A novel approach to diagnosis of defective equipments in GIS using self organizing map

Raj Aggarwal; Tao Lin; Chul Hwan Kim

A novel approach to diagnosis of defective equipments in GIS using self organizing map

Raj Aggarwal
, Tao Lin
, Chul Hwan Kim

Department of Electronic and Electrical Engineering

University of Bath, Department of Electronic & Electrical Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Scopus citations

Abstract

The condition monitoring (CM) for the Gas Insulated Switchgear (GIS) requires an accurate and reliable identification of the defective equipments in it for maintenance purposes. In this paper, a feature extraction procedure is explored, which is based on the power spectra density (PSD) of the de-noised partial discharges (PDs) emanating from the defective equipments in GIS. Furthermore, artificial intelligence techniques, in particular, the Self Organizing Map (SOM) is investigated for the role as classifier to precisely identify these defective equipments, based on the PSD feature patterns. The performance of the SOM based classifier is ascertained by using the PDs acquired from practical GISs on South Korean 154 kV EHV transmission networks.

Original language	English
Title of host publication	2004 IEEE Power Engineering Society General Meeting
Pages	362-367
Number of pages	6
State	Published - 2004
Event	2004 IEEE Power Engineering Society General Meeting - Denver, CO, United States Duration: 6 Jun 2004 → 10 Jun 2004

Publication series

Name	2004 IEEE Power Engineering Society General Meeting
Volume	1

Conference

Conference	2004 IEEE Power Engineering Society General Meeting
Country/Territory	United States
City	Denver, CO
Period	6/06/04 → 10/06/04

Keywords

Artificial neural networks
Equipment defect diagnosis
Gas insulated switchgear
Self organizing map

Cite this

@inproceedings{a40923c5b65349c390e4846a87045acc,

title = "A novel approach to diagnosis of defective equipments in GIS using self organizing map",

abstract = "The condition monitoring (CM) for the Gas Insulated Switchgear (GIS) requires an accurate and reliable identification of the defective equipments in it for maintenance purposes. In this paper, a feature extraction procedure is explored, which is based on the power spectra density (PSD) of the de-noised partial discharges (PDs) emanating from the defective equipments in GIS. Furthermore, artificial intelligence techniques, in particular, the Self Organizing Map (SOM) is investigated for the role as classifier to precisely identify these defective equipments, based on the PSD feature patterns. The performance of the SOM based classifier is ascertained by using the PDs acquired from practical GISs on South Korean 154 kV EHV transmission networks.",

keywords = "Artificial neural networks, Equipment defect diagnosis, Gas insulated switchgear, Self organizing map",

author = "Raj Aggarwal and Tao Lin and Kim, \{Chul Hwan\}",

year = "2004",

language = "English",

isbn = "0780384652",

series = "2004 IEEE Power Engineering Society General Meeting",

pages = "362--367",

booktitle = "2004 IEEE Power Engineering Society General Meeting",

note = "2004 IEEE Power Engineering Society General Meeting ; Conference date: 06-06-2004 Through 10-06-2004",

}

TY - GEN

T1 - A novel approach to diagnosis of defective equipments in GIS using self organizing map

AU - Aggarwal, Raj

AU - Lin, Tao

AU - Kim, Chul Hwan

PY - 2004

Y1 - 2004

N2 - The condition monitoring (CM) for the Gas Insulated Switchgear (GIS) requires an accurate and reliable identification of the defective equipments in it for maintenance purposes. In this paper, a feature extraction procedure is explored, which is based on the power spectra density (PSD) of the de-noised partial discharges (PDs) emanating from the defective equipments in GIS. Furthermore, artificial intelligence techniques, in particular, the Self Organizing Map (SOM) is investigated for the role as classifier to precisely identify these defective equipments, based on the PSD feature patterns. The performance of the SOM based classifier is ascertained by using the PDs acquired from practical GISs on South Korean 154 kV EHV transmission networks.

AB - The condition monitoring (CM) for the Gas Insulated Switchgear (GIS) requires an accurate and reliable identification of the defective equipments in it for maintenance purposes. In this paper, a feature extraction procedure is explored, which is based on the power spectra density (PSD) of the de-noised partial discharges (PDs) emanating from the defective equipments in GIS. Furthermore, artificial intelligence techniques, in particular, the Self Organizing Map (SOM) is investigated for the role as classifier to precisely identify these defective equipments, based on the PSD feature patterns. The performance of the SOM based classifier is ascertained by using the PDs acquired from practical GISs on South Korean 154 kV EHV transmission networks.

KW - Artificial neural networks

KW - Equipment defect diagnosis

KW - Gas insulated switchgear

KW - Self organizing map

UR - https://www.scopus.com/pages/publications/13244283279

M3 - Conference contribution

AN - SCOPUS:13244283279

SN - 0780384652

SN - 9780780384651

T3 - 2004 IEEE Power Engineering Society General Meeting

SP - 362

EP - 367

BT - 2004 IEEE Power Engineering Society General Meeting

T2 - 2004 IEEE Power Engineering Society General Meeting

Y2 - 6 June 2004 through 10 June 2004

ER -

A novel approach to diagnosis of defective equipments in GIS using self organizing map

Abstract

Publication series

Conference

Keywords

Other files and links

Fingerprint

Cite this