Improving RF-based partial discharge localization via machine learning ensemble method

Ephraim Tersoo Iorkyase, Christos Tachtatzis, Pavlos Lazaridis, David Upton, Bakhtiar Saeed, Ian Glover, Robert C. Atkinson

Research output: Contribution to journalArticle

Abstract

Partial discharge (PD) is regarded as a precursor to plant failure and therefore, an effective indication of plant condition. Locating the source of PD before failure is key to efficient maintenance and improving reliability of power systems. This paper presents a low cost, autonomous partial discharge radiolocation mechanism to improve PD localization precision. The proposed radio frequency-based technique uses the wavelet packet transform (WPT) and machine learning ensemble methods to locate PDs. More specifically, the received signals are decomposed by the WPT and analyzed in order to identify localized PD signal patterns in the presence of noise. The regression tree algorithm, bootstrap aggregating method, and regression random forest are used to develop PD localization models based on the WPT-based PD features. The proposed PD localization scheme has been found to successfully locate PD with negligible error. Additionally, the principle of the PD location scheme has been validated using a separate test dataset. Numerical results demonstrate that the WPT-random forest PD localization scheme produced superior performance as a result of its robustness against noise.

LanguageEnglish
Pages1478-1489
Number of pages12
JournalIEEE Transactions on Power Delivery
Volume34
Issue number4
Early online date25 Mar 2019
DOIs
Publication statusPublished - 31 Aug 2019

Fingerprint

Partial discharges
Learning systems

Keywords

  • partial discharge
  • localization
  • wavelet packet transform
  • bootstrap aggregating
  • random forest
  • regression tree

Cite this

@article{cf2646503e854f96a023f65e1dd9a2eb,
title = "Improving RF-based partial discharge localization via machine learning ensemble method",
abstract = "Partial discharge (PD) is regarded as a precursor to plant failure and therefore, an effective indication of plant condition. Locating the source of PD before failure is key to efficient maintenance and improving reliability of power systems. This paper presents a low cost, autonomous partial discharge radiolocation mechanism to improve PD localization precision. The proposed radio frequency-based technique uses the wavelet packet transform (WPT) and machine learning ensemble methods to locate PDs. More specifically, the received signals are decomposed by the WPT and analyzed in order to identify localized PD signal patterns in the presence of noise. The regression tree algorithm, bootstrap aggregating method, and regression random forest are used to develop PD localization models based on the WPT-based PD features. The proposed PD localization scheme has been found to successfully locate PD with negligible error. Additionally, the principle of the PD location scheme has been validated using a separate test dataset. Numerical results demonstrate that the WPT-random forest PD localization scheme produced superior performance as a result of its robustness against noise.",
keywords = "partial discharge, localization, wavelet packet transform, bootstrap aggregating, random forest, regression tree",
author = "Iorkyase, {Ephraim Tersoo} and Christos Tachtatzis and Pavlos Lazaridis and David Upton and Bakhtiar Saeed and Ian Glover and Atkinson, {Robert C.}",
note = "{\circledC} 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting /republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.",
year = "2019",
month = "8",
day = "31",
doi = "10.1109/TPWRD.2019.2907154",
language = "English",
volume = "34",
pages = "1478--1489",
journal = "IEEE Transactions on Power Delivery",
issn = "0885-8977",
number = "4",

}

Improving RF-based partial discharge localization via machine learning ensemble method. / Iorkyase, Ephraim Tersoo; Tachtatzis, Christos; Lazaridis, Pavlos; Upton, David; Saeed, Bakhtiar; Glover, Ian; Atkinson, Robert C.

In: IEEE Transactions on Power Delivery, Vol. 34, No. 4, 31.08.2019, p. 1478-1489.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Improving RF-based partial discharge localization via machine learning ensemble method

AU - Iorkyase, Ephraim Tersoo

AU - Tachtatzis, Christos

AU - Lazaridis, Pavlos

AU - Upton, David

AU - Saeed, Bakhtiar

AU - Glover, Ian

AU - Atkinson, Robert C.

N1 - © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting /republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

PY - 2019/8/31

Y1 - 2019/8/31

N2 - Partial discharge (PD) is regarded as a precursor to plant failure and therefore, an effective indication of plant condition. Locating the source of PD before failure is key to efficient maintenance and improving reliability of power systems. This paper presents a low cost, autonomous partial discharge radiolocation mechanism to improve PD localization precision. The proposed radio frequency-based technique uses the wavelet packet transform (WPT) and machine learning ensemble methods to locate PDs. More specifically, the received signals are decomposed by the WPT and analyzed in order to identify localized PD signal patterns in the presence of noise. The regression tree algorithm, bootstrap aggregating method, and regression random forest are used to develop PD localization models based on the WPT-based PD features. The proposed PD localization scheme has been found to successfully locate PD with negligible error. Additionally, the principle of the PD location scheme has been validated using a separate test dataset. Numerical results demonstrate that the WPT-random forest PD localization scheme produced superior performance as a result of its robustness against noise.

AB - Partial discharge (PD) is regarded as a precursor to plant failure and therefore, an effective indication of plant condition. Locating the source of PD before failure is key to efficient maintenance and improving reliability of power systems. This paper presents a low cost, autonomous partial discharge radiolocation mechanism to improve PD localization precision. The proposed radio frequency-based technique uses the wavelet packet transform (WPT) and machine learning ensemble methods to locate PDs. More specifically, the received signals are decomposed by the WPT and analyzed in order to identify localized PD signal patterns in the presence of noise. The regression tree algorithm, bootstrap aggregating method, and regression random forest are used to develop PD localization models based on the WPT-based PD features. The proposed PD localization scheme has been found to successfully locate PD with negligible error. Additionally, the principle of the PD location scheme has been validated using a separate test dataset. Numerical results demonstrate that the WPT-random forest PD localization scheme produced superior performance as a result of its robustness against noise.

KW - partial discharge

KW - localization

KW - wavelet packet transform

KW - bootstrap aggregating

KW - random forest

KW - regression tree

U2 - 10.1109/TPWRD.2019.2907154

DO - 10.1109/TPWRD.2019.2907154

M3 - Article

VL - 34

SP - 1478

EP - 1489

JO - IEEE Transactions on Power Delivery

T2 - IEEE Transactions on Power Delivery

JF - IEEE Transactions on Power Delivery

SN - 0885-8977

IS - 4

ER -