臺灣博碩士論文加值系統

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的生產環境等因素，構成了居高不下的生產成本，各晶圓製造廠莫不汲於藉由各種製程控制與分析手法，以達成提升良率及降低成本之最終目的。在晶圓廠內，晶圓圖缺陷分析乃是最直接及有效反應異常製程之分析，所以如何提供一具有正確判斷率與快速反應的晶圓缺陷偵測系統，對於良率提升、故障排除和節省成本皆有莫大的幫助。
本研究提出一以倒傳遞網路基礎之半導體晶圓缺陷偵測系統，其主要目的乃藉由網路訓練過程，將針測所得到之晶圓缺陷圖或Bin圖，對欲觀察之缺陷特徵進行比對，而求得相關程度最大之缺陷特徵。研究中分析了不同的資料轉換對判斷正確率所造成的影響，以及如何在不同的參數組合中取得較佳的模式輸出；此外，本系統亦對於可辨識與不可辨識的各種狀況做出結論之推導。
依據現場製造工程師實際數據之驗證，可證明本系統對於晶圓圖缺陷判斷能力可符合半導體製造業的實際需求。藉由本系統可輔助工程師快速而正確的尋找出發生問題製程，進而對製程進行修正並避免類似問題之產生，除了增加製程之穩定性外，更進一步達成良率提升之目標。

For semiconductor industry, the complicated chips manufacturing process, expensive raw materials and demanding production environment make the cost relatively high. Every fabrication company eagerly searches through different manufacturing control and analysis methods to reach the goals of production cost reduction and yield improvement. In a fabrication line, the most direct and efficient way to identify an abnormal process during manufacture is by analyzing the defect maps of semiconductor wafers. Hence it is really crucial to construct a defect inspection system for semiconductor chips, which can provide better judgment and response to the detection of faults. The outcome would be an improved yield rate, the timely identification and elimination of malfunctions and eventual cost reduction.
Our current research proposed a defect detection system for semiconductor wafers based on Back-Propagation Network .The major purpose of the current study is to evaluate the characteristics of defects on observed defect maps or bin maps and, thus, obtain the most related defect characteristics through the network training process. Our research will show the effect of different data conversion on the defect detection rate and provide a better output model among the various combinations of parameters. Moreover, our detection system can differentiate between the distinguishable and indistinguishable situations.
Based on the verification of real-time manufacturing data provided by online engineers, it is proven that our system can correctly diagnose and analyze the defects such that it fulfills the requirements of semiconductor industry. This system could help engineers find out the problems on the fabrication line in a more timely and efficient manner so that engineers can modify the process to prevent similar problems from recurring, which would consequently stabilize the production process and even improve the yield rate.

目 錄
摘要…………………….…………………………...…………………….i
Abstract………………....………...……………………………………..ii
致謝辭…………………………………………………………………...iv
目 錄…………..…………...………………………………………….....v
圖目錄….………………………………………………………………viii
表目錄….………………………………………………………………...x
第一章 序論……………………….……………………………………………….1
1.1 研究背景………………………………………………………………………….1
1.2 研究動機………………………………………………………………………….2
1.3 研究範圍與方法………………………………………………..………………...5
1.4 論文架構………………………………………………………………………….6
第二章 文獻回顧………………………………………………………..7
2.1 半導體晶圓製程簡介…………………………………………………………….8
2.1.1 晶圓製造…………………………………………………………………..9
2.1.2 晶圓針測製程……………………………………………………………13
2.1.3 半導體製造後段製程……………………………………………………14
2.1.3.1構裝…………….………………………………………………….14
