Utility pole deterioration modeling by machine learning with big data of distribution facility inspection result

Thumbnail Image

Files

CIRED 2019 - 774.pdf (662.67 KB)

Paper number

774

Working Group Number

Conference name

CIRED 2019

Conference date

3-6 June 2019

Conference location

Madrid, Spain

Peer-reviewed

Yes

Short title

Convener

Authors

Yamanaka, Masaru, Kansai Electric Power Co.-Inc., Japan
Tokunaga, Tatsuya, Kansai Electric Power Co. Inc., Japan
Matsuki, Tatsushi, Kansai Electric Power Co. Inc., Japan

Abstract

Asthe aging of power distribution facilities progresses, the needs of asset management increases.It is necessary to make a rational repair planconsideringa comprehensive judgment from the view point of safety, cost, and workforce. Therefore, it is important to predict the occurrence of equipment failure and to determine the timing of repair/replacement.To generate data that will contribute to effective asset management, we performed big data analysis using the large amount inspection data possessed by our company. And we have been working on generating deterioration models forfailure modes of utility pole.In this paper, we introduce the accuracy of thedeterioration models which wecreated and an example of items with large influence on the each failure mode.

Table of content

Keywords

Publisher

AIM

Date

2019-06-03

Published in

CIRED 2019 Conference

Permanent link to this record

https://cired-repository.org/handle/20.500.12455/150
http://dx.doi.org/10.34890/304

ISSN

2032-9644

ISBN

978-2-9602415-0-1