using SiF4-O2 plasmas,” Journal of Vacuum Science & Technology A: Vacuum, Surfaces, and Films, vol. 15, pp. 2893-2904, 1997.
[18] Harpham, C., Dawson, C. W., and Brown, M. R., “A review of genetic algorithms applied to training radial basis function networks,” Neural Computing and Application, vol. 13, pp.193-201, 2004.
[19] Harry, M. and Schroeder, R., Six sigma: the breakthrough management strategy revolutionizing the world's top corporations, Currency, 2000.
[20] Hoerl, R. W., “Six Sigma Black Belts: What Do They Need to Know?” Journal of Quality Technology, vol. 33, no. 4, pp.319-406, 2001.
[21] Holderbaum, W., “Application of Neural Network to Hybrid Systems With binary Inputs,” IEEE Transactions on Neural Networks, vol. 18, no. 4, 2007.
[22] Hornick, K., Stinchcombe, M., and White, H., “Universal Approximation of an Unknown Mapping and its Derivatives Using Multilayer Feedforward Networks,” Neural Networks, vol. 3, pp. 551-560, 1990.
[23] Hou, T.-H., Su, C.-H., and Chang, H.-Z., “An integrated multi-objective immune algorithm for optimizing the wire bonding process of integrated circuits,” Journal of Intelligent Manufacturing, vol. 19, no. 3, pp. 361-374, 2008.
[24] Hung, S.-Y., Chao, C.-K., Lin, T.-H., and Lin, C.-P., “Applying ANN/GA algorithm to optimize the high fill-factor micrelens array fabrication using UV proximity printing process,” Journal of Micromechiianica and Microengineering, vol. 15, pp. 2385-2397, 2005.
[25] Hwang, H.-S., “Web-based multi-attribute analysis model for engineering project evaluation,” Computers and Industrial Engineering, vol. 46, Issue 4, pp. 669-678, 2004.
[26] Hsu, C.-M., and Su, C.-T., “Multiobjective machine-component grouping in cellular manufacturing: A genetic algorithm,” Production Planning Control, vol. 9, no. 2, pp. 155-166, 1998.
[27] Hsu, S.-C., and Chien, C.-F., “Hybrid data mining approach for pattern extraction from wafer bin map to improve yield in semiconductor manufacturing,” International Journal of Production Economics, vol. 107, Issue 1, pp. 88-103, 2007.
[28] Johnson, R. A., and Wichern, D. W., Applied Multivariate Statistical Analysis, Prentice-Hall, 1998.
[29] Karr, C. L., and Freeman, L. M., Industrial applications of genetic algorithms, CRC Press, 1999.
[30] Khan, Z., Prasad, B., and Singh, T., “Machining condition optimization by genetic algorithms and simulated annealing,” Computers & Operations Research, vol. 24, Issue, 7, pp. 647-657, 1997.
[31] Khuri, A. I., Response surface methodology and related topics, New Jersey, World Scientific, 2006.
[32] Kozakiewicz, J. M., Benis, L. J., Fisher, S. M., and Marseglia, J. B., “Safe chemotherapy administration: Using failure mode and effects analysis in computerized prescriber order entry,” American Journal of Health-System Pharmacy, vol. 62, Issue 17, pp. 1813-1816, 2005.
[33] Kuei, C.-H. and C. N. Madu, “Customer-centric six sigma quality and reliability management,” The International Journal of Quality & Reliability Management, vol. 20, pp. 954-964, 2003.
[34] Kwak, Y. H., and Anbari, F. T., “Benefits, obstacles, and future of six sigma approach,” Technovation, vol. 26, pp. 708-715, 2006.
[35] Layne, K. L., “Methods to determine optimum factor levels for multiple responses in designed experimentation,” Quality Engineering, vol.7, no. 4, pp. 649-656, 1995.
[36] Lee, H. W., Arunasalam, P., Laratta, W. P., Seetharamu, K. N., and Azid, I. A., “Neuro-Genetic Optimization of Temperature Control for a Continuous Flow Polymerase Chain Reaction Microdevice,” Journal of Biomechanical Engineering, vol. 129, pp. 540-547, 2007.
[37] Lim, S. W., Shimogaki, Y., Nakano, Y., and Tada, K., “ Preparation of low dielectric constant F-doped SiO2 films by plasma enhanced chemical vapor deposition,” Applied Physics Letters, vol. 68, Issue 6, pp. 832-834, 1996.
[38] Linderman, K., Schroeder, R. G., Zaheer, S., and Choo, A. S., “Six Sigma: a goal-theoretic perspective,” Journal of Operations Management, vol. 21, Issue 2, pp. 193-203, 2003.
[39] Luo, X., Hou, W., Li, Y., and Wang, Z., “A fuzzy neural network for predicting clothing thermal comfort,” Computer and Mathematics with Applications, vol. 53, pp. 1840-1846, 2007.
[40] Maleyeff, J., and Kaminsky, F. C., “Six Sigma and introductory statistics education,” Education & Training, vol. 44, pp. 82-89, 2002.
[41] Malve, S., and Uzsoy, R., “A genetic algorithm for minimizing maximum lateness on parallel identical batch processing machines with dynamic job arrivals and incompatible job families,” Computers & Operations Research, vol. 34, Issue, 10, pp. 3016-3028, 2007.
[42] Mishra, S., “Neural-network-based adaptive UPFC for improving transient stability performance of power system,” Neural Networks, IEEE Transaction on, vol. 17, Issue 2, pp. 461-470, 2006.
