隨著半導體產業製程技術不斷進步，製程研發技術門檻又愈來愈高。進入奈米製程世代之後，晶圓製造流程變得更加複雜與冗長，每顆電晶體製造成本不斷的增加。如此高額的研發成本、產能資本支出與製造成本，形成晶圓製造廠多重負擔，為了獲得最大的投資報酬率與維持獲利水準，必須消弭生產過程中產生異常，以避免良率損失甚至產品報廢。但生產數據每片以十萬筆的速度成長，傳統統計迴歸分析、相關性分析，已無法有效快速地找出導致製程異常的原因，以及可能潛藏的問題。本研究以晶圓製造過程所蒐集的生產與製程資料為基礎，透過結合大數據儲存與運算技術、開源分析軟體與圖形化智慧型分析工具，建構半導體大數據分析應用系統架構。並針對半導體晶圓製造良率檢測資料，進行良率異常偵測與異常因子診斷分析之模型建構，透過良率異常偵測機制，偵測良率異常狀況，並依照好壞晶圓分類自動進行良率異常因子診斷分析與可疑因子決策模型，有效快速地尋找出可能造成製程變異的因子，協助快速釐清產品良率異常的原因，提昇工程師在良率提昇的決策品質。本研究運用某半導體廠之實際資料，檢驗本研究的效度和可行性，提供工程師及領域專家作為建構良率分析系統的參考架構，協助提昇半導體製程的良率，每一顆產品良率改善案平均良率提升 3% 以上，以及一千萬元潛在獲利，加速產品量產時程，提升產品競爭力與利潤。

關鍵字：大數據；資料探勘；智慧製造；異常良率偵測；異常良率診斷；良率改善；半導體製造；

With the advance of technology, semiconductor industry process continuously improves with huge investment. The wafer manufacturing process becomes more complex and lengthy after entering the nanometer generation process. How to detect yield loss and identify possible root causes in a timely manner become critical issues. Due to data intensive nature of semiconductor process, traditional statistical regression analysis and correlation analysis are unable to quickly and easily figure out the causes of process anomalies and potential problems. Therefore, this study develops a intelligent yield detect and diagnostic analysis framework that can intelligently detect and alert the abnormal situations at early stage. This framework will be validated with practical data of a foundry. By incorporating with engineers and domain experts, this system can be a decision-support system to efficiently improve the yield. To gain the average product yield of each yield improvement project increased by more 3% and 10 million NT dollars potential profit, accelerating the production schedule of products and enhancing the competitiveness and profits of the products.

Keywords: big data; data mining; smart manufacturing; anomaly yield detection; anomaly yield diagnostic; yield improvement; semiconductor manufacturing;

第 1 章 緒論 1
1.1 研究背景 1
1.2 研究動機 2
1.3 研究目的 3
1.4 論文架構與研究內容 4
第 2 章 文獻探討 5
2.1 大數據 5
2.2 資料探勘 (Data Mining) 10
2.3 大數據於產業界的應用 14
第 3 章 研究架構與方法 18
3.1 研究架構與方法 18
3.2 半導體大數據分析應用系統架構 19
3.3 半導體晶圓製造資料整合與關聯性建立 20
3.4 半導體智慧型良率偵測與診斷分析模型 24
3.4.1 良率異常偵測 26
3.4.2 良率診斷分析 39
第 4 章 實證研究 47
4.1 半導體晶圓製造大數據分析系統平台 48
4.2 半導體晶圓製造資料整合與關聯性建立 49
4.3.1 良率異常偵測方法驗證 50
4.3.2 良率診斷分析方法驗證 56
4.3.3 整體模型驗證 62
4.4 模擬驗證 65
4.5 系統實際驗證 68
4.6 系統實作結果分析與總結 72
4.7 討論 75
第 5 章 結論 78
5.1 研究貢獻 78
5.2 未來研究方向 78
參考文獻 80

