淡江大學覺生紀念圖書館 (TKU Library)
進階搜尋


下載電子全文限經由淡江IP使用) 
系統識別號 U0002-0207200716545500
中文論文名稱 決策樹應用於薄膜玻璃濺鍍製程良率分析之研究
英文論文名稱 An Analysis of the Applying Decision Trees to the Process Yield of Thin Layer Glass Sputtering
校院名稱 淡江大學
系所名稱(中) 資訊工程學系碩士在職專班
系所名稱(英) Department of Computer Science and Information Engineering
學年度 95
學期 2
出版年 96
研究生中文姓名 王茂年
研究生英文姓名 Maw-Nian Wang
學號 794190016
學位類別 碩士
語文別 中文
口試日期 2007-06-14
論文頁數 60頁
口試委員 指導教授-林丕靜
委員-王鄭慈
委員-蔣定安
中文關鍵字 決策樹  資料採礦  迴歸樹  良率 
英文關鍵字 Decision Tree  Data Mining  Regression Tree  Yield 
學科別分類 學科別應用科學資訊工程
中文摘要 近年來,光電產業已成為我國高科技產業的重點工業。為提升獲利能力,從建廠之初,廠商無不希望快速提升製程技術、大幅縮短試產時程及早進入量產;除此之外,工廠亦須在「大量少樣」或「少量多樣」的生產模式中抉擇,以建立最佳生產模式。為建立成功的獲利模型,部分工廠採取「少量多樣」的生產策略,俾將有限資源集中投入工廠量產。
處於「少量多樣」的生產環境下,很難在短時間找出良率決策規則,並形成良率決策規則資料庫。本研究在提供廠商一個簡明之良率改善架構的製程模型,以有效提升良率並控制良率的變異。傳統應用決策樹以改善製程良率之研究,大多利用批次(Lot)資料輸入到迴歸樹(Regression Trees)進行分析,但此方法較難在資料有限且良率變異較大的情況下,較難找出製程參數的最佳區間。本研究乃改採生產管理系統(Manufacturing Execution System,MES)與統計製程管制(Statistical Process Control,SPC)中所收集之資料,將原始批號資料轉換成實際進入每一製程的玻璃片資料數量,再分別將每一個製程參數資料各自利用決策樹進行獨立分析,並決定良率的製程參數範圍,以作為製程工程師解決問題的參考依據,進而提升工廠製程良率。
本研究係以台南科學園區內某光電廠之薄膜玻璃濺鍍製程案例為實證,檢驗本研究架構之效度,從研究結果顯示:利用本研究所採行之分析方法,除可分別定義較佳良率之製程參數其正向與反向條件外,並可有效協助製程工程師提高製程良率。實作顯示:該光電廠之製程良率已大幅改善,良率較以往增加約20~30%。
英文摘要 For the past few years, Photonics has become the key technology among many Hi-Tec industries in our country. In order to increase profits, Photonics manufacturers all hope to fast improve their manufacture technique, which can save the trial manufacturing process on a great scale and reach the mass production stage earlier. They also need to determine production strategies such as mass quantity but few varieties or great varieties but less quantity to see which the best production mode is. A few manufacturers would choose great varieties but less quantity production strategy to set up a successful profit model, pouring all the limited resources into mass production line.
The purpose of the research is to provide manufacturers a simplified production model of yield improvement under the great varieties but less quantity production circumstances and to effectively improve and control yield variation. Many conventional study of applying classification trees to improve process yield would conduct the analysis by inputting batch data to Regression Trees. However, if the data is scarce and yield variation is too big, this method can not effectively distinguish which batch and its quantity. It is also hard to find out which the best range is for process parameter. Therefore, this research chooses to adopt the data collected by MES(Manufacturing Execution System) and SPC(Statistical Process Control) and transform the original batch data into actual data.
This research is based on a Photonics manufacturer located in Southern Taiwan Science Park. The research takes its thin layer glass sputtering for example. Moreover, it analyzed every process parameter by decision tree and decided the range of acceptable process parameters of yield in order to provide insights for yield enhancement and lights of problem-solving for process engineers. This case also examined the validity of this manufacturing process model. This research shows that the process yield of the Photonics manufacturer has improved a lot by 20 ~ 30 % compared with its past record.
論文目次 目 錄
第一章、緒論…………………………………….……………………1
1.1研究背景…………………………………………………………………1
1.2研究動機與目的…………………………………………………………3
1.3研究成果…………………………………………………………………4
1.4論文架構…………………………………………………………………4
第二章文獻探討……………………………………………………….6
2.1 TFT-LCD原理及應用 …………………………………………………6
2.2 TFT-LCD製程 …………………………………………………………8
2.3濺鍍製程技術 …………………………………………………………11
2.4研究方法 ………………………………………………………………14
2-4-1資料採礦的意義與程序…………………………………………14
2-4-2決策樹……………………………………………………………15
2-4-3 CART演算法..…………………………………………………16
2-4-4應用決策樹應用於提升產品良率之研究………………………18
第三章 良率缺陷問題陳述 …………………………………………21
3.1 製程與資料的繁複度 …………………………………………………21
3.2 資料樣本數有限 ………………………………………………………23
第四章 研究架構 ……………………………………………………26
4.1 研究步驟 ………………………………………………………………27
4.2 設定良率與缺陷改善問題 ……………………………………………27
4.3 定義探勘工作 …………………………………………………………29
4.4 資料預處理 ……………………………………………………………32
4.5 資料採礦與評估探勘結果 ……………………………………………38
第五章 實證結果與討論 ……………………………………………40
5.1 製程良率改善之正向決策規則 ………………………………………40
5.2 製程良率改善之反向決策規則 ………………………………………44
第六章 結論與未來研究方向 ………………………………………47
參考文獻 ……………………………………………………………..49
英文論文 ……………………………………………………………..53