2.1.3.2 最終測試………………………………………………………….16
2.2 半導體產品良率控制之探討…………………………………………………...16
2.2.1 良率定義…………………………………………………………………16
2.2.2 造成良率損失的因素……………………………………………………17
2.2.3良率模型………………………………………………………………….20
2.3半導體產品良率提昇之探討……………………………………………………22
2.3.1 故障分析…………………………………………………………………22
2.3.2 缺陷定義…………………………………………………………………22
2.3.3 缺陷圖分析………………………………………………………………25
2.3.4 加強缺陷比率……………………………………………………………26
2.3.5 決策樹分析（Decision Tree Analysis）…………………………………28
2.3.6 類神經網路（Neural Networks）……………………………………….30
2.3.7自我組織映射網路（Self-Organizing Feature Map ; SOFM）……….33
2.3.8 ART神經網路……………………………………………………………35
第三章 半導體製程資料特徵萃取與偵測系統………………………38
3.1. 問題定義與架構（Problem Definition and Structure）……………………..38
3.2 資料準備（Data Preparation）………………………………………………...39
3.2.1 建構晶圓圖分類………..………………………………………………..41
3.2.2 晶圓圖資料轉換…………………………………………………………43
3.2.3 模擬晶圓圖輸入資料……………………………………………………45
3.3 建立模式（Modeling）…………………………………………………………47
3.3.1 類神經網路運用…………………………………………………………50
3.3.1.1 類神經網路組成………………………………………………….51
3.3.1.2 類神經網路運作程序…………………………………………….53
3.3.1.3 類神經網路之特性……………………………………………….54
3.3.1.4 轉移函數………………………………………………………….55
3.3.2 倒傳遞網路………………………………………………………………56
3.3.2.1 監督式學習……………………………………………………….57
3.3.2.2 所建構之網路結構……………………………………………….59
3.3.2.3 決定神經元個數………………………………………………….60
3.3.2.4 調整學習速度…………………………………………………….62
3.3 特徵辨識步驟……………………………………………………………...63
3.4 輸出模式（Output Data）……………………………………………………..64
第四章 系統實作與導入………………………………………………66
4.1系統環境……..……………………………………..……………………………66
4.2系統設定…………………………………………………………………………67
4.2.1輸入晶圓圖資料………………………………………………………….69
4.2.2建構訓練網路…………………………………………………………….70
4.3輸出結果…………………………………………………………………………74
4.3.1驗證數據集……………………………………………………………….75
4.3.2辨識結果………………………………………………………………….77
4.3.3重複性缺陷……………………………………………………………….77
4.3.3.1一維資料轉換……………………………………………………..78
4.3.3.2重複性缺陷之驗證………………………………………………..80
4.3.3.3輸出結果…………………………………………………………..80
4.3.4過度配適………………………………………………………………….81
4.3.5強化特徵………………………………………………………………….83
4.4本章結論…………………………………………………………………………84
第五章 結論與建議
5.1歸納與結論………………………………………………………………………86
5.2未來方向…………………………………………………………………………87
參考文獻………………………………………………………………..89

參考文獻
1.李偉傑，半導體之工程資料分析與診斷系統，國立清華大學碩士論文，1996。
2.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，國立清華大學碩士論文，2000。
3.林聖哲，半導體製程即時監控與診斷專家系統，國立清華大學碩士論文， 1996。
4.莊達人，VLSI製造技術，高立圖書有限公司，1997。
5.劉淑範，以缺陷分析為基礎之自動化與智慧型良率提升系統，國立清華大學碩士論文，1998。
6.林鼎浩，建構半導體製程資料挖況架構及其實證研究，國立清華大學碩士論文，2000。
7.林寅智，以工程資料為基礎之半導體故障分析系統，國立清華大學碩士論文，1998。
8.張智星，MATLAB程式設計與應用，清蔚出版社，1998。
9.蘇木春、張孝春，機器學習：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，1998。
10.羅華強，類神經網路-MATLAB的應用，清蔚出版社，2001。
11.Apte,C,Weiss and S,”Data Mining with Decision Tree and Decision Rule, ”Future Generation Computer System ,Vol. 13,1997, pp.197-210.
12.Berry, M.and Linoff, G.,” Mastering Data Mining: The Art & Science of Customer Relationship Management”, John Wiley &Sons, New York, 2000.
13.Cabena, P., Hadjinian P.,Stadler R.,Verhess J., and Zanasi A,” Discovering Data Mining From Concept to Implementatation”, Prentice Hall PTR, Upper Saddle River, New Jersey,1997.
14.Cunningham, J.A.,” The use and evaluation of yield models in integrated circuit manufacturing,” IEEE Transactions on Semiconductor Manufacturing, Vol. 3 No. 2 , May 1990 , pp. 60-71.