中文部分:
1. SEMI(2016), SEMI半導體智慧製造國際論壇探索工業4.0生產流程再進化http://www.semi.org/zh/node/72216 View On Jun 30, 2018。
2. 王宇灿、李一飞、袁勤俭(2014)，国际大数据研究热点及前沿演化可视化分析，工程研究-跨学科视野中的工程，2014年 03期，282 – 293。
3. 余至浩(2014)，台積電運用大資料分析 創造半導體製程技術優勢，https://www.ithome.com.tw/news/92290, View On Jun 30, 2018。
4. 李欣宜(2015)，一次搞懂大數據，數位時代。
5. 李傑(2016)，工業大數據，天下財經 310，天下雜誌。
6. 李灝汶(2016)，工業4.0成熟度的評估與診斷系統，清華大學工業工程與工程管理研究所碩士論文。
7. 汪建南、馬雲龍(2016)，工業 4.0 的國際發展趨勢與台灣因應之道，國際金融參考資料，第六十九輯，133-155。
8. 吳明儒 (2015)，視覺特徵用於大規模學習：以晶圓圖與音樂曲風分類為例，清華大學資訊工程學系博士論文。
9. 佩羅德.多明戈斯(2016)，大演算，三采文化。
10. 凃馨慈(2016)，健保資料大數據分析：應用貝氏Logistic迴歸機器學習模型研究失智症與心房顫動風險因子，中山大學資訊工程學系研究所碩士論文。
11. 城田真琴(2011)，大數據的獲利模式，經濟新潮社。
12. 翁慈宗(2009)，科學發展，2009年10月，442期，P32-39。
13. 高銘輝(2016)，互聯網金融之創新與風險，國立中央大學財務金融學系在職專班碩士論文。
14. 莊銘弘(2010)，考量半導體製程能力限制下之晶圓圖隨機性辨識法及應用，國立交通大學統計學研究所碩士論文。
15. 陳致瑀(2016)，醫療大數據平台之商業模式探討與未來展望，國立臺灣大學商學研究所碩士論文。
16. 陳暎仁(2013)，半導體先進製程控制之品質工程研究架構及實證研究，清華大學工業工程與工程管理研究所博士論文。
17. 陳瑾瑜(2015)，巨量資料應用於金融業創新服務之個案研究，台灣科技大學財務金融研究所博碩士論文。
18. 湯瑪斯.戴文波特(2015)，哈佛教你精通大數據，遠見.天下文化。
19. 黃亦筠(2015)，西門子的超級印鈔機，天下雜誌564期。
20. 黃稚銨 (2011)，利用特性要因分析法改善場擴散金氧半場效電晶體製程，國立交通大學半導體材料與製程設備學程碩士論文
21. 黃瀚萱、陳信希(2016)，醫療大數據及其應用，台灣醫學 20卷6期，589-594。
22. 張洝源和周大鈞 (2011) ，應用德爾菲法及分析網路程序法於半導體分析晶片缺點因子改善製程良率之研究，國立虎尾科技大學學報 第三十卷第二期，P17-36
23. 楊文靜 (2017)，應用大數據與分析網路程序法建構智慧永續城市評估模型之研究，國立臺北大學不動產與城鄉環境學系碩士論文。
24. 麥爾荀伯格（Mayer-Schonberger, V.)、庫基耶（Cukier, K.）（2013）。大數據（林俊宏譯）。臺北市：天下文化。
25. 謝政賢(2015)，大數據演算法下之投資策略分析，中興大學財務金融學系所碩士論文。
26. 謝劍斌等(2016)，20個視覺機器學習理論深讀，佳魁資資訊。
27. 簡禎富、許嘉裕(2014)，資料挖礦大數據分析，前程。
28. 簡禎富* 林昀萱 鄭仁傑 (2008)，建構模糊決策樹及其在有交互作用之半導體資料之資料挖礦以提昇良率之研究, 品質學報 Vol. 15, No. 3, 193-210


