Classification of partial discharges in insulation materials via support vector machine and discrete wavelet transform
Long term partial discharges (PDs) within an insulation material of high voltage equipment can cause equipment failure. Thus, it is important to detect PDs within the insulation material and classify the PD type with high accuracy so that repair and maintenance can be performed effectively. In this...
Saved in:
Main Authors: | , , , , , |
---|---|
Format: | Conference or Workshop Item |
Language: | English |
Subjects: | |
Online Access: | http://eprints.um.edu.my/35253/1/Profesor%20madya%20Ir.%20Dr.%20Hazlee%20Azil%20bin%20Illias_Classification%20of%20Partial%20Discharges%20in%20Insulation.pdf http://eprints.um.edu.my/35253/ |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.um.eprints.35253 |
---|---|
record_format |
eprints |
spelling |
my.um.eprints.352532022-10-12T07:48:33Z http://eprints.um.edu.my/35253/ Classification of partial discharges in insulation materials via support vector machine and discrete wavelet transform Illias, Hazlee Azil Neoh, Ying Ting Ong, Zhen Yu Kando, Masaaki Mohd Ariffin, Azrul Mohd Yousof, Mohd Fairouz TK Electrical engineering. Electronics Nuclear engineering Long term partial discharges (PDs) within an insulation material of high voltage equipment can cause equipment failure. Thus, it is important to detect PDs within the insulation material and classify the PD type with high accuracy so that repair and maintenance can be performed effectively. In this work, three different types of PD, which include internal, surface and corona discharges, are measured from insulation materials. To evaluate the effect of noise on the PD measurement data, different levels of Additive White Gaussian Noise were added to the signals. Then, feature extractions were performed from the PD signals using Discrete Wavelet Transform (DWT). Different types of DWT families were used for feature extraction. The extracted features were then fed into support vector machine (SVM) for training and testing purposes. The classification accuracy of each test was recorded and compared. It was found that classification of PD signals using SVM as a classifier and DWT as a feature extraction yields reasonable classification accuracy results under different noise levels, which is in the range of 90%-99%. Conference or Workshop Item PeerReviewed text en http://eprints.um.edu.my/35253/1/Profesor%20madya%20Ir.%20Dr.%20Hazlee%20Azil%20bin%20Illias_Classification%20of%20Partial%20Discharges%20in%20Insulation.pdf Illias, Hazlee Azil and Neoh, Ying Ting and Ong, Zhen Yu and Kando, Masaaki and Mohd Ariffin, Azrul and Mohd Yousof, Mohd Fairouz Classification of partial discharges in insulation materials via support vector machine and discrete wavelet transform. In: 2021 International Conference on the Properties and Applications of Dielectric Materials, 12-14 July 2021, Kuala Lumpur. (Submitted) |
institution |
Universiti Malaya |
building |
UM Library |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Malaya |
content_source |
UM Research Repository |
url_provider |
http://eprints.um.edu.my/ |
language |
English |
topic |
TK Electrical engineering. Electronics Nuclear engineering |
spellingShingle |
TK Electrical engineering. Electronics Nuclear engineering Illias, Hazlee Azil Neoh, Ying Ting Ong, Zhen Yu Kando, Masaaki Mohd Ariffin, Azrul Mohd Yousof, Mohd Fairouz Classification of partial discharges in insulation materials via support vector machine and discrete wavelet transform |
description |
Long term partial discharges (PDs) within an insulation material of high voltage equipment can cause equipment failure. Thus, it is important to detect PDs within the insulation material and classify the PD type with high accuracy so that repair and maintenance can be performed effectively. In this work, three different types of PD, which include internal, surface and corona discharges, are measured from insulation materials. To evaluate the effect of noise on the PD measurement data, different levels of Additive White Gaussian Noise were added to the signals. Then, feature extractions were performed from the PD signals using Discrete Wavelet Transform (DWT). Different types of DWT families were used for feature extraction. The extracted features were then fed into support vector machine (SVM) for training and testing purposes. The classification accuracy of each test was recorded and compared. It was found that classification of PD signals using SVM as a classifier and DWT as a feature extraction yields reasonable classification accuracy results under different noise levels, which is in the range of 90%-99%. |
format |
Conference or Workshop Item |
author |
Illias, Hazlee Azil Neoh, Ying Ting Ong, Zhen Yu Kando, Masaaki Mohd Ariffin, Azrul Mohd Yousof, Mohd Fairouz |
author_facet |
Illias, Hazlee Azil Neoh, Ying Ting Ong, Zhen Yu Kando, Masaaki Mohd Ariffin, Azrul Mohd Yousof, Mohd Fairouz |
author_sort |
Illias, Hazlee Azil |
title |
Classification of partial discharges in insulation materials via support vector machine and discrete wavelet transform |
title_short |
Classification of partial discharges in insulation materials via support vector machine and discrete wavelet transform |
title_full |
Classification of partial discharges in insulation materials via support vector machine and discrete wavelet transform |
title_fullStr |
Classification of partial discharges in insulation materials via support vector machine and discrete wavelet transform |
title_full_unstemmed |
Classification of partial discharges in insulation materials via support vector machine and discrete wavelet transform |
title_sort |
classification of partial discharges in insulation materials via support vector machine and discrete wavelet transform |
url |
http://eprints.um.edu.my/35253/1/Profesor%20madya%20Ir.%20Dr.%20Hazlee%20Azil%20bin%20Illias_Classification%20of%20Partial%20Discharges%20in%20Insulation.pdf http://eprints.um.edu.my/35253/ |
_version_ |
1748181066752983040 |
score |
13.15806 |