臺灣博碩士論文加值系統

設備是公司重要的資產，高附加價值的設備更需要妥善維護及管理以滿足公司之生產營運需求。設備狀況之良窳深切影響生產系統之產能及產品之品質及良率，所以良好的設備管理是企業在競爭日益激烈的市場環境下生存之重要關鍵。近年來為了改善設備的安全性，增加生產產品的良率，應用網路科技於設備之診斷、維修與監控等技術逐漸受到學術界與實務界之重視。這些診斷與維修行為需要一決策系統來提供失效原因判斷與分類。儲存在資料庫或資料倉儲內的設備狀態歷史紀錄資料量相當龐大，這些大量的設備狀態資料在資料探勘方面有一個相當困難的問題，即是真實設備狀態資料經常為不平衡資料（Imbalance Data），也就是說設備正常資料量遠多於失效狀態之資料，這狀況會影響決策資料之正確性。本研究將透過資訊粒化技術來減少資料量，並增加稀少資料的比例以解決資料不平衡的問題，提供決策者更精確之資訊。
研究中將以台電公司火力發電廠為例.由於電廠中之產出為發電量，發電量對於設備各項參數如溫度、壓力、振動、輪軸轉速之變化亦最為敏感，因此失效模式分析將以發電量變化為主要監測對象，透過資訊粒化縮減資料量，再分別以類神經網路及支援向量機對縮減後資料進行訓練，而分類結果能輔助失效原因診斷，進而針對失效狀況即時作出回應。

Equipments, especially those with substantial adding value, are important assets of a company and need to be carefully maintained. Since most of the industries are highly automated, the condition of machines directly affects the capacity, quality and yield of a production system. As a result, equipment failure mode analysis becomes a crucial issue for equipment providers and shop floor supervisors. The historical information of a machine can be voluminous, and imbalance phenomenon often exists between normal data and failure data. In this study, imbalance data mining, a data mining technique, is adopted to solve this problem. Some practical data are used to verify the feasibility of this method.
This study takes the Taipower thermal power plant as its example. Since the parameters of a machine or equipment, such as temperature, pressure, vibration, and turbine shaft speed, exert considerable influence on the power load, Failure Mode and Effect Analysis conducted by this study focuses on monitoring the power load. The method reduces the size of information by using granulation technique and trains the reduced information by neural network and support vector machine. The results of classification can help diagnose the reasons of failures and provide real-time responses to handle the failures.

摘　要 i
ABSTRACT ii
誌 謝 iii
目 錄 iv
表目錄 vii
圖目錄 ix
第一章 緒論 1
1.1 研究背景與動機 1
1.2 研究目的 3
1.3 研究架構與流程 3
第二章 文獻探討 6
2.1 電子化製造 6
2.1.1 電子化製造的原理和定義 6
2.1.2 電子化製造架構 8
2.1.3 半導體業之電子化製造 10
2.2 電子化維護 13
2.2.1 電子化維護定義 14
2.2.2 電子化維護指導方針構成要素 14
2.2.3 電子化維護能力 14
2.2.4 智慧型維護系統 16
2.3 資料探勘 18
2.3.1 資料探勘簡介 18
2.3.2 屬性選取方法 20
2.3.3 資料探勘相關技術 21
2.3.4 分類相關技術 22
2.3.5 分群相關技術 26
2.4 資訊粒化 33
2.4.1 資訊粒化簡介 33
2.4.2 資訊粒化程序 35
2.4.3 資訊粒子建構 35
2.4.4 資訊粒度之選取 36
2.4.5 資料粒子的描述 40
2.4.6 資訊粒子之屬性選取及知識萃取 42
2.4.7 資訊粒化之應用 43
2.5 潛在語意檢索 44
2.5.1 潛在語意檢索原理 45
2.5.2 奇異值分解 46
2.5.3 應用LSI於縮減詞彙-文件矩陣 47
2.5.4 潛在語意檢索之應用 49
2.6 失效模式與效應分析 50
2.6.1 FMEA步驟 51
2.6.2 FMEA之應用 52
2.6.3 失效樹分析 54
2.7 火力發電 57
2.7.1 火力發電廠設備簡介 57
2.7.2 汽力機組重要監視參數 59
2.7.3 汽力機組常見失效狀況 61
2.7.4 安全系統 62
