Improving RF-based Partial Discharge Localization via Machine Learning Ensemble Method

Ephraim Iorkyase, Christos Tachtatzis, Ian Glover, Pavlos Lazaridis, David Upton, Bahghtar Saeed, 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.

Original languageEnglish
Article number8673583
Pages (from-to)1478 - 1489
Number of pages12
JournalIEEE Transactions on Power Delivery
Volume34
Issue number4
Early online date25 Mar 2019
DOIs
Publication statusPublished - 1 Aug 2019

Fingerprint

Partial discharges
Learning systems

Cite this

Iorkyase, E., Tachtatzis, C., Glover, I., Lazaridis, P., Upton, D., Saeed, B., & Atkinson, R. C. (2019). Improving RF-based Partial Discharge Localization via Machine Learning Ensemble Method. IEEE Transactions on Power Delivery, 34(4), 1478 - 1489. [8673583]. https://doi.org/10.1109/TPWRD.2019.2907154
Iorkyase, Ephraim ; Tachtatzis, Christos ; Glover, Ian ; Lazaridis, Pavlos ; Upton, David ; Saeed, Bahghtar ; Atkinson, Robert C. / Improving RF-based Partial Discharge Localization via Machine Learning Ensemble Method. In: IEEE Transactions on Power Delivery. 2019 ; Vol. 34, No. 4. pp. 1478 - 1489.
@article{fc93d4833b2247199b9322abf0432470,
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, Antenna, Wavelet analysis, Machine learning, Localization, Localization Algorithm, Wavelet packet transform, Bootstrap aggregating, Random forest, Regression tree, Partial discharges, Partial discharge, Discrete wavelet transforms, Time-domain analysis, Feature extraction, bootstrap aggregating, localization, regression tree, wavelet packet transform, random forest",
author = "Ephraim Iorkyase and Christos Tachtatzis and Ian Glover and Pavlos Lazaridis and David Upton and Bahghtar Saeed and Atkinson, {Robert C.}",
year = "2019",
month = "8",
day = "1",
doi = "10.1109/TPWRD.2019.2907154",
language = "English",
volume = "34",
pages = "1478 -- 1489",
journal = "IEEE Transactions on Power Delivery",
issn = "0885-8977",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "4",

}

Iorkyase, E, Tachtatzis, C, Glover, I, Lazaridis, P, Upton, D, Saeed, B & Atkinson, RC 2019, 'Improving RF-based Partial Discharge Localization via Machine Learning Ensemble Method', IEEE Transactions on Power Delivery, vol. 34, no. 4, 8673583, pp. 1478 - 1489. https://doi.org/10.1109/TPWRD.2019.2907154

Improving RF-based Partial Discharge Localization via Machine Learning Ensemble Method. / Iorkyase, Ephraim; Tachtatzis, Christos; Glover, Ian; Lazaridis, Pavlos; Upton, David; Saeed, Bahghtar; Atkinson, Robert C.

In: IEEE Transactions on Power Delivery, Vol. 34, No. 4, 8673583, 01.08.2019, 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

AU - Tachtatzis, Christos

AU - Glover, Ian

AU - Lazaridis, Pavlos

AU - Upton, David

AU - Saeed, Bahghtar

AU - Atkinson, Robert C.

PY - 2019/8/1

Y1 - 2019/8/1

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 - Antenna

KW - Wavelet analysis

KW - Machine learning

KW - Localization

KW - Localization Algorithm

KW - Wavelet packet transform

KW - Bootstrap aggregating

KW - Random forest

KW - Regression tree

KW - Partial discharges

KW - Partial discharge

KW - Discrete wavelet transforms

KW - Time-domain analysis

KW - Feature extraction

KW - bootstrap aggregating

KW - localization

KW - regression tree

KW - wavelet packet transform

KW - random forest

UR - http://www.scopus.com/inward/record.url?scp=85063368029&partnerID=8YFLogxK

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

JF - IEEE Transactions on Power Delivery

SN - 0885-8977

IS - 4

M1 - 8673583

ER -