Deep residual neural network for EMI event classification using bispectrum representation

Imene Mitiche; Mark David Jenkins; Philip  Boreham; Alan Nesbitt; Brian G. Stewart; Gordon Morison

doi:10.23919/EUSIPCO.2018.8553177

Deep residual neural network for EMI event classification using bispectrum representation

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

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

41 Downloads (Pure)

Abstract

This paper presents a novel method for condition monitoring of High Voltage (HV) power plant equipment through analysis of discharge signals. These discharge signals are measured using the Electromagnetic Interference (EMI) method and processed using third order Higher-Order Statistics (HOS) to obtain a Bispectrum representation. By mapping the time-domain signal to a Bispectrum image representations the problem can be approached as an image classification task. This allows for the novel application of a Deep Residual Neural Network (ResNet) to
the classification of HV discharge signals. The network is trained on signals into 9 classes and achieves high classification accuracy in each category, improving upon our previous work on this task.

Original language	English
Title of host publication	2018 26th European Signal Processing Conference (EUSIPCO)
Publisher	IEEE
Pages	186-190
Number of pages	5
ISBN (Electronic)	9789082797015
ISBN (Print)	9781538637364
DOIs	https://doi.org/10.23919/EUSIPCO.2018.8553177
Publication status	Published - 3 Dec 2018

Publication series

Name
ISSN (Electronic)	2076-1465

Keywords

residual neural network
EMI measurement
electromagnetic interference
partial discharges
discharges (electric)
feature extraction
fault location
signal processing

Documents and Links

10.23919/EUSIPCO.2018.8553177

Mitiche, I. et al (2018) Deep Residual Neural Network for EMI Event Classification Using Bispectrum Representations
Copyright © 2018 IEEE. This is a post-peer review, pre-copy edited version of the article and may differ slightly from the final published version of the work. This work is made available in line with the publisher policy. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, 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 components of this work in other works.
Accepted author manuscript, 1.89 MB

Fingerprint Dive into the research topics of 'Deep residual neural network for EMI event classification using bispectrum representation'. Together they form a unique fingerprint.

Alan Nesbitt
- ane2@gcu.ac.uk
- Department of Electrical and Electronic Engineering - Head of Department
Person

Cite this

@inproceedings{c88d703b2b764feaa73ddc9f7df81ef0,

title = "Deep residual neural network for EMI event classification using bispectrum representation",

abstract = "This paper presents a novel method for condition monitoring of High Voltage (HV) power plant equipment through analysis of discharge signals. These discharge signals are measured using the Electromagnetic Interference (EMI) method and processed using third order Higher-Order Statistics (HOS) to obtain a Bispectrum representation. By mapping the time-domain signal to a Bispectrum image representations the problem can be approached as an image classification task. This allows for the novel application of a Deep Residual Neural Network (ResNet) tothe classification of HV discharge signals. The network is trained on signals into 9 classes and achieves high classification accuracy in each category, improving upon our previous work on this task.",

keywords = "residual neural network, EMI measurement, electromagnetic interference, partial discharges, discharges (electric), feature extraction, fault location, signal processing",

author = "Imene Mitiche and Jenkins, {Mark David} and Philip Boreham and Alan Nesbitt and Stewart, {Brian G.} and Gordon Morison",

note = "Acceptance in SAN AAM: no embargo No ISSN found for output, out of policy scope. ST 13/11/19",

year = "2018",

month = dec,

day = "3",

doi = "10.23919/EUSIPCO.2018.8553177",

language = "English",

isbn = "9781538637364",

publisher = "IEEE",

pages = "186--190",

booktitle = "2018 26th European Signal Processing Conference (EUSIPCO)",

}

Deep residual neural network for EMI event classification using bispectrum representation. / Mitiche, Imene; Jenkins, Mark David; Boreham, Philip ; Nesbitt, Alan; Stewart, Brian G.; Morison, Gordon.

2018 26th European Signal Processing Conference (EUSIPCO). IEEE, 2018. p. 186-190.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Deep residual neural network for EMI event classification using bispectrum representation

AU - Mitiche, Imene

AU - Jenkins, Mark David

AU - Boreham, Philip

AU - Nesbitt, Alan

AU - Stewart, Brian G.

AU - Morison, Gordon

N1 - Acceptance in SAN AAM: no embargo No ISSN found for output, out of policy scope. ST 13/11/19

PY - 2018/12/3

Y1 - 2018/12/3

N2 - This paper presents a novel method for condition monitoring of High Voltage (HV) power plant equipment through analysis of discharge signals. These discharge signals are measured using the Electromagnetic Interference (EMI) method and processed using third order Higher-Order Statistics (HOS) to obtain a Bispectrum representation. By mapping the time-domain signal to a Bispectrum image representations the problem can be approached as an image classification task. This allows for the novel application of a Deep Residual Neural Network (ResNet) tothe classification of HV discharge signals. The network is trained on signals into 9 classes and achieves high classification accuracy in each category, improving upon our previous work on this task.

AB - This paper presents a novel method for condition monitoring of High Voltage (HV) power plant equipment through analysis of discharge signals. These discharge signals are measured using the Electromagnetic Interference (EMI) method and processed using third order Higher-Order Statistics (HOS) to obtain a Bispectrum representation. By mapping the time-domain signal to a Bispectrum image representations the problem can be approached as an image classification task. This allows for the novel application of a Deep Residual Neural Network (ResNet) tothe classification of HV discharge signals. The network is trained on signals into 9 classes and achieves high classification accuracy in each category, improving upon our previous work on this task.

KW - residual neural network

KW - EMI measurement

KW - electromagnetic interference

KW - partial discharges

KW - discharges (electric)

KW - feature extraction

KW - fault location

KW - signal processing

U2 - 10.23919/EUSIPCO.2018.8553177

DO - 10.23919/EUSIPCO.2018.8553177

M3 - Conference contribution

SN - 9781538637364

SP - 186

EP - 190

BT - 2018 26th European Signal Processing Conference (EUSIPCO)

PB - IEEE

ER -