表 目 錄
表1.1  光電產品界定範圍……………………………………….1
表1.2  台灣光電產業各領域之成長率與整體佔有率………….2
表4.1 玻璃鍍膜缺陷原因分析....………………………………29
表4.2  玻璃濺鍍參數欄位………………………………………31
表4.3  製程生產管理資訊(一)………………………………….34
表4.4  製程生產管理資訊(二)………………………………….34
表4.5  製程測量值………………………………………………35
表4.6  轉換成玻璃號碼後的資料(一)………………………….36
表4.7  轉換成玻璃號碼後的資料(二)……….…………………37








圖 目 錄
圖2.1  TFT-LCD結構圖………………………………………….7
圖2.2  電子顯微鏡下的液晶分子….…………………………….8
圖2.3  TFT-LCD製程表…………………….……………………9
圖2.4  磁控濺鍍機……………………………………………….11
圖2.5  濺鍍機台加工模組示意圖……………………………….12
圖2.6  濺鍍台車玻璃位置示意圖……………………………….12
圖2.7  M6濺鍍模組示意圖..……………………………………13
圖3.1 Parag以CART迴歸樹表示測試資料…………………..24
圖4.1  研究架構圖……………………………………………….26
圖5.1  分類樹良率分析圖之一………………………………….41
圖5.2  分類樹良率分析圖之二………………………………….43


