臺灣博碩士論文加值系統

在國內的運輸界中，軌道工業一直是相當受到重視的，近百年來對台灣經濟上的貢獻可說相當的重大。然而在營運過程中勢必會碰到電路板件故障與損壞的問題，而在企業內部的維修過程中，常因維修準則判斷不易與工程師經驗傳承等問題，導致影響維修時程與增加維修成本，進而造成企業者莫大的損失。為了解決這些問題，本論文運用資料探勘中的關連法則探勘技術配合Apriori 演算法，對電路板件維修管理系統的維修資料庫進行萃取以及整合。同時設計一套電路板件維修輔助系統，利用探勘維修資料庫之後所得到的規則，對於電路板件故障問題與維修準則之間的關連進行分析，以提供給企業內部維修部門的維修工程師做為維修決策參考之用。由於電路板件維修輔助系統，除了提供故障問題的維修準則之外，同時也針對了電路板件的潛在故障問題提供維修準則的建議，因此可以幫助維修工程師同時進行故障預防檢修的動作，以降低電路板件未來的故障率。目前該系統已實際應用於國內某軌道工業的維修部門中，經過實機的上線測試，將故障電路板件的結案率由73%提升至84%，證明本系統在故障電路板件上的維修建議，確實可以給予維修工程師實質上的幫助。

In the last century, the rail industry has placed an important position in the transportation area, and offers a great contribution to the economics. During industrial operation, the electric board failure is an inevitable problem. It often requires experienced engineers to effectively and efficiently repair the electric boards to reduce the loss that failure made. On the other hand, some failures may cause the other failures occur in the future. To avoid the possibility of malfunctions and reduce the chances an electric board need to be repaired in the near future, it is important to find out the correlations among failures and eliminate all the causes of failures at one repair cycle.
In this study, the Apriori Association Rules Mining algorithms, a famous technique in Data Mining, is applied to extract the association rules of failures from the maintenance database in the Electric Board Maintenance Management System. We use the rules to design an Electric Board Maintenance Supporting System. This system analyzes the relation between the electric board failure and repair strategy according to the rules extracted from maintenance database. It not only provides the suggested repair strategy, but also offers suggestions on the maintenance policy for potential problems. These advices help engineers to take precautions, and then lower the chances of electric board failures.
At present, this system is online to serve the maintenance department of some famous enterprise in Taiwan track industry. According to the data collected from online tests during 3 months, the successful rate of repairing electric board failures is increased from 73% up to 84%. This result indicates that the system we developed helps a lot in maintaining the electric board. The benefits are reducing the loss resulted from multiple failures and increasing the profit gain of the track industry.

中文摘要 1
Abstract 2
誌謝 3
目錄 4
表目錄 6
圖目錄 7
第一章 緒論 9
1.1 研究背景 9
1.2 研究動機 11
1.3 研究目的 12
1.4 論文架構 13
第二章 文獻探討 14
2.1 資料探勘(Data mining) 14
2.1.1 知識發現的過程 15
2.1.2 資料探勘常用的技術 17
2.1.3 資料探勘之六種模型 18
2.2決策支援系統 23
2.3以資料探勘為基礎之決策支援系統 27
2.3.1以資料探勘為基礎之製造業退貨問題管理偵測及分析系統研製 28
2.3.2資料探勘應用於中小企業新產品發展之研究-以自行車產業為例 30
2.4關連法則探勘演算法 32
第三章 電路板件維修決策之探勘 36
3.1 電路板件維修流程 36
3.2 電路板件維修管理系統 39
3.3 資料前處理 43
3.4 電路板件故障關連之探勘 48
3.4.1 電路板件故障關連之探勘方法 48
3.4.2電路板件故障關連之探勘結果 52
3.5 電路板件維修準則之探勘 54
3.5.1電路板件維修準則之探勘方法 54
3.5.2電路板件維修準則之探勘結果 58
3.6 電路板件潛在故障排除準則之探勘 59
3.6.1電路板件潛在故障排除準則之探勘方法 59
3.6.2電路板件潛在故障排除準則之探勘結果 61
第四章 電路板件維修輔助系統 63
4.1 系統架構 63
4.1.1 故障關連探勘模組 64
4.1.2 維修準則探勘模組 65
4.1.3 潛在故障排除準則探勘模組 66
4.1.4 維修決策支援模組 67
4.2 系統實作成果 67
第五章 系統效能評估 75
5.1 評估模式 75
5.2 評估結果 76
第六章 結論及未來展望 84
參考文獻 86

