データマイニングによる高圧受電設備保全技術高度化の提案

カテゴリ: 論文誌(論文単位)

グループ名: 【D】産業応用部門

発行日: 2013/12/02

タイトル(英語): Improved Inspection of Facilities for High-Voltage Class using Datamining

著者名: 西村　和則（広島工業大学 大学院 工学系研究科），前畑　安志（広島工業大学 大学院 工学系研究科），砂山　渡（広島市立大学 大学院 情報科学研究科）

著者名(英語): Kazunori Nishimura (Graduate School of Engineering, Hiroshima Institute of Technology), Yasushi Maehata (Graduate School of Engineering, Hiroshima Institute of Technology), Wataru Sunayama (Graduate School of Information Sciences, Hiroshima City University)

キーワード: 状態監視保全，定期保全，データマイニング，保全高度化，故障予測モデル　　condition based maintenance，time based maintenance，data mining，improvement of maintenance，failure predictive model

要約(英語): In recent years, the inspection of power supply facilities can be conducted with high accuracy using remote monitoring technology. In contrast, it is difficult to install sensors at demand facilities because their scale and installation environment differ among customers. As a result, the demand facilities are inspected at fixed time intervals. In this paper, we propose Condition-Based Maintenance (CBM), which improves the maintenance quality at the demand facilities. The proposed method is developed using the maintenance data of demand facilities, which has been collected using Time-Based Maintenance (TBM) thus far, and we conduct analysis primarily using failure data. We use Datamining to analyze transaction data that we modeled based on the maintenance data and to construct the “failure predictive model” that can predict the failure of facilities and its causes from the results of the analysis. By using the constructed model, we will be able to define an object that requires maintenance, which may most likely lead to failures in the future, and this study can contribute to improvement in maintenance technologies for the demand facilities using the proposed CBM.

本誌: 電気学会論文誌D（産業応用部門誌） Vol.133 No.12 （2013）

本誌掲載ページ: 1165-1170 p

原稿種別: 論文／日本語

電子版へのリンク: https://www.jstage.jst.go.jp/article/ieejias/133/12/133_1165/_article/-char/ja/