Rough set theory applied to pattern recognition of partial discharge in noise affected cable data

Xiaosheng Peng, Jinyu Wen, Zhaohui Li, Guangyao Yang, Chengke Zhou, Alistair Reid, Donald M. Hepburn, Martin D. Judd, W. H. Siew

Research output: Contribution to journalArticle

13 Citations (Scopus)

Abstract

This paper presents an effective, Rough Set (RS) based, pattern recognition method for rejecting interference signals and recognising Partial Discharge (PD) signals from different sources. Firstly, RS theory is presented in terms of Information System, Lower and Upper Approximation, Signal Discretisation, Attribute Reduction and a flowchart of the RS based pattern recognition method. Secondly, PD testing of five types of artificial defect in ethylene-propylene rubber (EPR) cable is carried out and data pre-processing and feature extraction are employed to separate PD and interference signals. Thirdly, the RS based PD signal recognition method is applied to 4000 samples and is proven to have 99% accuracy. Fourthly, the RS based PD recognition method is applied to signals from five different sources and an accuracy of more than 93% is attained when a combination of signal discretisation and attribute reduction methods are applied. Finally, Back-propagation Neural Network (BPNN) and Support Vector Machine (SVM) methods are studied and compared with the developed method. The proposed RS method is proven to have higher accuracy than SVM and BPNN and can be applied for on-line PD monitoring of cable systems after training with valid sample data.
LanguageEnglish
Pages147-156
Number of pages10
JournalIEEE Transactions on Dielectrics and Electrical Insulation
Volume24
Issue number1
Early online date7 Mar 2017
DOIs
Publication statusE-pub ahead of print - 7 Mar 2017

Fingerprint

Rough set theory
Partial discharges
Pattern recognition
Cables
Signal interference
Backpropagation
Support vector machines
Neural networks
Propylene
Feature extraction
Rubber
Ethylene
Information systems
Defects
Monitoring
Testing
Processing

Keywords

  • partial discharge
  • pattern recognition
  • signal discretisation
  • rough set
  • knowledge rule evaluation
  • cable systems

Cite this

Peng, Xiaosheng ; Wen, Jinyu ; Li, Zhaohui ; Yang, Guangyao ; Zhou, Chengke ; Reid, Alistair ; Hepburn, Donald M. ; Judd, Martin D. ; Siew, W. H. / Rough set theory applied to pattern recognition of partial discharge in noise affected cable data. In: IEEE Transactions on Dielectrics and Electrical Insulation. 2017 ; Vol. 24, No. 1. pp. 147-156.
@article{c8426848c81c4b75913545ee2ff5dd39,
title = "Rough set theory applied to pattern recognition of partial discharge in noise affected cable data",
abstract = "This paper presents an effective, Rough Set (RS) based, pattern recognition method for rejecting interference signals and recognising Partial Discharge (PD) signals from different sources. Firstly, RS theory is presented in terms of Information System, Lower and Upper Approximation, Signal Discretisation, Attribute Reduction and a flowchart of the RS based pattern recognition method. Secondly, PD testing of five types of artificial defect in ethylene-propylene rubber (EPR) cable is carried out and data pre-processing and feature extraction are employed to separate PD and interference signals. Thirdly, the RS based PD signal recognition method is applied to 4000 samples and is proven to have 99{\%} accuracy. Fourthly, the RS based PD recognition method is applied to signals from five different sources and an accuracy of more than 93{\%} is attained when a combination of signal discretisation and attribute reduction methods are applied. Finally, Back-propagation Neural Network (BPNN) and Support Vector Machine (SVM) methods are studied and compared with the developed method. The proposed RS method is proven to have higher accuracy than SVM and BPNN and can be applied for on-line PD monitoring of cable systems after training with valid sample data.",
keywords = "partial discharge, pattern recognition, signal discretisation, rough set, knowledge rule evaluation, cable systems",
author = "Xiaosheng Peng and Jinyu Wen and Zhaohui Li and Guangyao Yang and Chengke Zhou and Alistair Reid and Hepburn, {Donald M.} and Judd, {Martin D.} and Siew, {W. H.}",
note = "{\circledC} 2016 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 = "2017",
month = "3",
day = "7",
doi = "10.1109/TDEI.2016.006060",
language = "English",
volume = "24",
pages = "147--156",
journal = "IEEE Transactions on Dielectrics and Electrical Insulation",
issn = "1070-9878",
number = "1",