[1] 謝國倫，我國軌道工業合作執行成果與未來作為，工業合作電子報第8期(2005)。
[2] 曾憲雄、曾秋蓉、蔡秀滿、蘇東興，「資料探勘」，旗標出板社，(2005)。
[3] 尹相志，「資料採礦聖經」，學貫行銷股份有限公司，(2006)。
[4] 梁定澎，「決策支援系統與企業智慧」，智勝出版社，(2003)。
[5] 曾守正，「從想像中找出事實：如何使Data Mining 成為企業的一部份？」，資訊與電腦，82-84 (1997)。
[6] 梁定澎，「決策支援系統」，松崗圖書公司，(1999)。
[7] 呂錦松，“以資料探勘為基礎之製造業退貨問題管理偵測及分析系統研製”中華大學資訊工程研究所碩士論文，2004。
[8] 劉基全、溫志皓，“資料探勘應用於中小企業新產品發展之研究-以自行車產業為例”國防大學資源管理研究所碩士論文，2003。
[9] 李美德，“診斷關係群決策支援系統開發與評估以呼吸系統疾病為例”國立中正大學資訊管理研究所碩士論文，2005。
[10] 吳孟賢，“以全球資訊網為基礎之ERP資料探勘整合系統”，國立交通大學資訊管理研究所碩士論文，2002。
[11] R. Agrawal , and R. Srikant , Fast Algorithms for “ Mining Association Rules,” Proceedings of the 20th International Conference on Very Large Databases (VLDB) . Santiago de Chile, Chile. Morgan Kaufmann, ISBN 1-55860-153-8 , pp.487-499,1994
[12] M. Berry, and G. Linoff, “Data Mining Techniques for Marketing, Sales and Customer Support”, pp.112-335, 1997

[13] A. Chen, L. Liu, N. Chen,and G. Xia ,“Application of data mining in supply chain management”, Intelligent Control and Automation. Proceedings of the 3rd World Congress on , Vol.3 , pp. 1943-1947 , 2000.
[14] M.S Chen , J. Han ,and P.S Yu ,Data Mining：An Overview from a Database Perspective, IEEE Transactions on Knowledge and Data engineering, pp. 866-883, 1996.
[15] U.G Fayyad, G. P. Shapiro and P. Smyth, “ The KDD process for extractinguseful knowledge from volumes of data,” Cummunication of the ACM, pp.27-34, 1996.
[16] J. Han , and M. Kamber , Data Mining: Concepts and Techniques, Morgan Kanfmann Publishers, 2001.
[17] J. Han, and Y. Fu, “ Discovery of Multiple-Level AssociationRules “
from large databases,IEEE Transactions on knowledge and Data Engineering, pp11, 1999.
[18] W. Jason, “Data Mining:Exploring The Corporate Asset”,Information Systems Management FALL, 1998.
[19] C. Kleisssner, “Data mining for the enterprise,” In Proceedings of the Thirty-First Hawaii International Conference on, Vol.7, pp.295-304, 1998.
[20] A.Konig , “Interactive visualization and analysis of hierarchical neural projections for data mining”, IEEE Transactions on Neural Networks, Vol.11, No 3 , pp.615-624 , 2000 .
[21] J.W.T. Lee ,“An ordinal framework for data mining of fuzzy rules”, Fuzzy Systems, The Ninth IEEE International Conference on , Vol.1 , pp.399-404, 2000.
[22] H. Maki and Y. Teranishi, Development of Automated Data Mining System for Quality Control in Manufacturing, Vol.2114, issue Lecture Notes in Computer Science, 2002.
[23] H. Markus , Lecture Notes in Artifical Intelligence, “ Algorithms for Association Rules” Vol.2600, pp226-234.
[24] J. Pei, J. Han, H. Lu, S. Nishio, and S. Tang, Dongquing Yang : “ H-Mine: Hyper-Structure Mining of Frequent Patterns in Large Databases ” from VLDB IEEE International Conference on Data Mining, San Jose, California, pp441, 2001.
[25] P. Software ,“An Introduction to Data Mining”.
[26] R.H. Sprague , “A Framework for the Development of Decision Support System”, MIS Quarterly,4(4), 1980.
[27] E. Turban , and J.E. Aronson , “ Decision support system and intelligent system”, Prentice Hall , Upper Saddle River, 1998.
[28] E. Turban , and J.E. Aronson , “ Decision support system and intelligent system” , Ed , Prentice Hall , 2002.
[29] C. Westphal, and T. Blaxton, “Data mining solutions : methods and tools for solving real-world problems ”, 1998.