參考文獻 ﹝01﹞Breimann Leo,Jerome H.Friedman, Richard A.Olshen,and Charles J.Stone, “Classification and Regression Tree”, Wadsworth International Group, Belmont,CA,1984.
﹝02﹞Dan Braha, Armin Shmilovici , “On the Use of Decision Tree Induction for Discovery of Interactions in a Photolithographic Process,” IEEE
transactions on semiconductor manufacturing , Vol.16, No.44,2003, pp:644-652.
﹝03﹞D.W.Hosmer and S.Lemeshow, “Applied logistic regression”, John-Wiley & Sons (1989).
﹝04﹞E. A. Sack, “Global yield engineering for IC production,” Solid State Technol., vol. Market Watch, pp. 81–85, Dec. 1998.
﹝05﹞F. Lee, “Advanced yield enhancement: Integrated yield analysis,” in Proc. IEEE/SEMI Advanced Semiconductor Manufacturing Con. And Workshop, Cambridge, MA, Sept. 1997, pp. 67–75.
﹝06﹞F. Mieno, T. Sato, Y. Shibuya, K. Odagiri, H. Tsuda, and R. Take, “Yield improvement using data mining system,” Semiconductor Manufacturing Conference Proceedings, 1999 IEEE International Symposium on, 1999, pp: 391-394.
﹝07﹞François Bergeret , Caroline Le Gall,“Yield Improvement Using Statistical Analysis of Process Dates”. IEEE transactions on Semiconductor Manufacturing, VOL. 16, NO. 3, AUGUST 2003.
﹝08﹞G. E. P. Box, W. G. Hunter, and J. S. Hunter, “Statistics for Experimenters”.New York: Wiley, 1978.
﹝09﹞J.Ross Qrinlan,“Induction of Decision Tree”, Machine Learning Journal, Vol. 1, pp.81-106,1986
﹝10﹞Kass, G.V., An Exploratory Technique for Investigating Large Quantities of Categorical Data. Applied Statistics , 1980., pp.119-127.
﹝11﹞K. W. Tobin, T. P. Karnowski, S. S. Gleason, D. Jensen, and F. Lakhani, “Integrated Circuit yield management,” in Proc. 196th Meeting Electrochemical Society, INC., Honolulu, HI, Oct. 1999, pp. 17–22.
﹝12﹞Michael J.A.Berry, Gordon S.Linoff, “Mastering Data Mining, The Art & Science of Customer Relationship Management, ” John Wiley & Sons, Inc, 2000
﹝13﹞Parag C. Pendharkar, Girish H. Subramanian, and James A. Rodger, “A Probabilistic Model for Predicting Software Development Effort”, IEEE Transactions on software engineering, VOL. 31, NO. 7, JULY 2005
﹝14﹞P. V. Zant, “Microchip Fabrication: A Practical Guide to Semiconductor Processing”, 3rd ed. New York: McGraw-Hill, 1997.
﹝15﹞Quinlan J.R(1993)C4.5, “ Programs for machine learning”. Morgan Kaufmann, San Mateo, CA.
﹝16﹞Quinlan, J.R. (2003). C5.0 Online Tutorial,http://www.rulequest.com.
﹝17﹞R.Agrawa1, T.Imilienski, aid A.SWAM1: Proc. of the ACM SIGMOD Int'l Conf. on Management of Data, pp 207-216, May 1993
﹝18﹞Richard Kittler and Weidong Wang, “Data Mining for yield Improvements”, in International Conference on Modeling and Analysis of Semiconductor Manufacturing, 2000.
﹝19﹞S. P. Cunningham, C. J. Spanos, and K. Voros, “Seminconductor yield improvement: Results and best practices,” IEEE Trans. Seminconduct Manufacting., vol. 8, pp. 103–109, May 1995.
﹝20﹞T. P. Ryan, “Statistical Methods for Quality Improvement”. New York:Wiley, 1989.
﹝21﹞Uzsoy, R., C. Y. Lee, and L. A. Martin-Vega, “A review of production
planning and scheduling models in semiconductor industry. Part I: System characteristics, performance evaluation and production planning,” IIE Transactions, 24(4), 47-60 (1992).
﹝22﹞Uzsoy, R., C. Y. Lee, and L. A. Martin-Vega, “A review of production planning and scheduling models in semiconductor industry. Part II: Shop floor control,” IIE Transactions, 26(5), 44-54 (1994).
﹝23﹞Venkat Raghavan, “Application of Decision Trees for Integrated Circuit Yield Improvement”,2002 IEEE/SEMI Advanced Semiconductor Manufacturing Conference.
﹝24﹞Yu-Chuan Su, Min-Hsiung Hung, Fan-Tien Cheng and Yeh-Tung Chen, “A Processing Quality Prognostics Scheme for Plasma Sputtering in TFT-LCD Manufacturing”, IEEE Transactions on semiconductor manufacturing, VOL. 19, NO. 2, MAY 2006
﹝25﹞光電科技協進會(Photonics Industry & Technology Development Association,PIDA,2000年)
﹝26﹞光電科技協進會(PIDA,2006/12)
﹝27﹞李勇、何洋波、馬麗、強祖基,『用分類回歸樹方法研究亮温異常变化』,2003年4月。
﹝28﹞陳年興、廖聖傑,『從學習歷成檔案建構支援決策樹以支援網路教學』,民國92年。
﹝29﹞黃美玲、許佑新、黃智仁、陳正誼、陳俊誠,中華民國品質學會第42屆年會暨第12屆全國品質管理研討會『應用決策樹於青光眼患者之鑑別』論文。
﹝30﹞經濟部統計資料(陳瑞隆,2006/8/5)
﹝31﹞謝紀綱、裘正定、韓彥俊、莫 莉,『上市公司財務困境預測模型比較研究』,2005年9月。
論文使用權限
  • 同意紙本無償授權給館內讀者為學術之目的重製使用,於2007-07-18公開。
  • 同意授權瀏覽/列印電子全文服務,於2009-07-18起公開。


  • 若您有任何疑問,請與我們聯絡!
    圖書館: 請來電 (02)2621-5656 轉 2281 或 來信