}

Rough set theory applied to pattern recognition of partial discharge in noise affected cable data. / Peng, Xiaosheng; Wen, Jinyu; Li, Zhaohui; Yang, Guangyao; Zhou, Chengke; Reid, Alistair; Hepburn, Donald M.; Judd, Martin D.; Siew, W. H.

In: IEEE Transactions on Dielectrics and Electrical Insulation, Vol. 24, No. 1, 07.03.2017, p. 147-156.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Rough set theory applied to pattern recognition of partial discharge in noise affected cable data

AU - Peng, Xiaosheng

AU - Wen, Jinyu

AU - Li, Zhaohui

AU - Yang, Guangyao

AU - Zhou, Chengke

AU - Reid, Alistair

AU - Hepburn, Donald M.

AU - Judd, Martin D.

AU - Siew, W. H.

N1 - © 2016 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 - 2017/3/7

Y1 - 2017/3/7

N2 - This paper presents an effective, Rough Set (RS) based, pattern recognition method for rejecting interference signals and recognising Partial Discharge (PD) signals from different sources. Firstly, RS theory is presented in terms of Information System, Lower and Upper Approximation, Signal Discretisation, Attribute Reduction and a flowchart of the RS based pattern recognition method. Secondly, PD testing of five types of artificial defect in ethylene-propylene rubber (EPR) cable is carried out and data pre-processing and feature extraction are employed to separate PD and interference signals. Thirdly, the RS based PD signal recognition method is applied to 4000 samples and is proven to have 99% accuracy. Fourthly, the RS based PD recognition method is applied to signals from five different sources and an accuracy of more than 93% is attained when a combination of signal discretisation and attribute reduction methods are applied. Finally, Back-propagation Neural Network (BPNN) and Support Vector Machine (SVM) methods are studied and compared with the developed method. The proposed RS method is proven to have higher accuracy than SVM and BPNN and can be applied for on-line PD monitoring of cable systems after training with valid sample data.

AB - This paper presents an effective, Rough Set (RS) based, pattern recognition method for rejecting interference signals and recognising Partial Discharge (PD) signals from different sources. Firstly, RS theory is presented in terms of Information System, Lower and Upper Approximation, Signal Discretisation, Attribute Reduction and a flowchart of the RS based pattern recognition method. Secondly, PD testing of five types of artificial defect in ethylene-propylene rubber (EPR) cable is carried out and data pre-processing and feature extraction are employed to separate PD and interference signals. Thirdly, the RS based PD signal recognition method is applied to 4000 samples and is proven to have 99% accuracy. Fourthly, the RS based PD recognition method is applied to signals from five different sources and an accuracy of more than 93% is attained when a combination of signal discretisation and attribute reduction methods are applied. Finally, Back-propagation Neural Network (BPNN) and Support Vector Machine (SVM) methods are studied and compared with the developed method. The proposed RS method is proven to have higher accuracy than SVM and BPNN and can be applied for on-line PD monitoring of cable systems after training with valid sample data.

KW - partial discharge

KW - pattern recognition

KW - signal discretisation

KW - rough set

KW - knowledge rule evaluation

KW - cable systems

UR - http://ieeexplore.ieee.org/document/7873470/

U2 - 10.1109/TDEI.2016.006060

DO - 10.1109/TDEI.2016.006060

M3 - Article

VL - 24

SP - 147

EP - 156

JO - IEEE Transactions on Dielectrics and Electrical Insulation

T2 - IEEE Transactions on Dielectrics and Electrical Insulation

JF - IEEE Transactions on Dielectrics and Electrical Insulation

SN - 1070-9878

IS - 1

ER -