An image-based deep transfer learning approach to classify power quality disturbances

Todeschini, Grazia; Kheta, Karan; Giannetti, Cinzia

doi:10.1016/j.epsr.2022.108795

Journal article 507 views 52 downloads

An image-based deep transfer learning approach to classify power quality disturbances

Grazia Todeschini

, Karan Kheta, Cinzia Giannetti

Electric Power Systems Research, Volume: 213, Start page: 108795

Swansea University Authors: Karan Kheta, Cinzia Giannetti

PDF | Version of Record

© 2022 The Author(s). This is an open access article under the CC BY license
Download (5.44MB)

Check full text

DOI (Published version): 10.1016/j.epsr.2022.108795

Abstract

Power quality disturbances (PQDs) consist in deviation of voltage and current waveforms from the ideal sinusoid at fundamental frequency, and need to be monitored to ensure a reliabile electrical supply. While, traditionally, power quality monitoring has been performed using signal processing techni...

Full description

Published in:	Electric Power Systems Research
ISSN:	0378-7796
Published:	Elsevier BV 2022
Online Access:	Check full text
URI:	https://cronfa.swan.ac.uk/Record/cronfa61303
Tags:	Add Tag No Tags, Be the first to tag this record!

first_indexed	2022-09-27T16:14:55Z
last_indexed	2023-01-13T19:21:59Z
id	cronfa61303
recordtype	SURis
fullrecord	<?xml version="1.0"?><rfc1807><datestamp>2022-10-12T12:36:12.2965600</datestamp><bib-version>v2</bib-version><id>61303</id><entry>2022-09-22</entry><title>An image-based deep transfer learning approach to classify power quality disturbances</title><swanseaauthors><author><sid>8dee4b792e2ff0fd2aa26c0b55b32251</sid><firstname>Karan</firstname><surname>Kheta</surname><name>Karan Kheta</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>a8d947a38cb58a8d2dfe6f50cb7eb1c6</sid><ORCID>0000-0003-0339-5872</ORCID><firstname>Cinzia</firstname><surname>Giannetti</surname><name>Cinzia Giannetti</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2022-09-22</date><deptcode>EEN</deptcode><abstract>Power quality disturbances (PQDs) consist in deviation of voltage and current waveforms from the ideal sinusoid at fundamental frequency, and need to be monitored to ensure a reliabile electrical supply. While, traditionally, power quality monitoring has been performed using signal processing techniques, coupled with shallow Machine Learning classifiers or wave change detection methods, more recently, new approaches, based on Deep Learning, have been proposed. These methods have the potential to achieve high classification accuracy and to remove the need of extensive data pre-processing, hence being more suitable for real-time deployments. However, high classification performance has been only demonstrated using synthetically generated data. In order to address limitations related to processing time and accuracy, this paper proposes a novel end-to-end framework for automated detection of PQDs based on Deep Transfer Learning. The proposed approach uses a small set of images of voltage waveforms to train the model and classify different types of PQDs. This method leverages on the high performance of existing pre-trained models for image classification and shows consistent high accuracy for data with varying resolution. The proposed methodology provides a pathway towards effective deployment of Deep Learning in power quality monitoring systems and real-time applications.</abstract><type>Journal Article</type><journal>Electric Power Systems Research</journal><volume>213</volume><journalNumber/><paginationStart>108795</paginationStart><paginationEnd/><publisher>Elsevier BV</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>0378-7796</issnPrint><issnElectronic/><keywords>Convolutional neural networks; Power quality disturbance; Power quality; Monitoring; Transfer learning; Voltage sag; Voltage swell</keywords><publishedDay>1</publishedDay><publishedMonth>12</publishedMonth><publishedYear>2022</publishedYear><publishedDate>2022-12-01</publishedDate><doi>10.1016/j.epsr.2022.108795</doi><url/><notes/><college>COLLEGE NANME</college><department>Engineering</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>EEN</DepartmentCode><institution>Swansea University</institution><apcterm/><funders>Dr Todeschini and Dr Giannetti are supported by the UK Engineering and Physical Sciences Research Council (EPSRC) (EP/T013206/2; EP/S001387/1; EP/V061798/1). All authors would like to acknowledge the support of the IMPACT project, part-funded by the European Regional Development Fund (ERDF) via the Welsh Government. Dr Giannetti would like to acknowledge the support of AccelerateAI, part-funded by the ERDF via the Welsh Government.