15.Cresswell, M.W., Khera, D.and Linholm, L.W.; Schuster, C.E.,” A directed-graph classifier of semiconductor wafer-test patterns,” IEEE Transactions on Semiconductor Manufacturing, Vol. 5,No. 3, Aug 1992, pp. 255-263.
16.Deboeck, G. and Kohonen, T. Eds ,“Visual Exploration in Finance with Self-Organizing Maps.” Springer-Verlag, London,1998.
17.Fayyad, U., Piatetsky-Shapiro, G., and Smyth, P., “The KDD Process for Extracting Useful Knowledge from Volumes of Data ”, Communication of ACM, Vol. 39, No.11,1996, pp.27-34
18.Friedman, D.J., Hansen, M.H. and Nair, V.N.; James, D.A.,” Model-free estimation of defect clustering in integrated circuit fabrication” IEEE Transactions on Semiconductor Manufacturing, Vol. 10 No. 3, Aug 1997 , pp.344-359.
19.Fei-Long Chen and Shu-Fan Liu,” A neural-network approach to recognize defect spatial pattern in semiconductor fabrication,”IEEE Transactions on Semiconductor Manufacturing, Vol. 13 No. 3 , Aug 2000 , pp.366 —373.
20.Hamsen, M.H., Nair, V.N., Friedman D.J.,” Monitoring Wafer Map Data From Integrated Circuit Fabrication Processes for Spatially Clustered Defects,” Technometrics, Vol. 39, No. 3, 1998, pp.241-253.
21.Harris, R.E., ”Defect density assessment in an integrated circuit fabrication line,” IEEE International Workshop on Defect and Fault Tolerance in VLSI Systems, Nov 1992, pp.2-11.
22.Hess, C. and Weiland, L.H.,” Extraction of wafer-level defect density distributions to improve yield prediction,” IEEE Transactions on Semiconductor Manufacturing, Vol. 12 , No. 2 , May 1999 , pp. 175-183.
23.Irani, K. B., Cheng, J., Fayyad, U. M., and Qian, Z., “Applying Machine Learning to Semiconductor Manufacturing”,IEEE Expert, Vol. 8, No.1,1993, pp. 41 —47.
24.Kaempf, U.,” The binomial test: a simple tool to identify process problems,” IEEE Transactions on Semiconductor Manufacturing, Vol. 8 , No. 2 , May 1995, pp. 160-166.
25.Lazaroff, D., Bakker, D. and Granath, D.R.,” Evaluating different sampling techniques for process control using automated patterned wafer inspection systems,” IEEE/SEMI Advanced Semiconductor Manufacturing Conference and Workshop, ASMC 91 Proceedings, 21-23 Oct 1991, pp. 92-97.
26.Mirza, A. I., O’ Donoghue, G., Darke, A. W. and Graves, S. C., “Spatial Yield Modeling for Semiconductor Wafers,” IEEE/SEMI Advanced Semiconductor Manufacturing, Vol. 10, No 2, 1995, pp. 276-281.
27.Nag, P. K., Maly, W, Jocobs. and H. J.,” Simulation of Yield/Cost Learning Curves with Y4,”IEEE Transactions on Semiconductor Manufacturing, Vol. 10 , No. 2,1997 , pp.256-266.
28.Safavian, S. R., and Landgrebe, D., “A Survey of Decision Tree Classifier Methodology”, IEEE Transactions on Systems, Man, and Cybernetics, Vol.21, No.3,1991, pp. 660-674.
29.Stapper, C. H. and Ronser, R. J.,” Integrated Circuit Yield Management and Yield Analysis: Development and Implementation,” IEEE Transactions on Semiconductor Manufacturing, Vol. 8 , No2 , 1995 , pp 95-105.
30.Taam,W. and Hamada,M.,” Detecting Spatial Effects from Factorial Experiments :An Application from Integrated-circuit Manufacturing,” Technometrics,Vol.35, No.4
31.Safavian, S. R., and Landgrebe, D. (1991), “A Survey of Decision Tree Classifier Methodology”, IEEE Transactions on Systems, Man, and Cybernetics, Vol.21, No.3, pp. 660-674.
Westphal, C., and Blaxton, T. (1998), Data Mining Solutions: methods and tools for solving real-world problems, Wiley, New York.