Random forest based optimal feature selection for partial discharge pattern recognition in HV cables

Xiaosheng Peng, Jinshu Li, Ganjun Wang, Yiijiang Wu, Lee Li, Zhaohui Li, Ashfaque Ahmed Bhatti, Chengke Zhou, Donald M. Hepburn, Alistair J Reid, Martin D. Judd, W. H. Siew

Research output: Contribution to journalArticle

Abstract

Optimal selection of features of Partial Discharge (PD) signals recorded from defects in High Voltage (HV) cables will contribute not only to the improvement of PD pattern recognition accuracy and efficiency but also to PD parameter visualization in HV cable condition monitoring and diagnostics. This paper presents a novel Random Forest (RF)-based feature selection algorithm for PD pattern recognition of HV cables. The algorithm is applied to feature selection of both PD signals and interference signals with the aim of obtaining the optimal features for data processing. Firstly, the experimental data acquisition and feature extraction processes are introduced. PD signals were captured from faults created in a cable to obtain the raw PD data, then a set of 3500 transient PD pulses and a set of 3500 typical interference pulses were extracted, based on which 34 PD features were extracted for further processing. Furthermore, 119 two-dimensional features and 1082 three-dimensional features were generated. The paper then discusses the basic principle of the RF algorithm. Finally, RF-based feature selection was implemented to determine the optimal features for PD pattern recognition. The results were obtained and evaluated with the Back Propagation Neural Network (BPNN) and Support Vector Machine (SVM). Results show that the proposed RF-based method is effective for PD feature selection of HV cables with the potential for application to additional HV power apparatus.
LanguageEnglish
Number of pages10
JournalIEEE Transactions on Power Delivery
Publication statusAccepted/In press - 18 May 2019

Fingerprint

Partial discharges
Pattern recognition
Feature extraction
Cables
Electric potential
Condition monitoring
Signal interference
Backpropagation
Support vector machines
Data acquisition
Visualization
Neural networks
Defects

Keywords

  • feature selection
  • high voltage cables
  • partial discharge
  • random forest

Cite this

Peng, Xiaosheng ; Li, Jinshu ; Wang, Ganjun ; Wu, Yiijiang ; Li, Lee ; Li, Zhaohui ; Ahmed Bhatti, Ashfaque ; Zhou, Chengke ; Hepburn, Donald M. ; Reid, Alistair J ; Judd, Martin D. ; Siew, W. H. / Random forest based optimal feature selection for partial discharge pattern recognition in HV cables. In: IEEE Transactions on Power Delivery. 2019.
@article{247c1f77cb7648c0b9498b41471e73f1,
title = "Random forest based optimal feature selection for partial discharge pattern recognition in HV cables",
abstract = "Optimal selection of features of Partial Discharge (PD) signals recorded from defects in High Voltage (HV) cables will contribute not only to the improvement of PD pattern recognition accuracy and efficiency but also to PD parameter visualization in HV cable condition monitoring and diagnostics. This paper presents a novel Random Forest (RF)-based feature selection algorithm for PD pattern recognition of HV cables. The algorithm is applied to feature selection of both PD signals and interference signals with the aim of obtaining the optimal features for data processing. Firstly, the experimental data acquisition and feature extraction processes are introduced. PD signals were captured from faults created in a cable to obtain the raw PD data, then a set of 3500 transient PD pulses and a set of 3500 typical interference pulses were extracted, based on which 34 PD features were extracted for further processing. Furthermore, 119 two-dimensional features and 1082 three-dimensional features were generated. The paper then discusses the basic principle of the RF algorithm. Finally, RF-based feature selection was implemented to determine the optimal features for PD pattern recognition. The results were obtained and evaluated with the Back Propagation Neural Network (BPNN) and Support Vector Machine (SVM). Results show that the proposed RF-based method is effective for PD feature selection of HV cables with the potential for application to additional HV power apparatus.",
keywords = "feature selection, high voltage cables, partial discharge, random forest",
author = "Xiaosheng Peng and Jinshu Li and Ganjun Wang and Yiijiang Wu and Lee Li and Zhaohui Li and {Ahmed Bhatti}, Ashfaque and Chengke Zhou and Hepburn, {Donald M.} and Reid, {Alistair J} and Judd, {Martin D.} and Siew, {W. H.}",
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 = "5",
day = "18",
language = "English",
journal = "IEEE Transactions on Power Delivery",
issn = "0885-8977",

}

Peng, X, Li, J, Wang, G, Wu, Y, Li, L, Li, Z, Ahmed Bhatti, A, Zhou, C, Hepburn, DM, Reid, AJ, Judd, MD & Siew, WH 2019, 'Random forest based optimal feature selection for partial discharge pattern recognition in HV cables' IEEE Transactions on Power Delivery.