第三章 失效分析方法 63
3.1 資訊粒化演算法 63
3.1.1 應用分群法於資訊粒化 63
3.1.2 IG+LSI演算法 64
3.2 倒傳遞類神經網路 67
3.2.1 應用BPN方法於資料分類流程 69
3.3 支援向量機 70
3.3.1 線性支援向量機 71
3.3.2 非線性支援向量機 72
3.3.3 應用SVM方法於資料分類流程 74
3.4 基於決策樹之失效樹模型建構 75
第四章 實證研究 77
4.1 資料敘述 77
4.2 資料前處理 79
4.2.1 決策樹分析 79
4.2.2 迴歸分析 81
4.2.3 結合決策樹與迴歸分析 87
4.3 資料分析 88
4.3.1 實驗架構與原始資料分析 88
4.3.2 執行IG+LSI之分析結果 91
4.3.3 實驗結果討論 107
4.4 基於決策樹之失效樹分析 109
4.4.1 決策樹 109
4.4.2 失效樹 112
第五章 結論與建議 114
5.1 研究結論 114
5.2 未來建議 115
參考文獻 116
附錄 DM_tool使用說明 122

[1]Han, J., and Kamber, M., 2001, Data Mining：Concepts and Techniques, San Francisco: Morgan Kaufmann.
[2]Tan, P. N., Steinbach, M., Kumar, V., 2006, Introduction to Data Minining, Boston : Addison Wesley.
[3]Chawla, N. V., Japkowicz, N., Kolcz, A., 2004, Special issue on learning from imbalanced data sets, Explorations, 6(1), 1-6.
[4]Muammer Koç, Jun Ni, Jay Lee, Pulak Bandyopadhyay, “INTRODUCTION OF e-MANUFACTURING”, 2003, http://www.e-insite.net/semiconductor/
[5].Dave Bloss and Devadas Pillai Intel Corp., Chandler, Ariz., “E-Manufacturing Opportunities in Semiconductor Processing”,Semiconductor International,7/1/2001, http://www.e-insite.net/semiconductor/
[6]Semiconductor Leading Edge Technologies Inc, Equipment Engineering System Data collection Capability Requirement Document, 2003
[7]Singer, P., “E-Diagnostics: Monitoring Tool Performance, Semiconductor International”, 2001, http://www.e-insite.net/semiconductor/
[8]Zaifeng Chen, Jay Lee, Hai Qiu, Intelligent Maintenance Infotronics System Platform for Remote Monitoring and E-Maintenance,2003,http://www.imscenter.net
[9]Dragan Djurdjanovic, Jihong Yan, Hai Qiu, Jay Lee, Jun Ni, Web-Enabled Remote Spindle Monitoring and Prognostics, 2003.
[10]Zadeh, L. A., 1994, Fuzzy Graphs, Rough Sets and Information Granularity, Proceedings of the third international workshop on rough sets and soft computing.
[11]Yao, Y. Y., 2001, Modeling Data Mining with Granular Computing, Proceedings of the 25th Annual International Computer Software and Applications Conference (COMPSAC 2001).
[12]Taguchi, G., and Juoulum, R., 2002, The Mahalanobis-Taguchi strategy-a pattern technology system, New York : Wiley.
[13]Bargiela, A., Pedrycz, W., 2003, Granular Computing : An introduction, Boston : Kluwer Academic Publishers.
[14]Su, C. T., Chen, L. S., Yih, Y., 2006, Knowledge acquisition through information granulation for imbalanced data, Expert Systems with Applications.
[15]Castellano, G., Fanelli, A. M., Italy, B., 2001, Information Granulation via Neural Network-Based Learning, IFSA World Congress and 20th NAFIPS International Conference, 3059-3064.