英文部分：

1. Bauer, H., Ranade, P. and Tandon, S.(2012), "Big Data And The Opportunities It Creates for Semiconductor Players", Mckinsey on Semiconductors Autumn 2012, 46-55
2. Baly, R. and Hajj, H. (2012), "Wafer Classification Using Support Vector Machines", IEEE Transactions on Semiconductor Manufacturing, 25(3), 373-383.
3. Berry, M. J. A and Linoff, G. (1997), "Data Mining Technology", John Wiley & Sons Inc.
4. Cabena, P., Hadjinian, R., Stadler, J. V., and Zanasi, A. (1998), "Discovering Data Mining from Concept to Implementation", N. J.: Prentice-Hall.
5. Calinski, T., and Harabasz, J.(1974), "A Dendrite Method For Cluster Analysis", Communications in Statistics, 3(1), 1–27.
6. Chang, F., Dean, J., Ghemawat, S., Hsieh, W. C., Deborah, A., Burrows, W.M., Chandra, T., Fikes, A., and Gruber, R. E. (2006), "Bigtable: A Distributed Storage System for Structured Data", Google.
7. Chen, C. F., Wang, W. C. and Cheng, J. C. (2007), “Data Mining for Yield Enhancement in Semiconductor Manufacturing And An Empirical Study”, Expert Systems With Applications, vol. 3, 192-198.
8. Chien, C. F. and Chuang, S.C.(2014), "A Framework for Root Cause Detection of Sub-Batch Processing System for Semiconductor Manufacturing Big Data Analytics", IEEE Transactions on Semiconductor Manufacturing, 27(4), 485-488.
9. Chien, C. F., Chen, Y. J. and Wu.(2016), "Big Data Analytics For Modeling WAT Parameter Variation Induced by Process Tool in Semiconductor Manufacturing and Empirical Study", J. Z. Winter Simulation Conference (WSC), 2512-2522.
10. Chien, C. F., Hsu, C. Y., Morrison, J. R., and Dou, R. (2016), “Semiconductor Manufacturing Intelligence And Automation”, Computers and Industrial Engineering, 99(C), 315-317.
11. Chien, C. F., Liu, C.W., and Chuang, S.C. (2017), “Analysis Semiconductor Manufacturing Big Data for Root Cause Detection of Excursion for Yield Enhancement”, International Journal of Production Research, 55(17), 5095-5107.
12. Cortes, C. & Vapnik, V. (1995), "Support-Vector Network”, Machine Learning, September 1995, Volume 20, Issue 3, pp 273–297
13. Dean, J. and Ghemawat, S. (2004), "MapReduce: Simplified Data Processing on Large Clusters", Google.
14. DeCandia, Giuseppe, DenizHastorun, Jampani, M., Kakulapati, G., AvinashLakshman, Pilchin, A., SwaminathanSivasubramanian, Vosshall, P and Vogels, W.(2007), "Dynamo: Amazon’s Highly Available Key-value Store", Amazon.
15. Douglas, L. (2001), "3D Data Management: Controlling Data Volume, Velocity and Variety". Gartner.
16. Douglas, L.(2012), "The Importance of 'Big Data': A Definition. ", Gartner.
17. Cambria, E., Rajagopal, ., Olsher, D. and Das, D..(2013), "Big social data analysis. ",Taylor & Francis.
18. Fayyad, U., et al. (1995), “From Knowledge Discovery to Data Mining: An Overview,” Advances in Knowledge Discovery and Data Mining, AAAI/MIT Press
19. Ghemawat, S., Gobioff, H. and Leung, S.T. (2003), Google File System, Google.
20. Gonzalez, R. C. and R. E. Woods. (2008), "Digital Image Processing",. Prentice-Hall, 3rd edition.
21. Grupe, F. H. and Owrang M. M.(1995), "Database Mining Discovering New Knowledge and Competitive Advantage", Information Systems Management Vol. 12, Iss. 4
22. Hsu, C. Y. (2015), "Clustering Ensemble for Identifying Defective Wafer Bin Map in Semiconductor Manufacturing", Hindawi Publishing Corporation Mathematical Problems in Engineering, 2015(707358), pp 1~11
23. Hsu, S. C. and Chien, C. F. (2007), "Hybrid Data Mining Approach for Pattern Extraction from Wafer Bin Map to Improve Yield in Semiconductor Manufacturing", International Journal of Production Economics, 107(1), 88-103.
24. Jue, A. (2014), Facebook’s Instagram: Making the Switch to Cassandra from Redis, a 75%『Insta』Savings, https://www.datastax.com/dev/blog/facebooks-instagram-making-the-switch-to-cassandra-from-redis-a-75-insta-savings, View on Jun 30, 2018
25. Khakifirooz, M., Chien, C. F., and Chen, Y. J. (Forthcoming),”Bayesian Inference for Mining Semiconductor Manufacturing Big Data for Yield Enhancement and Smart Production to Empower Industry 4.0,” Applied Soft Computing.
26. Killick, R. and Eckley, I. A. (2014), "Change Point: An R Package for Change Point Analysis", Journal of Statistical Software, 58(3), 1-19.
27. Kohli, S. (2015), Apple Inc.: Cassandra at Apple for Massive Scale, https://www.youtube.com/watch?v=Bc4ql9TDzyg ,2015-03-03.
28. Nakata, K., Orihara, R. Mizuoka, Y. and Takagi, K.(2017), "A Comprehensive Big-Data-Based Monitoring System for Yield Enhancement in Semiconductor Manufacturing", IEEE Transactions on Semiconductor Manufacturing, 30(4), 339-344.
