台電事故案例系統之設計及群集演算法於文件搜尋之應用

Design of Accident Case Management System and Application of Clustering Algorithm to Document Retrieval

劉錦興(Jin-Xing Liu)

指導教授 ： 姚立德

國立臺北科技大學/機電學院/電機工程系所/碩士(2011年)

摘要

為落實台電變電設備狀態基準維護(Condition-based Maintenance, CBM)之目標，本論文將「事故案例管理系統」及「異狀管理系統」的資料庫建置整合「變電設備維護管理系統」，並新增「細密巡視」功能於現有之「變電設備維護管理系統」，提高預防性維護之效能。
隨著台電設備之老化、天災及人為因素等事故情形之發生，因此本論文建置事故案例管理系統伺服器成為知識管理系統，以便提供台電人員做為參考之依據，目的為預防事故的發生以及提升整體之處理流程和經驗。過去關於資料查詢時，經常使用資料檢索技術，強化資料搜尋的準確性，本論文探討台電所架設之事故案例管理系統利用網頁使用模式探勘的觀念與方法，提出一種使用者導向之文件分群方法，透過使用者使用之關鍵字搜尋與瀏覽紀錄決定事故案例文件間的相似度，並利用資料探勘中群集演算法進行文件分群，歸納而成為未來使用者的相關資訊推薦。

關鍵字

事故案例管理系統 ； 網頁使用探勘 ； 群集演算法 ； 文件分群

並列摘要

For the implementation of Taiwan power Condition-based Maintenance of the target, The “Accident Case Management System” and The “Abnormal Management System” database integration The “Substation Facility Maintenance and Management System (SFMMS)”,and add a “Detailed Inspection” capabilities of the existing SFMMS to improve the effectiveness of preventive maintenance.
With the aging of Taiwan power equipment, natural disasters and man-made factors such as the occurrence of the accident situation,so The “Accident Case Management System” to build as a knowledge management system server,in order to provide a basis for Taiwan power as a reference, the purpose of preventing accidents and the processes and enhance the overall experience.Information queries about the past, often using information retrieval technology, and strengthen the accuracy of information search. The study of “Accident Case Management System” in Taiwan power using the concept of Web Usage Mining Concept and methods, present a user-oriented document clustering methods, by the user using the keyword search and browsing records to determine the similarity between the accident cases,and use of cluster algorithms in data mining, summarized as future users of information about the recommendation.

並列關鍵字

Accident Case Management System ； Web Usage Mining ； Cluster Algorithms ； Document Clustering

參考文獻

[1] U. Fayyad, G. Piateskyy-Shapiro and P. Smyth, ”From Data Mining to Knowledge Discovery in Databases,” American Association for Artifical Intelligence, pp. 37-54, Fall 1996.

[2] Q. Song and M. Shepperd, “Mining Web Browsing Pattern for E-commerce,” Computers in Industry, Vol. 57, pp. 622-630, June 2006.

[3] F. M. Facca and P. L. Lanzi, “Mining Interesting Knowledge From Weblogs: A Survey,” Data & Knowledge Engineering, Vol. 53, pp. 225-241, Aug 2005.

[5] A. Edmunds and A. Morris, “The Problem of Information Overload in Business Organizations: A Review of the Literature,” International Journal of Information Management, Vol 20, No. 1, pp. 17-28, 2000.

[6] Etzioni, “The World-Wide Web: Quagmire or Gold Mine?,” Communications of the ACM, Vol. 39, No. 11, pp. 65-68, Nov. 1996.