在半導體製造管理中，良率是反映製程是否有重大問題的一項績效指標，也會直接反映在晶圓廠的成本與獲利能力上。目標良率能否在一定時間內達到主要是取決於良率的學習率。影響良率學習的因素有很多，例如製程、設備與產品組合的複雜性、操作員或工程師的經驗、設備的新舊、製程的週期時間、製程導入的時間、在製品的數量等。然而，不同生產優序(production priority）的貨批（lot）其生產週期及產量與良率學習之間的關係卻很少被探討，因此如何釐清不同生產優序下的生產參數對於良率學習的影響，以及如何決定最適生產優序下的產品組合，以追求最低的成本支出和最大的良率學習，是本論文之研究重點。
首先本研究以生產週期時間等為主要影響變數，配合不同的生產優序，藉由類神經網路（artificial neural networks）結合田口方法（Taguchi Methods）的最適化模型為分析工具，搭配灰色系統理論（grey system theorem）的分析，來探討不同生產優序下的各種影響變數對良率學習的影響。並且在確認類神經網路之準確度後，將先前所得到的關係與影響度加以應用，以得到良率學習變數控管的定性建議與最適化生產規劃的定量分析。
透過本研究所發展出來的最適化類神經模型，可以協助釐清製程改善的因子並加以控管，也可以決定最適化生產優序批量組合與最適化產能擴充模式，以改善半導體廠整體的獲利。

In semiconductor manufacturing, yield learning is the most critical issue for process improvement. Speeding up the yield learning period can reduce the production cost and enhance the business profit. There are many papers which discussed the variables affecting yield（i.e. scheduling, dispatching, cycle time control, operator education…etc.）, but few studies have quantified the impact of the cycle time and the quantity on the yield learning rate based on the historical data of an existing wafer fabrication facility (fab).
In this study, we have constructed a hybrid model using Taguchi Methods and artificial neural networks to find the relationship between the yield learning rate and the related variables (cycle time, product quantity, and production priority) within different stages of a fab life cycle process. Furthermore, the grey system theorem is also applied in order to compare the accuracy and to avoid the drawback in the explanation of the hybrid model.
We can use the results from the analysis of the hybrid model to get insight into the impact of cycle time and product quantity of different production priority on the yield learning rate of a fab life cycle process.
Furthermore, by incorporating the hybrid model and cost function to evaluate the financial benefit of different combination of variable conditions, the optimal hot lot ratio and the optimal capacity ramp-up speed can be found.
Based on the result of the qualitative analysis and the quantitative application, it can reduce the time for process improvement and achieve an ideal yield learning rate for a fab.

