Radio location of partial discharge sources: a support vector regression approach

E. T. Iorkyase, C. Tachtatzis, P. Lazaridis, I. A. Glover, R. C. Atkinson

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

Partial discharge (PD) can provide a useful forewarning of asset failure in electricity substations. A significant proportion of assets are susceptible to PD due to incipient weakness in their dielectrics. This paper examines a low cost approach for uninterrupted monitoring of PD using a network of inexpensive radio sensors to sample the spatial patterns of PD received signal strength. Machine learning techniques are proposed for localisation of PD sources. Specifically, two models based on Support Vector Machines (SVMs) are developed: Support Vector Regression (SVR) and Least-Squares Support Vector Regression (LSSVR). These models construct an explicit regression surface in a high dimensional feature space for function estimation. Their performance is compared to that of artificial neural network (ANN) models. The results show that both SVR and LSSVR methods are superior to ANNs in accuracy. LSSVR approach is particularly recommended as practical alternative for PD source localisation due to it low complexity.
LanguageEnglish
Number of pages9
JournalIET Science, Measurement and Technology
Early online date1 Nov 2017
DOIs
Publication statusE-pub ahead of print - 1 Nov 2017

Fingerprint

Partial discharges
regression analysis
machine learning
electricity
Support vector machines
Learning systems
proportion
Electricity
Neural networks
Monitoring
sensors
Sensors
Costs

Keywords

  • partial discharge
  • electricity substations
  • support vector regression

Cite this

@article{5840a688fb2d408bb66d2b3c6908be09,
title = "Radio location of partial discharge sources: a support vector regression approach",
abstract = "Partial discharge (PD) can provide a useful forewarning of asset failure in electricity substations. A significant proportion of assets are susceptible to PD due to incipient weakness in their dielectrics. This paper examines a low cost approach for uninterrupted monitoring of PD using a network of inexpensive radio sensors to sample the spatial patterns of PD received signal strength. Machine learning techniques are proposed for localisation of PD sources. Specifically, two models based on Support Vector Machines (SVMs) are developed: Support Vector Regression (SVR) and Least-Squares Support Vector Regression (LSSVR). These models construct an explicit regression surface in a high dimensional feature space for function estimation. Their performance is compared to that of artificial neural network (ANN) models. The results show that both SVR and LSSVR methods are superior to ANNs in accuracy. LSSVR approach is particularly recommended as practical alternative for PD source localisation due to it low complexity.",
keywords = "partial discharge, electricity substations, support vector regression",
author = "Iorkyase, {E. T.} and C. Tachtatzis and P. Lazaridis and Glover, {I. A.} and Atkinson, {R. C.}",
note = "This paper is a postprint of a paper submitted to and accepted for publication in IET Science, Measurement & Technology and is subject to Institution of Engineering and Technology Copyright. The copy of record is available at the IET Digital Library.",
year = "2017",
month = "11",
day = "1",
doi = "10.1049/iet-smt.2017.0175",
language = "English",
journal = "IET Science, Measurement and Technology",
issn = "1751-8822",
publisher = "Institution of Engineering and Technology",

}

TY - JOUR

T1 - Radio location of partial discharge sources

T2 - IET Science, Measurement and Technology

AU - Iorkyase, E. T.

AU - Tachtatzis, C.

AU - Lazaridis, P.

AU - Glover, I. A.

AU - Atkinson, R. C.

N1 - This paper is a postprint of a paper submitted to and accepted for publication in IET Science, Measurement & Technology and is subject to Institution of Engineering and Technology Copyright. The copy of record is available at the IET Digital Library.

PY - 2017/11/1

Y1 - 2017/11/1

N2 - Partial discharge (PD) can provide a useful forewarning of asset failure in electricity substations. A significant proportion of assets are susceptible to PD due to incipient weakness in their dielectrics. This paper examines a low cost approach for uninterrupted monitoring of PD using a network of inexpensive radio sensors to sample the spatial patterns of PD received signal strength. Machine learning techniques are proposed for localisation of PD sources. Specifically, two models based on Support Vector Machines (SVMs) are developed: Support Vector Regression (SVR) and Least-Squares Support Vector Regression (LSSVR). These models construct an explicit regression surface in a high dimensional feature space for function estimation. Their performance is compared to that of artificial neural network (ANN) models. The results show that both SVR and LSSVR methods are superior to ANNs in accuracy. LSSVR approach is particularly recommended as practical alternative for PD source localisation due to it low complexity.

AB - Partial discharge (PD) can provide a useful forewarning of asset failure in electricity substations. A significant proportion of assets are susceptible to PD due to incipient weakness in their dielectrics. This paper examines a low cost approach for uninterrupted monitoring of PD using a network of inexpensive radio sensors to sample the spatial patterns of PD received signal strength. Machine learning techniques are proposed for localisation of PD sources. Specifically, two models based on Support Vector Machines (SVMs) are developed: Support Vector Regression (SVR) and Least-Squares Support Vector Regression (LSSVR). These models construct an explicit regression surface in a high dimensional feature space for function estimation. Their performance is compared to that of artificial neural network (ANN) models. The results show that both SVR and LSSVR methods are superior to ANNs in accuracy. LSSVR approach is particularly recommended as practical alternative for PD source localisation due to it low complexity.

KW - partial discharge

KW - electricity substations

KW - support vector regression

UR - http://digital-library.theiet.org/content/journals/10.1049/iet-smt.2017.0175;jsessionid=1kcwkkz64ix2m.x-iet-live-01

U2 - 10.1049/iet-smt.2017.0175

DO - 10.1049/iet-smt.2017.0175

M3 - Article

JO - IET Science, Measurement and Technology

JF - IET Science, Measurement and Technology

SN - 1751-8822

ER -