Random forest based optimal feature selection for partial discharge pattern recognition in HV cables. / Peng, Xiaosheng; Li, Jinshu; Wang, Ganjun; Wu, Yiijiang; Li, Lee; Li, Zhaohui; Ahmed Bhatti, Ashfaque; Zhou, Chengke; Hepburn, Donald M.; Reid, Alistair J; Judd, Martin D.; Siew, W. H.

In: IEEE Transactions on Power Delivery, 18.05.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Random forest based optimal feature selection for partial discharge pattern recognition in HV cables

AU - Peng, Xiaosheng

AU - Li, Jinshu

AU - Wang, Ganjun

AU - Wu, Yiijiang

AU - Li, Lee

AU - Li, Zhaohui

AU - Ahmed Bhatti, Ashfaque

AU - Zhou, Chengke

AU - Hepburn, Donald M.

AU - Reid, Alistair J

AU - Judd, Martin D.

AU - Siew, W. H.

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 - 2019/5/18

Y1 - 2019/5/18

N2 - Optimal selection of features of Partial Discharge (PD) signals recorded from defects in High Voltage (HV) cables will contribute not only to the improvement of PD pattern recognition accuracy and efficiency but also to PD parameter visualization in HV cable condition monitoring and diagnostics. This paper presents a novel Random Forest (RF)-based feature selection algorithm for PD pattern recognition of HV cables. The algorithm is applied to feature selection of both PD signals and interference signals with the aim of obtaining the optimal features for data processing. Firstly, the experimental data acquisition and feature extraction processes are introduced. PD signals were captured from faults created in a cable to obtain the raw PD data, then a set of 3500 transient PD pulses and a set of 3500 typical interference pulses were extracted, based on which 34 PD features were extracted for further processing. Furthermore, 119 two-dimensional features and 1082 three-dimensional features were generated. The paper then discusses the basic principle of the RF algorithm. Finally, RF-based feature selection was implemented to determine the optimal features for PD pattern recognition. The results were obtained and evaluated with the Back Propagation Neural Network (BPNN) and Support Vector Machine (SVM). Results show that the proposed RF-based method is effective for PD feature selection of HV cables with the potential for application to additional HV power apparatus.

AB - Optimal selection of features of Partial Discharge (PD) signals recorded from defects in High Voltage (HV) cables will contribute not only to the improvement of PD pattern recognition accuracy and efficiency but also to PD parameter visualization in HV cable condition monitoring and diagnostics. This paper presents a novel Random Forest (RF)-based feature selection algorithm for PD pattern recognition of HV cables. The algorithm is applied to feature selection of both PD signals and interference signals with the aim of obtaining the optimal features for data processing. Firstly, the experimental data acquisition and feature extraction processes are introduced. PD signals were captured from faults created in a cable to obtain the raw PD data, then a set of 3500 transient PD pulses and a set of 3500 typical interference pulses were extracted, based on which 34 PD features were extracted for further processing. Furthermore, 119 two-dimensional features and 1082 three-dimensional features were generated. The paper then discusses the basic principle of the RF algorithm. Finally, RF-based feature selection was implemented to determine the optimal features for PD pattern recognition. The results were obtained and evaluated with the Back Propagation Neural Network (BPNN) and Support Vector Machine (SVM). Results show that the proposed RF-based method is effective for PD feature selection of HV cables with the potential for application to additional HV power apparatus.

KW - feature selection

KW - high voltage cables

KW - partial discharge

KW - random forest

UR - https://ieeexplore.ieee.org/xpl/RecentIssue.jsp

M3 - Article

JO - IEEE Transactions on Power Delivery

T2 - IEEE Transactions on Power Delivery

JF - IEEE Transactions on Power Delivery

SN - 0885-8977

ER -