英文部分
1. Balasubramaniam, S., A. Sarwar, and D.M.H. Walker（1997）, “Yield Learning in Integrated Circuit Package Assembly” IEEE Transactions on Components, Packaging ,and Manufacturing Technology – Part C, Vol.20, No.2, Apr. 1997.
2. Bohn, R.E.（1995）, “Noise and Learning in Semiconductor Manufacturing” Management Science, Vol.41, No.1, pp.31-42, 1995.
3. Brian, C., R.C. Warner, B. Bidanda and L.N. Kim（2000）, “Predicting glass furnace output using statistical and neural computing methods”, International Journal Product & Research , Vol.38, No.6 , pp.1255-1269, 2000.
4. Cavalieri, S., P. Maccarroneb, and R. Pinto（2004）, Parametric vs. neural networkmodels for the estimation of production costs: A case study in the automotive industry” International Journal Product & Economic 91, pp.165–177, 2004.
5. Chang, C.L., P.H. Liu, and C.C. Wei（2001）, “Failure mode and effects analysis using grey theory”, Integrated Manufacturing Systems, Vol.12, No.3, pp.211-216, 2001.
6. Chang, W.C., M. Yu, R. Wu, C.E. Chen, J. Chen, C.Y. Hsieh, and C.K. Wang（2001）, ”Yield Improvement through Cycle Time and Process Fluctuation Analyses”, IEEE/SEMI Advance Semiconductor Manufacturing Conference, 2001.
7. Cunningham, S.P., and C.J. Spanos（1995）, “Semiconductor Yield Improvement: Results and Best Practices”, IEEE Transactions on Semiconductor Manufacturing Vol.8, No.2, May, 1995.
8. Cunningham, S.P., and, J.G. Shanthikumar（1996）, ”Empirical Result on The Relationship between Die Yield and Cycle Time in Semiconductor Wafer Fabrication”, IEEE Transaction on Semiconductor Manufacturing, Vol.9, No2, May, 1996.
9. Dance, D. and R. Jarvis（1990）, “Using Yield Models Accelerate Learning Curve Progress”, Int’l Semiconductor Manufacturing Science Symposium, 1990.
10. Deng, J.（1982）, “Control problems of Grey System,” System and Control Letters, Vol.5, pp.288-294, 1982.
11. Deng, J.（1987）, “Introduction to Grey System Theory,” The Journal of Grey System, Vol. 1, No.1, pp.1-24, 1987.
12. Ehteshami, B., R.G. Petrakian, and P.M. Shabe（1992）, “Trade-offs in cycle time Management: Hot Lots”, IEEE Transactions on Semiconductor Manufacturing, Vol.5, No.2, May, 1992.
13. Fausett, L.（1994）, Fundamentals of Neural Networks, Prentice-Hall International, 1994.
14. Freeman, J.A. and D.M. Skapura（1992）, “Neural Networks Algorithms, Applications, and Programming Techniques”, Addison-Wesley Publishing Company, New York, 1992.
15. Fronckowiak, D., P. Andreas, and N. Kazumi（1996）, “Using Discrete Event Simulation to Analyze the Impact of Job Priorities on Cycle Time in Semiconductor Manufacturing”, IEEE/SEMI Advance Semiconductor Manufacturing Conference, 1996.
16. Kim, B. and P.G. Tae（2001）, “Modeling Plasma Equipment Using Neural Network”, IEEE Transaction on Plasma Science, Vol.29, N0.1, Feb. 2001.
17. Kim, B., S.S. Han, T.S. Kim, B.S. Kim and S.I. Joo（2003）, ”Modeling Refraction Characteristics of Silicon Nitride Film Deposited in a SiH4-NH3-N2 Plasma Using Neural Network, IEEE Transaction on Plasma Science, Vol.31, No.3, June, 2003.
18. Narahari, Y. and L.M. Khan（1997）, “Modeling the Effect of Hot Lots in Semiconductor Manufacturing System ”, IEEE Transactions on Semiconductor Manufacturing Vol.10, N0.1, Feb. 1997.
19. Nag, P.K., W. Maly, H.J. Jacobs（1997）, “Simulation of Yield / Cost Learning Curves with Y4”, IEEE Transactions on Semiconductor Manufacturing Vol.10, N0.2, May, 1997.
20. Nemoto, K., E. Akcali and R.M. Uzsoy（2000）, “Quantifying the Benefit of Cycle Time Reduction in Semiconductor Wafer Fabrication”, IEEE Transactions on Electronics Packing Manufacturing Vol.23, No.1, Jan. 2000.
21. Riordan, W., R. Miller and J. Hicks（1999）, “Reliability versus yield and die location in deep submicron VLSI” IEEE, pp.207-210, 1999.
22. Rumelhart, D.E., G.E. Hintion, and R.J. Willians（1986）, “Learning Representations by Back-Propagating errors,” Nature, Vol.323, pp.533-536, 1986.
23. Sheu, D.D, and J.Y. Kuo, “A model for preventive maintenance operations and forecasting”, Journal of Intelligent Manufacturing”, Vol 17, No 4, Aug. 2006.
24. Tsaur, R.C.（2005）, ”Fuzzy grey GM(1,1) model under fuzzy system”, International Journal of Computer Mathematics, Vol. 82, No. 2, Feb. pp.141–149, 2005.
25. Vellido, A., P.J. Lisboa, and J.Vaughan（1999）, “Neural Networks in Business: A Survey of Applications”, Expert Systems with Applications, Vol.17, pp.51-70, 1999.
26. Weber, C., V. Sankaran, W. Tobin, Jr. Kenneth, and G. Scher（2002）, “Quantifying the Value of Ownership of Yield Analysis Technologies”, IEEE Transactions on Semiconductor Manufacturing Vol.15, No.4, Nov. 2002.
27. Wein, L.M.（1992）, “On the Relationship between Yield and Cycle Time in Semiconductor Wafer Fabrication”, IEEE Transactions on Semiconductor Manufacturing Vol.5, No.2, May, 1992.
28. Williams, R.J. and D. Zipser（1989）, “A learning algorithm for continually running fully recurrent neural networks”, Neural Computation, Vol.1, pp270-280, 1989.
29. Wu, D., D.L. Olson and Z.Y. Dong（2006）, “Data mining and simulation: a grey relationship demonstration”, International Journal of Systems Science, Vol. 37, No. 13, pp981–986, Oct. 2006.

中文部份
1. 王隆嘉，「知識管理應用於機器設備採購之應用---以半導體廠機器設備為 例」，中原大學，碩士論文，民國92年。
2. 吳漢雄，鄧聚龍，溫坤禮，灰色分析入門，高立出版社，民國85年。
3. 溫坤禮，「灰關聯模型方法與應用」，高立出版社，民國92年。
4. 陳建銘，「多廠區緊急訂單承接評估及跨廠產能規劃探討」，元智大學，碩士論文，民國92年。
5. 鄧聚龍、郭洪、溫坤禮、張廷政、張偉哲，「灰預測模型方法與應用」，高立圖書有限公司，民國88年。
6. 鄧聚龍，「灰色系統理論與應用」，高立出版社，民國89年。
7. 唐麗英，謝坤霖「積體電路良率管理之良率模型建構---類神經網路之應用」，南華大學學術期刊，資訊管理研究，第3卷，民國92年7月。
8. 黃繼寬，「考慮產業差異下，信用評分模型效力分析以Cross Validation為例」，東吳大學經濟研究所，碩士論文，民國94年。
9. 夏郭賢，吳漢雄，灰關聯分析之線性數據前處理探討，灰色系統學刊，第1卷，第1期，頁47-53，民國87年。
10. 葉怡成，「類神經網路應用與實作」，儒林圖書公司，台灣，民國89年。
11. 蘇朝墩，「類神經網路模式與應用---上課補充教材」，清華大學工工系，台灣，民國95年。
12. 蘇朝墩，「品質工程」，中華民國品質學會，台北，民國93年。
13. 蔡碩倉，「台灣地區農會信用部金融預警評等系統之研究」，國立中興大學 農業經濟研究所，博士論文，民國87年。
14. 鄭崇義，「田口品質工程技術理論與實務---（第三版）」，中華民國品質學會，民國89年。
15. 謝坤龍，「台灣公債殖利率預測模型之建構-調適性網路模糊推論系統與灰預測之應用」，東吳大學經濟研究所，碩士論文，民國95年。
16. 施宜協，「運用灰預測、灰色馬可夫與適應性模糊類神經推論系統於市場中立型避險基金建構之研究」，台灣科技大學資訊管理所，碩士論文，民國95年。