Classification of multiple electromagnetic interference events in high voltage power plant

Imene Mitiche, Gordon Morison, Alan Nesbitt, Michael Hughes-Narborough, Brian G. Stewart, Philip Boreham

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

2 Downloads (Pure)

Abstract

This paper addresses condition assessment of electrical assets contained in high voltage power plants. Our work introduces a novel analysis approach of multiple event signals related to faults, and which are measured using Electro-Magnetic Interference method. The proposed method transfers the expert’s knowledge on events presence in the signals to an intelligent system which could potentially be used for automatic EMI diagnosis. Cyclic spectrum analysis is used as feature extraction to efficiently extract the repetitive rate and the dynamic discharge level of the events, and multi-class support vector machine is adopted for their classification. This first and novel method achieved successful results which may have potential implications on developing a framework for automatic diagnosis tool of EMI events.
Original languageEnglish
Title of host publication53rd International Universities Power Engineering Conference
Place of PublicationPiscataway, N.J.
PublisherIEEE
Number of pages4
Publication statusAccepted/In press - 11 Jul 2018
Event53rd International Universities Power Engineering Conference - Glasgow Caledonian University, Glasgow, United Kingdom
Duration: 4 Sep 20187 Sep 2018
Conference number: 53rd
http://www.upec2018.com/

Conference

Conference53rd International Universities Power Engineering Conference
Abbreviated titleUPEC 2018
CountryUnited Kingdom
CityGlasgow
Period4/09/187/09/18
Internet address

Fingerprint

Signal interference
Power plants
Electric potential
Intelligent systems
Spectrum analysis
Support vector machines
Feature extraction

Keywords

  • electrical condition assessment
  • electro-magnetic interference
  • partial discharge
  • expert system
  • pattern recognition

Cite this

Mitiche, I., Morison, G., Nesbitt, A., Hughes-Narborough, M., Stewart, B. G., & Boreham, P. (Accepted/In press). Classification of multiple electromagnetic interference events in high voltage power plant. In 53rd International Universities Power Engineering Conference Piscataway, N.J.: IEEE.
Mitiche, Imene ; Morison, Gordon ; Nesbitt, Alan ; Hughes-Narborough, Michael ; Stewart, Brian G. ; Boreham, Philip. / Classification of multiple electromagnetic interference events in high voltage power plant. 53rd International Universities Power Engineering Conference. Piscataway, N.J. : IEEE, 2018.
@inproceedings{33deb6fa430c440fb7f9e6b962b817ab,
title = "Classification of multiple electromagnetic interference events in high voltage power plant",
abstract = "This paper addresses condition assessment of electrical assets contained in high voltage power plants. Our work introduces a novel analysis approach of multiple event signals related to faults, and which are measured using Electro-Magnetic Interference method. The proposed method transfers the expert’s knowledge on events presence in the signals to an intelligent system which could potentially be used for automatic EMI diagnosis. Cyclic spectrum analysis is used as feature extraction to efficiently extract the repetitive rate and the dynamic discharge level of the events, and multi-class support vector machine is adopted for their classification. This first and novel method achieved successful results which may have potential implications on developing a framework for automatic diagnosis tool of EMI events.",
keywords = "electrical condition assessment, electro-magnetic interference, partial discharge, expert system, pattern recognition",
author = "Imene Mitiche and Gordon Morison and Alan Nesbitt and Michael Hughes-Narborough and Stewart, {Brian G.} and Philip Boreham",
year = "2018",
month = "7",
day = "11",
language = "English",
booktitle = "53rd International Universities Power Engineering Conference",
publisher = "IEEE",

}

Mitiche, I, Morison, G, Nesbitt, A, Hughes-Narborough, M, Stewart, BG & Boreham, P 2018, Classification of multiple electromagnetic interference events in high voltage power plant. in 53rd International Universities Power Engineering Conference. IEEE, Piscataway, N.J., 53rd International Universities Power Engineering Conference, Glasgow, United Kingdom, 4/09/18.

Classification of multiple electromagnetic interference events in high voltage power plant. / Mitiche, Imene; Morison, Gordon; Nesbitt, Alan; Hughes-Narborough, Michael; Stewart, Brian G.; Boreham, Philip.

53rd International Universities Power Engineering Conference. Piscataway, N.J. : IEEE, 2018.

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

TY - GEN

T1 - Classification of multiple electromagnetic interference events in high voltage power plant

AU - Mitiche, Imene

AU - Morison, Gordon

AU - Nesbitt, Alan

AU - Hughes-Narborough, Michael

AU - Stewart, Brian G.

AU - Boreham, Philip

PY - 2018/7/11

Y1 - 2018/7/11

N2 - This paper addresses condition assessment of electrical assets contained in high voltage power plants. Our work introduces a novel analysis approach of multiple event signals related to faults, and which are measured using Electro-Magnetic Interference method. The proposed method transfers the expert’s knowledge on events presence in the signals to an intelligent system which could potentially be used for automatic EMI diagnosis. Cyclic spectrum analysis is used as feature extraction to efficiently extract the repetitive rate and the dynamic discharge level of the events, and multi-class support vector machine is adopted for their classification. This first and novel method achieved successful results which may have potential implications on developing a framework for automatic diagnosis tool of EMI events.

AB - This paper addresses condition assessment of electrical assets contained in high voltage power plants. Our work introduces a novel analysis approach of multiple event signals related to faults, and which are measured using Electro-Magnetic Interference method. The proposed method transfers the expert’s knowledge on events presence in the signals to an intelligent system which could potentially be used for automatic EMI diagnosis. Cyclic spectrum analysis is used as feature extraction to efficiently extract the repetitive rate and the dynamic discharge level of the events, and multi-class support vector machine is adopted for their classification. This first and novel method achieved successful results which may have potential implications on developing a framework for automatic diagnosis tool of EMI events.

KW - electrical condition assessment

KW - electro-magnetic interference

KW - partial discharge

KW - expert system

KW - pattern recognition

UR - http://www.upec2018.com/

M3 - Conference contribution book

BT - 53rd International Universities Power Engineering Conference

PB - IEEE

CY - Piscataway, N.J.

ER -

Mitiche I, Morison G, Nesbitt A, Hughes-Narborough M, Stewart BG, Boreham P. Classification of multiple electromagnetic interference events in high voltage power plant. In 53rd International Universities Power Engineering Conference. Piscataway, N.J.: IEEE. 2018