Entropy-based feature extraction for electromagnetic discharges classification in high-voltage power generation

Imene Mitiche, Gordon Morison, Alan Nesbitt, Brian G. Stewart, Philip Boreham

Research output: Contribution to journalArticle

21 Downloads (Pure)

Abstract

This work exploits four entropy measures known as Sample, Permutation, Weighted Permutation, and Dispersion Entropy to extract relevant information from Electromagnetic Interference (EMI) discharge signals that are useful in fault diagnosis of High-Voltage (HV) equipment. Multi-class classification algorithms are used to classify or distinguish between various discharge sources such as Partial Discharges (PD), Exciter, Arcing, micro Sparking and Random Noise. The signals were measured and recorded on different sites followed by EMI expert’s data analysis in order to identify and label the discharge source type contained within the signal. The classification was performed both within each site and across all sites. The system performs well for both cases with extremely high classification accuracy within site. This work demonstrates the ability to extract relevant entropy-based features from EMI discharge sources from time-resolved signals requiring minimal computation making the system ideal for a potential application to online condition monitoring based on EMI.
Original languageEnglish
Article number549
JournalEntropy
Volume20
Issue number8
DOIs
Publication statusPublished - 25 Jul 2018

Fingerprint

pattern recognition
electromagnetic interference
high voltages
entropy
electromagnetism
permutations
time signals
random noise

Keywords

  • EMI measurement
  • partial discharge
  • entropy
  • classification

Cite this

@article{f137c289ac0a464f879ffce37b16e597,
title = "Entropy-based feature extraction for electromagnetic discharges classification in high-voltage power generation",
abstract = "This work exploits four entropy measures known as Sample, Permutation, Weighted Permutation, and Dispersion Entropy to extract relevant information from Electromagnetic Interference (EMI) discharge signals that are useful in fault diagnosis of High-Voltage (HV) equipment. Multi-class classification algorithms are used to classify or distinguish between various discharge sources such as Partial Discharges (PD), Exciter, Arcing, micro Sparking and Random Noise. The signals were measured and recorded on different sites followed by EMI expert’s data analysis in order to identify and label the discharge source type contained within the signal. The classification was performed both within each site and across all sites. The system performs well for both cases with extremely high classification accuracy within site. This work demonstrates the ability to extract relevant entropy-based features from EMI discharge sources from time-resolved signals requiring minimal computation making the system ideal for a potential application to online condition monitoring based on EMI.",
keywords = "EMI measurement, partial discharge, entropy, classification",
author = "Imene Mitiche and Gordon Morison and Alan Nesbitt and Stewart, {Brian G.} and Philip Boreham",
note = "Acceptance from webpage OA article",
year = "2018",
month = "7",
day = "25",
doi = "10.3390/e20080549",
language = "English",
volume = "20",
journal = "Entropy",
issn = "1099-4300",
publisher = "MDPI",
number = "8",

}

Entropy-based feature extraction for electromagnetic discharges classification in high-voltage power generation. / Mitiche, Imene; Morison, Gordon; Nesbitt, Alan; Stewart, Brian G.; Boreham, Philip .

In: Entropy, Vol. 20, No. 8, 549, 25.07.2018.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Entropy-based feature extraction for electromagnetic discharges classification in high-voltage power generation

AU - Mitiche, Imene

AU - Morison, Gordon

AU - Nesbitt, Alan

AU - Stewart, Brian G.

AU - Boreham, Philip

N1 - Acceptance from webpage OA article

PY - 2018/7/25

Y1 - 2018/7/25

N2 - This work exploits four entropy measures known as Sample, Permutation, Weighted Permutation, and Dispersion Entropy to extract relevant information from Electromagnetic Interference (EMI) discharge signals that are useful in fault diagnosis of High-Voltage (HV) equipment. Multi-class classification algorithms are used to classify or distinguish between various discharge sources such as Partial Discharges (PD), Exciter, Arcing, micro Sparking and Random Noise. The signals were measured and recorded on different sites followed by EMI expert’s data analysis in order to identify and label the discharge source type contained within the signal. The classification was performed both within each site and across all sites. The system performs well for both cases with extremely high classification accuracy within site. This work demonstrates the ability to extract relevant entropy-based features from EMI discharge sources from time-resolved signals requiring minimal computation making the system ideal for a potential application to online condition monitoring based on EMI.

AB - This work exploits four entropy measures known as Sample, Permutation, Weighted Permutation, and Dispersion Entropy to extract relevant information from Electromagnetic Interference (EMI) discharge signals that are useful in fault diagnosis of High-Voltage (HV) equipment. Multi-class classification algorithms are used to classify or distinguish between various discharge sources such as Partial Discharges (PD), Exciter, Arcing, micro Sparking and Random Noise. The signals were measured and recorded on different sites followed by EMI expert’s data analysis in order to identify and label the discharge source type contained within the signal. The classification was performed both within each site and across all sites. The system performs well for both cases with extremely high classification accuracy within site. This work demonstrates the ability to extract relevant entropy-based features from EMI discharge sources from time-resolved signals requiring minimal computation making the system ideal for a potential application to online condition monitoring based on EMI.

KW - EMI measurement

KW - partial discharge

KW - entropy

KW - classification

U2 - 10.3390/e20080549

DO - 10.3390/e20080549

M3 - Article

VL - 20

JO - Entropy

JF - Entropy

SN - 1099-4300

IS - 8

M1 - 549

ER -