29. Lakshman, A. and Malik, P.(2008), "Cassandra - A Decentralized Structured Storage System", Facebook.
30. Lee K. B., Cheon S., and Kim C. O. (2017), “A Convolutional Neural Network for Fault Classification and Diagnosis in Semiconductor Manufacturing Processes”, IEEE Transactions on Semiconductor Manufacturing, 30(2), 135-142
31. Liu, S. F., Chen, F. L. and LU, W. B. (2002), "Wafer Bin Map Recognition Using a Neural Network Approach", International Journal of Production Research, 40(10), 2207-2223.
32. Meyer, D. (2017), "Support Vector Machines", R-Project.org.
33. Moyne J. and Iskandar J. (2017), "Big Data Analytics for Smart Manufacturing: Case Studies in Semiconductor Manufacturing", Processes, pp 1-20
34. Nakata K., Orihara, R., Mizuoka, Y. and Takagi K. (2017), “A Comprehensive Big-Data-Based Monitoring System for Yield enhancement in Semiconductor Manufacturing”, IEEE Transaction On Semiconductor Manufacturing, 30(4), 339-344
35. Normandeau, K.(2013), “Beyond Volume, Variety and Velocity is The Issue of Big Data Veracity”, https://insidebigdata.com/2013/09/12/beyond-volume-variety-velocity-issue-big-data-veracity/, view on Jun 30, 2018
36. Page, L., Brin, S., Motwani, R. and Winograd, T. (1999), “The PageRank Citation Ranking: Bringing Order to The Web”. Technical Report. Stanford InfoLab.
37. Pimentel, M. A. F., Clifton, D. A., Clifton, L., and Tarassenko, L. (1999), "A Review of Novelty Detection", Signal Processing 99(June), 215–249.
38. Pyle, D. (1999), "Data Preparation for Data Mining", Morgan Kaufrnann, San Francisco, CA.
39. Qu, F. (2014), "eBay: Apache Cassandra Best Practices at Ebay", https://www.youtube.com/watch?v=gn4MDRmrfKo, 2014-10-10
40. Rekha, J. H., and Parvathi, R. (2015), "Big data, Cloud and Computing Challenges Survey on Software Project Risks and Big Data Analytics", Procedia Computer Science, 50, 295-300.
41. Schroeck, M., Shockley, R., Smart, J., Dolores, R. M., and Tufano, P. (2013), "Analysis :The Application of The Data in The Real World White Paper (W) – CNZH", IBM
42. Sharma, R. and Kashyap Y. (2015), "A study of NoSQL Databases and Working Overviews", International Journal of Recent Trends in Engineering and Research Volume 02, Issue 02.
43. Shvachko, K., Kuang, H., Radia, S. and Chansler, R.(2010), "The Hadoop Distributed File System", Yahoo
44. Sumikawa, N., Wang, L.C. and Abadir, M.S. (2013), "A Pattern Mining Framework for Inter-Wafer Abnormality Analysis", Test Conference (ITC), IEEE International, pp 1~10
45. Tiwari, S., Akkalakshmi, M., Bhagavatula, K., (2017), "Analysis of NoSQL Databases:Mongodb,HBase,Neo4J", International Journal of Engineering Trends and Technology (IJETT) – Special Issue – April 2017, 234 -239
46. Thuraisingham, B. (2000), “A Primer for Understanding and Applying Data Mining,” IT Professional, 2(1), 28-31.
47. Vapnik, V. and Sterin, A. (1977), "On Structural Risk Minimization or Overall Risk in A Problem of Pattern Recognition". Automation and Remote Control
48. Villanova University (2014), What is Big Data? Retrieved from http://www.villanovau.com/university-online-programs/what-is-big-data/, view on Jun 30, 2018
49. Vora, M. N.(2011), "Hadoop-HBase for Large-Scale Data", International Conference on Computer Science and Network Technology, December 24, 2011, p601-605.
50. Wang, J. L., Zhang J., and Wang X., (2018), “Bilateral LSTM: A Two-Dimensional Long Short-Term Memory Model With Multiply Memory Units for Short-Term Cycle Time Forecasting in Re-entrant Manufacturing Systems”, IEEE Transactions on Industrial Informatics, 14(2), 748-758.
51. Wikipdedia(2013), Data Mining, https://en.wikipedia.org/wiki/Data_mining, view on Jun 30, 2018
52. Wu, M. J., Jang, J. S. R. and Chen, J. L. (2015), "Wafer Map Failure Pattern Recognition and Similarity Ranking for Large-Scale Data Sets", IEEE Transactions on Semiconductor Manufacturing, 28(1), 1-12.
53. Yi, X., Liu, F., Liu, J., and Jin, H. (2014), "Building a Network Highway For Big Data: Architecture and Challenges", IEEE Network, 28(4), 5-13.
54. Yoo, Y., Park, S. H., An, D., Kim, S. S. and Baek, J. G. (2014), "A Spatial Point Pattern Analysis to Recognize Fail Bit Patterns in Semiconductor Manufacturing", International Scholarly and Scientific Research & Innovation 8(2), 465-469.
55. Yuan, D., Jia1, X., and Lee, J. (2016), "Enhanced Virtual Metrology on Chemical Mechanical Planarization Process Using an Integrated Model and Data-Driven Approach", Annual Conference of the prognostics and health management society, pp 1~8
56. Zaharia, M., Chowdhury, M., Franklin, M. J., and Shenker, S. (2010), "Spark: Cluster Computing with Working Sets", Ion Stoica University of California, Berkeley.