Cover Image

Analysis of partial discharge measurement data using a support vector machine

This paper investigates the recognition of partial discharge sources by using a statistical learning theory, Support Vector Machine (SVM). SVM provides a new approach to pattern classification and has been proven to be successful in fields such as image identification and face recognition. To apply...

Full description

Saved in:
Bibliographic Details
Main Authors: Aziz N.F.A., Hao L., Lewin P.L.
Other Authors: 57221906825
Format: Conference Paper
Published: 2023
Subjects:
On-line monitoring
Partial discharge
Partial discharge classification
Pattern recognition
Support vector machine
Classification (of information)
Discharge (fluid mechanics)
Electric machine insulation
Face recognition
Feature extraction
Fluid mechanics
Frequency domain analysis
Image retrieval
Learning systems
Research and development management
Vectors
Partial discharges
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.uniten.dspace-29774
record_format dspace
spelling my.uniten.dspace-297742024-04-17T10:23:34Z Analysis of partial discharge measurement data using a support vector machine Aziz N.F.A. Hao L. Lewin P.L. 57221906825 14030216100 7102386669 On-line monitoring Partial discharge Partial discharge classification Pattern recognition Support vector machine Classification (of information) Discharge (fluid mechanics) Electric machine insulation Face recognition Feature extraction Fluid mechanics Frequency domain analysis Image retrieval Learning systems Research and development management Vectors On-line monitoring Partial discharge Partial discharge classification Pattern recognition Support vector machine Partial discharges This paper investigates the recognition of partial discharge sources by using a statistical learning theory, Support Vector Machine (SVM). SVM provides a new approach to pattern classification and has been proven to be successful in fields such as image identification and face recognition. To apply SVM learning in partial discharge classification, data input is very important. The input should be able to fully represent different patterns in an effective way. The determination of features that describe the characteristics of partial discharge signals and the extraction of reliable information from the raw data are the key to acquiring valuable patterns of partial discharge signals. In this paper, data obtained from experiment is carried out in both time and frequency domain. By using appropriate combination of kernel functions and parameters, it is concluded that the frequency domain approach gives a better classification rate. �2007 IEEE. Final 2023-12-28T08:57:37Z 2023-12-28T08:57:37Z 2007 Conference Paper 10.1109/SCORED.2007.4451430 2-s2.0-50449096613 https://www.scopus.com/inward/record.uri?eid=2-s2.0-50449096613&doi=10.1109%2fSCORED.2007.4451430&partnerID=40&md5=c9ad86601ddbe6a823dba52b4d5a1e19 https://irepository.uniten.edu.my/handle/123456789/29774 4451430 Scopus
institution Universiti Tenaga Nasional
building UNITEN Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Tenaga Nasional
content_source UNITEN Institutional Repository
url_provider http://dspace.uniten.edu.my/
topic On-line monitoring
Partial discharge
Partial discharge classification
Pattern recognition
Support vector machine
Classification (of information)
Discharge (fluid mechanics)
Electric machine insulation
Face recognition
Feature extraction
Fluid mechanics
Frequency domain analysis
Image retrieval
Learning systems
Research and development management
Vectors
On-line monitoring
Partial discharge
Partial discharge classification
Pattern recognition
Support vector machine
Partial discharges
spellingShingle On-line monitoring
Partial discharge
Partial discharge classification
Pattern recognition
Support vector machine
Classification (of information)
Discharge (fluid mechanics)
Electric machine insulation
Face recognition
Feature extraction
Fluid mechanics
Frequency domain analysis
Image retrieval
Learning systems
Research and development management
Vectors
On-line monitoring
Partial discharge
Partial discharge classification
Pattern recognition
Support vector machine
Partial discharges
Aziz N.F.A.
Hao L.
Lewin P.L.
Analysis of partial discharge measurement data using a support vector machine
description This paper investigates the recognition of partial discharge sources by using a statistical learning theory, Support Vector Machine (SVM). SVM provides a new approach to pattern classification and has been proven to be successful in fields such as image identification and face recognition. To apply SVM learning in partial discharge classification, data input is very important. The input should be able to fully represent different patterns in an effective way. The determination of features that describe the characteristics of partial discharge signals and the extraction of reliable information from the raw data are the key to acquiring valuable patterns of partial discharge signals. In this paper, data obtained from experiment is carried out in both time and frequency domain. By using appropriate combination of kernel functions and parameters, it is concluded that the frequency domain approach gives a better classification rate. �2007 IEEE.
author2 57221906825
author_facet 57221906825
Aziz N.F.A.
Hao L.
Lewin P.L.
format Conference Paper
author Aziz N.F.A.
Hao L.
Lewin P.L.
author_sort Aziz N.F.A.
title Analysis of partial discharge measurement data using a support vector machine
title_short Analysis of partial discharge measurement data using a support vector machine
title_full Analysis of partial discharge measurement data using a support vector machine
title_fullStr Analysis of partial discharge measurement data using a support vector machine
title_full_unstemmed Analysis of partial discharge measurement data using a support vector machine
title_sort analysis of partial discharge measurement data using a support vector machine
publishDate 2023
_version_ 1806428449906098176
score 13.211869

Similar Items