對半導體製造業而言，複雜的晶圓製造過程、昂貴的原材料及嚴格之生產環境等因素，造成了龐大的生產成本，各晶圓製造廠莫不急於藉由各種製程控制與分析手法，達到提升良率及降低成本之目的。近年許多半導體廠投入許多資源於先進製程控制系統(Advanced Process Control；APC)，在先進製程控制領域內，失效偵測與分類系統(Fault Detection & Classification；FDC)的導入與研發是其重要之一部分。藉由FDC系統能快速線上偵測機台運作之異常狀態，提升製程良率。本研究以模糊系統及決策樹為基礎，針對黃光區軟烘烤製程之升溫曲線建構FDC系統。將所選取之曲線特徵值輸入模糊系統，可獲得一判斷異常曲線狀態之判別值，當判別值判定為異常時可經異常規則庫辨別何種異常現象，此規則庫經由事先收集整理之異常曲線資料，依曲線特徵值以決策樹之CART演算法所建構。經桃園某半導體廠所得之410筆資料實際驗證，其42筆異常曲線皆被此系統辨識出，剩下368筆正常曲線資料僅只有13筆遭誤判，但誤判的結果中發現這些資料也可能成為曲線升溫異常的前兆，因此，可證明所建構之模糊系統對於升溫曲線之判別能力可符合半導體製造業之實際需求。藉由本系統可輔助工程師快速且正確的尋找出異常曲線，所建構之異常曲線規則庫亦可提供製程工程師一良好之參考依據，能識別為何種異常曲線並找出製程問題所在，進一步達成良率提升之目標。

For semiconductor industry, there are several factors influencing the increasing cost, such as complicated Wafer process, expensive raw materials and strict production environment. To improve yield rate and decrease production cost, wafer fabrication factory puts emphasis on the method of its process control and analysis. In recent years, many semiconductor foundries have invested a large sum of capital in Advanced Process Control (APC). In the field of APC, the induction and development of Fault Detection & Classification (FDC) is definitely one of the important parts. FDC can rapidly detect abnormal situation of operation machine, so as to improve the yield rate. Based on fuzzy system and decision tree, the research tries to construct an FDC system on heating curve monitoring of soft bake in photolithography area. To key in characteristics of certain heating curve to the system, it can obtain one coefficient of determination to identify abnormal status. As the coefficient of determination reveals to be abnormal, rule base can identify what kind of abnormal situation it is. With data collection and extracting of characteristics of abnormal curve, this research adopts Classification and Regression Trees (CART) to construct its rule base. 410 process data collected from one wafer fabrication factory to test and verify the presented FDC system. Experiment results showed that 42 abnormal curves could be successfully identified by the system. Only 13 curves are incorrectly identified out of the other 368 normal curves. And these 13 curves are the augury of process become aberrance possibly. Therefore, the presented system helps semiconductor fabrication companies to detect abnormal heating curves in an efficient way. Process engineers are able to detect abnormal curves immediately with the aid of this system and therefore quickly identify corresponding situations correctly via the rule base.

1. 王大俊，認識Fuzzy-第三版, 全華科技圖書股份有限公司，2005。
2. 王建雄，「模糊控制器之設計思維」，碩士論文，國立台北科技大學生產系統工程與管理學系研究所，2002。
3. 李偉傑，「半導體之工程資料分析與診斷系統」，碩士論文，國立清華大學工業工程與工程管理學系研究所，1996。
4. 李培瑞，「半導體製程資料挖礦架構、決策樹分類法則及其實證研究」，碩士論文，國立清華大學工業工程與工程管理學系研究所，2000。
5. 林寅智，「以工程資料為基礎之半導體故障分析系統」，碩士論文，國立清華大學工業工程與工程管理學系研究所，1998。
6. 孫宗瀛、楊英魁，Fuzzy 控制理論、實作與應用，全華科技圖書股份有限公司，2001。
7. 張柏年，「以倒傳遞網路為基礎之自動化晶圓缺陷檢測系統」，碩士論文，國立清華大學工業工程與工程管理學系研究所，2003。
8. 張永明，「資料挖掘在證券業顧客關係管理上之應用」，碩士論文，逢甲大學工業工程與系統管理學系研究所，2005。
9. 陳煥卿，「模糊控制應用於冷卻系統節能之研究與設計」，碩士論文，大葉大學電機工程學系研究所，2004。
10. 黃政平，「台灣半導體製程技術現況與趨勢之研究--以技術地圖探討」，碩士論文，國立台北大學企業管理學系研究所，2003。
11. 曾介亭，「多代理人系統在建構 APC 作業平台之研究」，碩士論文，國立成功大學工程科學系專班，2006。
12. 廖添文，「GA-PID模糊控制器應用於灰訊號源之追蹤與設計」，碩士論文，大葉大學電機工程學系研究所，2003。
13. 戴鴻恩，「利用半導體製程即時參數值建立缺陷特徵化監控模型」，碩士論文，國立台灣科技大學管理研究所，2005。
14. 劉麗蘭，「以決策樹分析台灣上市櫃紡織業公司的財務危機」，碩士論文，逢甲大學經營管理碩士在職專班，2006。
15. Berry, M. and Linoff, G.,”Mastering Data Mining:The Art & Science of Customer Relationship Management”,John Wiley & Sons,New York,2000.
16. Cabena,P., Hadjinian P.,Stadler R.,Verhess J.,and Zanasi A,”Discovering Data Minging From Concept to Implementation”, Prentice Hall PTR,Upper Saddle River,New Jersey,1997.
17. Chao, C. J. and Cheng, F. P.,”Fuzzy Pattern Recognition Model for Diagnosing Cracks in RC Structures,”Journal of Computing in Civil Engineering, Vol. 12, No.2,111-119,1998.
18. Hong Xiao,”Introduction to Semiconductor Manufacturing Technology”, Prentice Hall College Div,2000.
19. Liang,L.,Basallo, E.,and Looney,C.,Proc.ISCA 14th Int.Conf.,LAS Vegas,279-284.
20. Linkens, D. A. and Afzalian, A.,”A New Fuzzy Logic Power System Stabiliser(PSS),”Processdings of the 4th European Congress on Intelligent Techniques and Soft Computing, Aachen,Germany,September, 1999-2003,1996.
21. Mirza, A.I.,O’Donoghue, G Drake,A.W. and Graves, S.C.,”Spatial Yield Modeling for Semiconductor Wafers,”IEEE/SEMI Advanced Semiconductor Manufacturing Conference,pp.276-281.1995.
22. M.Madea and S.Murakami,”A self-Turing Fuzzy Controller, ”Fuzzy Sets Syst.,vol.51,pp.29-40,1992.
23. Nag,P.K,Maly,W and Jocobs,H.J.,”Simulation of Yield/Cost Learning Curves with Y4,”IEEE Transactions on Semiconductor Manufacturing,Vol.10,No.2,pp.256-266,1997.
24. Park, H., Rhee, S., and Kim, D.,”A fuzzy pattern recognition based system for monitoring laser weld quality,” Measurement Science and Technology,Vol. 12.1318-1324,2001
25. W.J.Wang,S.F.Lee,and T.C.Chian,”Fuzzy control for the intersection’s traffic light near the exit ramp of a freeway”,Automatic Control Conference,2001,Da-Shing,Taiwan,ROC.