[16]Chen, L. S., 2006, Granular computing for imbalance data : theory and application, Doctoral dissertation, Department of Industrial Engineering and Management, National Chiao Tung University, Taiwan.
[17]Jang, J. R., 1993,Adaptive-Network-Based Fuzzy Inference System, IEEE Transactions on Systems, 23(3), 665-684.
[18]Kohonen, T., 1982, Self-organized formation of topologically correct feature maps, Biological Cybernetics, 43, 59-69.
[19]Bezdek, J. C., 1973, Cluster Validity with Fuzzy Sets, Journal of Cybernetics, 3(3), 58-73.
[20]Bargiela, A., Pedrycz, W., 2001, Classification and Clustering of Granular Data, Proceedings of IFSA-NAFIPS.
[21]Pedrycz, W., and Bargiela, A., 2002, Granular clustering : A granular signature of data, IEEE Transactions on Systems, man, and Cybernetics-Part B : Cybernetics, 32(2), 212-224.
[22]Mitra, S., Pal, S.K., Mitra, P., 2002, Data mining in soft computing framework : A survey, IEEE Transactions on Neural Networks, 13(1), 3-14.
[23]Yao, Y. Y., 2000, Granular Computing : Basic Issues and Possible Solutions, Proceedings of the 5th Joint Conference on Information Sciences. 186-189.
[24]Tan, P. N., Steinbach, M., Kumar, V., 2006, Introduction to Data Minining, Boston : Addison Wesley.
[25]David H., 1993, Using Statistical Testing in the Evalution of Retrieval Performance, Proc. Of the16th ACM/SIGIR Conference, 329-338.
[26]Deerwester, S., Dumais, S.T., Furnas, G..W., Landauer, T.K., Harshman, R., 1990, Indexing by latent semantic analysis, Journal of the American Society for Information Science, 41(6), 391-407.
[27]Sparck Jones, K., 1972, A statistical interpretation of term specificity and its applications in retrieval, Journal of Documentation, 28(1), 11-21.
[28]Van Rijsbergen, C. J., 1977, A theoretical basis for the use of co-occurrence data in information retrieval, Journal of Documentation, 33(2), 106-119.
[29]Berry, M. W., Dumais, S. T., Shippy, A. T., 1995, A Case Study of Latent Semantic Indexing, Tech. Rep. CS-95-271, University of Tennessee, Knoxville, TN, Jan.
[30]Sun, J. T., Chen Z., Zeng, H. J., Lu, Y. C., Shi, C. Y., Ma, W.Y., 2004, Supervised Latent Semantic Indexing for Document Categorization, 4th International Conference on Data Mining, 1-5.
[31]Foltz, P. W., 1990, Using latent semantic indexing for information filtering, ACM SIGOIS Bulletin, Proceedings of the conference on Office information systems, 11(2), 40-47.
[32]Golub, G., van Loan, C., 1989, Matrix computation (2nd ed.), MD: John Hopkins.
[33]Syu I., Lang, S. D., Deo, N., 1996, Incorporating Latent Semantic Indexing into a Neural Network Model for Information Retrieval, Proceedings of the fifth international conference on Information and knowledge management, 145-153.
[34]Hull, D., 1994, Improving Text Retrieval for the Routing problem Using Latent Semantic Indexing, Proceedings of the 17th annual international ACM SIGIR conference on Research and development in information retrieval, 282-291.
[35]Kontostathis, A., Pottenger, W. M., 2006, A framework for understanding LSI performance, Information Processing and Management, 42(1), 56-73.
[36]Bellegarda, J. R., 2000, Exploiting Latent Semantic Information in Statistical Language Modeling, Proceedings of IEEE, 88(8), 1279-1296.
[37]Vellido, A., Lisboa, P. J. G., Vaughan, J., 1999, Neural network in business : a survey of applications, Expert Systems with Application, 17, 51-70.