[43] Myers, R. H., and Montgomery, D. C., Response surface methodology: process and product optimization using designed experiments, NY, John Wiley & Sons, 2002.
[44] Naumann, E., and Hoisington, S. H., Customer Centered Six Sigma linking customers, process improvement, and financial results. ASQ Quality Press, 2001.
[45] Ortiz, F. Jr., Simpson, J. R., Pignatiello, J. J. Jr., and Heredia-Langner, A., “A Genetic Algorithm Approach to Multiple-Response Optimization,” Journal of Quality Technology, vol. 36, no. 4, pp. 432-450, 2004.
[46] Pande, P. S., Neuman, R. P., and Cavanagh, R. R., The Six Sigma way : how GE, Motorola, and other top companies are honing their performance, New York, Mcgraw-Hill, 2000.
[47] Park, S.-J., Lee, M.-S., Shin, S.-Y., Cho, K.-H., Lim, J.-T., Cho, B.-S., Jei, Y.-H., Kim, M.-K., and Park, C.-H., “Run-to-run overlay control of steppers in semiconductor manufacturing systems based on history data analysis and neural network modeling,” IEEE Transactions on Semiconductor Manufacturing, vol. 18, Issue 4, pp. 605-613, 2005.
[48] Pfeifer, T., Reissiger, W., and Canales, C., “Integrating Six Sigma with quality management systems,” The TQM Magazine, vol. 16, no. 4, pp. 241-249, 2004.
[49] Quirk, M., and Serda, J., Semiconductor manufacturing technology, New Jersey, Prentice-Hill, 2001.
[50] Raisinghani, M. S., “Six Sigma: concept, tools, and applications,” Industrial Management & Data Systems, vol. 105, no. 4, pp. 491-505, 2005.
[51] Ren, Y., Ding, Y., and Zhou, S. Y., “A data mining to study the significance of nonlinearity in multistation assembly processes,” IIE TRANSACTIONS, vol. 38, no. 12, pp. 1069-1083, 2006.
[52] Rodvold, D. M., McLeod, D. G., Brandt, J. M., Snow, P. B., Murphy, G. P., “Introduction to artificial neural networks for physicians: Taking the lid off the black box,” The Prostate, Vol. 46, pp. 39-44, 2001.
[53] Roland, H. E., and Moriarity, B., System Safety Engineering and Management. John Wiley & Sons, Inc. 1990.
[54] Rumelhart, D. E., Hinton, G. E., and Williams, R. J., “Learning representations by back-propagating errors,” Nature, vol. 323, pp. 533-536, 1986.
[55] Satty, T. L., “Rank from comparisons and from ratings in the analytic hierarchy/ network processes,” European Journal of Operational Research, vol. 168, pp. 557-570, 2006.
[56] Scipioni, A., Saccarola, G.., Centazzo, A. and Arena, F., “FMEA methodology design, implementation and integration with HACCP system in a food company,” Food Control, vol. 13, pp. 495-501, 2002.
[57] Siegel, J. G., and Shim, J. K., The Artificial Intelligence Handbook: Business Applications, South-Western Educational Pub, 2002.
[58] Singh, A.P., Kamal, T. S. and S. Kumar, “Development of ANN-based virtual fault detector for Wheatstone bridge-oriented transducers,” Sensors Journal, IEEE, vol. 5, Issue 5, pp. 1043-1049, 2005.
[59] Storn, R., and Price, K., “Differential Evolution – A Simple and Efficient Heuristic for global Optimization over Continuous Spaces,” Journal of Global Optimization, vol. 11, no. 4, pp. 341-359, 1997.
[60] Su, C.-T., Chen, M.-C., and Chan, H.-L., “Applying neural network and scatter search to optimize parameter design with dynamic characteristics,” Journal of the Operational Research, vol. 56, pp. 1132-1140, 2005.
[61] Su, C.-T., Chiang, T.-L., and Chiao, K., “Optimizing the IC delamination quality via Six-Sigma approach,” IEEE Transactions on Electronics Packing Manufacturing, vol. 28, pp. 241-248, 2005.
[62] Teoh, P. C., and Case, K., “An evaluation of failure modes and effects analysis generation method for conceptual design,” International Journal of Computer Integrated Manufacturing, vol. 18, no. 4, pp. 279-293, 2005.
[63] Treichler, D., Carmichael, R., Kusmanoff, A., Lewis, J., and Berthiez, G., “Design for Six Sigma: 15 Lessons Learned,” Quality Progress, vol. 35, no. 1, pp. 33-42, 2002.
[64] Tsao, C. C., “Comparison between response surface methodology and radial basis function network for core-center drill in drilling composite materials,” International journal of advanced manufacturing technology, vol. 37, Issue 11-12, pp. 1061-1068, 2008.
[65] Vaidya, O. S., and Kumar, S., “Analytic hierarchy process: An overview of applications,” European Journal of Operational Research, vol. 169, pp. 1-29, 2006.
[66] Wang, K.-J., Chen, J.-C., and Lin, Y. -S., “A hybrid knowledge discovery model using decision tree and neural network for selecting dispatching rules of a semiconductor final testing factory,” Production Planning and Control, vol. 16, Issue 7, pp. 665-680, 2005.
[67] Wu, T., Blackhurst, J., and Chidambaram, V., “A model for inbound supply risk analysis,” Computers in Industry, vol. 57, Issue 4, pp. 350-365, 2006.