Classification of Power Quality Disturbances Using Wigner-Ville Distribution and Deep Convolutional Neural Networks
This paper proposes a hybrid approach combining Wigner-Ville distribution (WVD) with convolutional neural network (CNN) for power quality disturbance (PQD) classification. Firstly, a WVD technique is developed to transfer a 1D voltage disturbance signal into a 2D image file, followed by a CNN model...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2019-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/8811462/ |
_version_ | 1818936357054054400 |
---|---|
author | Kewei Cai Wenping Cao Lassi Aarniovuori Hongshuai Pang Yuanshan Lin Guofeng Li |
author_facet | Kewei Cai Wenping Cao Lassi Aarniovuori Hongshuai Pang Yuanshan Lin Guofeng Li |
author_sort | Kewei Cai |
collection | DOAJ |
description | This paper proposes a hybrid approach combining Wigner-Ville distribution (WVD) with convolutional neural network (CNN) for power quality disturbance (PQD) classification. Firstly, a WVD technique is developed to transfer a 1D voltage disturbance signal into a 2D image file, followed by a CNN model developed for the image classification. Then, the feature maps are extracted automatically from the image file and different patterns are extracted from variables on CNN. A set of synthetic signals, as well as real-world measurement data, are used to test the proposed method. The high classification accuracy of test results is achieved to confirm the effectiveness of the proposed method. Furthermore, the model is simplified and optimized by visualizing the output of convolutional layers. On this basis, one visualizing technique called the class activation map (CAM) is used to identify the location and shape of “hotspots (PQDs)”. The effect of incorrect classification of the model is analyzed with the CAM. Therefore, the proposed method is proved to have the capability of providing necessary and accurate information for PQDs, which will then be used to determine the subsequent PQ remedy actions accordingly. |
first_indexed | 2024-12-20T05:34:46Z |
format | Article |
id | doaj.art-8d9a783457a743a68742cc7e3134683f |
institution | Directory Open Access Journal |
issn | 2169-3536 |
language | English |
last_indexed | 2024-12-20T05:34:46Z |
publishDate | 2019-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Access |
spelling | doaj.art-8d9a783457a743a68742cc7e3134683f2022-12-21T19:51:39ZengIEEEIEEE Access2169-35362019-01-01711909911910910.1109/ACCESS.2019.29371938811462Classification of Power Quality Disturbances Using Wigner-Ville Distribution and Deep Convolutional Neural NetworksKewei Cai0https://orcid.org/0000-0003-4144-3898Wenping Cao1https://orcid.org/0000-0002-8133-3020Lassi Aarniovuori2Hongshuai Pang3Yuanshan Lin4Guofeng Li5https://orcid.org/0000-0002-6687-112XCollege of Information Engineering, Dalian Ocean University, Dalian, ChinaCollege of Electrical and Power Engineering, Taiyuan University of Technology, Taiyuan, ChinaLUT School of Energy Systems, LUT University, Lappeenranta, FinlandCollege of Information Engineering, Dalian Ocean University, Dalian, ChinaCollege of Information Engineering, Dalian Ocean University, Dalian, ChinaSchool of Electrical Engineering, Dalian University of Technology, Dalian, ChinaThis paper proposes a hybrid approach combining Wigner-Ville distribution (WVD) with convolutional neural network (CNN) for power quality disturbance (PQD) classification. Firstly, a WVD technique is developed to transfer a 1D voltage disturbance signal into a 2D image file, followed by a CNN model developed for the image classification. Then, the feature maps are extracted automatically from the image file and different patterns are extracted from variables on CNN. A set of synthetic signals, as well as real-world measurement data, are used to test the proposed method. The high classification accuracy of test results is achieved to confirm the effectiveness of the proposed method. Furthermore, the model is simplified and optimized by visualizing the output of convolutional layers. On this basis, one visualizing technique called the class activation map (CAM) is used to identify the location and shape of “hotspots (PQDs)”. The effect of incorrect classification of the model is analyzed with the CAM. Therefore, the proposed method is proved to have the capability of providing necessary and accurate information for PQDs, which will then be used to determine the subsequent PQ remedy actions accordingly.https://ieeexplore.ieee.org/document/8811462/Classificationconvolutional neural network (CNN)deep learningpower quality disturbancespower systemsWigner-Ville distribution (WVD) |
spellingShingle | Kewei Cai Wenping Cao Lassi Aarniovuori Hongshuai Pang Yuanshan Lin Guofeng Li Classification of Power Quality Disturbances Using Wigner-Ville Distribution and Deep Convolutional Neural Networks IEEE Access Classification convolutional neural network (CNN) deep learning power quality disturbances power systems Wigner-Ville distribution (WVD) |
title | Classification of Power Quality Disturbances Using Wigner-Ville Distribution and Deep Convolutional Neural Networks |
title_full | Classification of Power Quality Disturbances Using Wigner-Ville Distribution and Deep Convolutional Neural Networks |
title_fullStr | Classification of Power Quality Disturbances Using Wigner-Ville Distribution and Deep Convolutional Neural Networks |
title_full_unstemmed | Classification of Power Quality Disturbances Using Wigner-Ville Distribution and Deep Convolutional Neural Networks |
title_short | Classification of Power Quality Disturbances Using Wigner-Ville Distribution and Deep Convolutional Neural Networks |
title_sort | classification of power quality disturbances using wigner ville distribution and deep convolutional neural networks |
topic | Classification convolutional neural network (CNN) deep learning power quality disturbances power systems Wigner-Ville distribution (WVD) |
url | https://ieeexplore.ieee.org/document/8811462/ |
work_keys_str_mv | AT keweicai classificationofpowerqualitydisturbancesusingwignervilledistributionanddeepconvolutionalneuralnetworks AT wenpingcao classificationofpowerqualitydisturbancesusingwignervilledistributionanddeepconvolutionalneuralnetworks AT lassiaarniovuori classificationofpowerqualitydisturbancesusingwignervilledistributionanddeepconvolutionalneuralnetworks AT hongshuaipang classificationofpowerqualitydisturbancesusingwignervilledistributionanddeepconvolutionalneuralnetworks AT yuanshanlin classificationofpowerqualitydisturbancesusingwignervilledistributionanddeepconvolutionalneuralnetworks AT guofengli classificationofpowerqualitydisturbancesusingwignervilledistributionanddeepconvolutionalneuralnetworks |