[38]Zhang, G. P., 2000, Neural networks for classification : a survey, IEEE Transactions on Systems, Man and Cybernetics-Part C : Applications and Review, 30(4), 451-462.
[39]Freeman, J. A. and Skapura, D. M.,1992, Neural Networks Algorithms, Applications, and Programming Techniques, Addison-Wesley Publishing Company: New York.
[40]V. Vapnik and A. Lerner, 1963, Pattern recognition using generalized portrait method,Automation and Remote Control,24,709-715.
[41]N. Cristianini,J. Shawf-Taylor,2000, An Introduction to Support Vector Machines and other kernel-based learning methods,Cambridge UniversityPress.
[42]C.J.C. Burges, 1998, A tutorial on support vector machines for pattern recognition. Data Mining and Knowledge Discovery,2(2):955-974.
[43]J. Friedman,1996,Another approach to polychotomous classification.Technical report,Department of Statistics,Stanford University.
[44]J.C. Platt, N. Cristianini and I. Shawe-Taylor ,2000, Large margin DAGs for multicall classification. In Advances in Neural Information Processing System,vol.12,pp.547-553.MIT Press.
[45]B.E. Boser,I.M. Guyon and V. Vapnik,1992,A training algorithm for optimal margin classifiers. In Fifth Annual Workshop on Computational Learning Theory,Pittsburgh,ACM.
[46]Steve R. Gunn,1998, Support Vector Machines for Classification and Regression. University of Southampton, Technical Report .
[47]Chih-Wei Hsu, Chih-Chung Chang and Chih-Jen Lin,2003, A Practical Guide to Support Vector Classification, Available at http://www.csie.ntu.edu.te/~cjlin/papers/guide/guide.pdf
[48]Fodor, I. K., Kamath, C., 2002, Dimension reduction techniques and the classification of bent double galaxies, Computational Statistics & Data Analysis, 91-122
[49]Smyth, B., 1999, Constructing competent case-based reasoners: theories, tools and techniques, Proceedings of the Workshop on Automating the Construction of Case-Based Reasoners, Stockholm, Sweeden.
[50]Riesbeck, C., Schank, R., 1989, Inside Case-Based Reasoning, NJ : Lawerence Erlbaum
[51]Duda, R. and Hart, P., 1973, Pattern Classification and Scene Analysis, New York : John Wiley & Sons.
[52]Goldberg, D., 1989, Genetic Algorithms in Search, Optimization, and Machine Learning, MA：Addison-Wesley.
[53]Pawlak, Z., 1991, Theoretical Aspects of Reasoning about Data, Boston : Kluwer Academic Publishers.
[54]Cios, K., Pedrycz, W., Swiniarski, R., 1998, Data Mining Methods for Knowiedge Discovery, Boston : Kluwer Academic Publishers.
[55]Rumelhart, D. E., Zipser, D., 1985, Feature discovery by competitive learning, Cognitive Science, 9:75-112.
[56]Stamatis, D. H., “Failure mode and effect tanalysis: FMEA from theory to execution”, 1995.
[57]Anand Pillay, Jin Wang, “Modified failure mode and effects analysis using approximate reasoning” ,Reliability Engineering and System Safety Volume: 79, Issue: 1, January 1, 2003, pp. 69-85.
[58]Haapanen Pentti, Helminen Atte,” Failure mode and effects analysis of software-based automation systems”, STUK-YTO-TR 190. Helsinki 2002.
[59]http://www.taipower.com.tw/
[60]小野盛寺重，“實踐FMEA手法”， 2001.
[61]劉愛忠，中國電力出版社，北京，汽輪機設備及運行，2003.
[62]曾韋榮，2006，結合潛在語意檢索及資訊粒化於資料探勘，國立台北科技大學商業自動化與管理研究所碩士論文。
[63]黃勝良，前程出版社，高雄市，複循環電廠概論與能源運用，2001.
[64]Jiawei Han andMicheline Kamber, Data Mining concepts and techniques, Morgan Kavfmann Publishers, 2001.