</funders><projectreference/><lastEdited>2022-10-12T12:36:12.2965600</lastEdited><Created>2022-09-22T15:42:22.9342596</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Mechanical Engineering</level></path><authors><author><firstname>Grazia</firstname><surname>Todeschini</surname><orcid>0000-0001-9411-0726</orcid><order>1</order></author><author><firstname>Karan</firstname><surname>Kheta</surname><order>2</order></author><author><firstname>Cinzia</firstname><surname>Giannetti</surname><orcid>0000-0003-0339-5872</orcid><order>3</order></author></authors><documents><document><filename>61303__25421__7b033abe964645929b61787de4619083.pdf</filename><originalFilename>61303_VoR.pdf</originalFilename><uploaded>2022-10-12T12:32:19.5883818</uploaded><type>Output</type><contentLength>5703603</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>© 2022 The Author(s). This is an open access article under the CC BY license</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>http://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling	2022-10-12T12:36:12.2965600 v2 61303 2022-09-22 An image-based deep transfer learning approach to classify power quality disturbances 8dee4b792e2ff0fd2aa26c0b55b32251 Karan Kheta Karan Kheta true false a8d947a38cb58a8d2dfe6f50cb7eb1c6 0000-0003-0339-5872 Cinzia Giannetti Cinzia Giannetti true false 2022-09-22 EEN Power quality disturbances (PQDs) consist in deviation of voltage and current waveforms from the ideal sinusoid at fundamental frequency, and need to be monitored to ensure a reliabile electrical supply. While, traditionally, power quality monitoring has been performed using signal processing techniques, coupled with shallow Machine Learning classifiers or wave change detection methods, more recently, new approaches, based on Deep Learning, have been proposed. These methods have the potential to achieve high classification accuracy and to remove the need of extensive data pre-processing, hence being more suitable for real-time deployments. However, high classification performance has been only demonstrated using synthetically generated data. In order to address limitations related to processing time and accuracy, this paper proposes a novel end-to-end framework for automated detection of PQDs based on Deep Transfer Learning. The proposed approach uses a small set of images of voltage waveforms to train the model and classify different types of PQDs. This method leverages on the high performance of existing pre-trained models for image classification and shows consistent high accuracy for data with varying resolution. The proposed methodology provides a pathway towards effective deployment of Deep Learning in power quality monitoring systems and real-time applications. Journal Article Electric Power Systems Research 213 108795 Elsevier BV 0378-7796 Convolutional neural networks; Power quality disturbance; Power quality; Monitoring; Transfer learning; Voltage sag; Voltage swell 1 12 2022 2022-12-01 10.1016/j.epsr.2022.108795 COLLEGE NANME Engineering COLLEGE CODE EEN Swansea University Dr Todeschini and Dr Giannetti are supported by the UK Engineering and Physical Sciences Research Council (EPSRC) (EP/T013206/2; EP/S001387/1; EP/V061798/1). All authors would like to acknowledge the support of the IMPACT project, part-funded by the European Regional Development Fund (ERDF) via the Welsh Government. Dr Giannetti would like to acknowledge the support of AccelerateAI, part-funded by the ERDF via the Welsh Government. 2022-10-12T12:36:12.2965600 2022-09-22T15:42:22.9342596 Faculty of Science and Engineering School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Mechanical Engineering Grazia Todeschini 0000-0001-9411-0726 1 Karan Kheta 2 Cinzia Giannetti 0000-0003-0339-5872 3 61303__25421__7b033abe964645929b61787de4619083.pdf 61303_VoR.pdf 2022-10-12T12:32:19.5883818 Output 5703603 application/pdf Version of Record true © 2022 The Author(s). This is an open access article under the CC BY license true eng http://creativecommons.org/licenses/by/4.0/
title	An image-based deep transfer learning approach to classify power quality disturbances
spellingShingle	An image-based deep transfer learning approach to classify power quality disturbances Karan Kheta Cinzia Giannetti
title_short	An image-based deep transfer learning approach to classify power quality disturbances
title_full	An image-based deep transfer learning approach to classify power quality disturbances
title_fullStr	An image-based deep transfer learning approach to classify power quality disturbances
title_full_unstemmed	An image-based deep transfer learning approach to classify power quality disturbances
title_sort	An image-based deep transfer learning approach to classify power quality disturbances
author_id_str_mv	8dee4b792e2ff0fd2aa26c0b55b32251 a8d947a38cb58a8d2dfe6f50cb7eb1c6
author_id_fullname_str_mv	8dee4b792e2ff0fd2aa26c0b55b32251_*_Karan Kheta a8d947a38cb58a8d2dfe6f50cb7eb1c6_*_Cinzia Giannetti
author	Karan Kheta Cinzia Giannetti
author2	Grazia Todeschini Karan Kheta Cinzia Giannetti
format	Journal article
container_title	Electric Power Systems Research
container_volume	213
container_start_page	108795
publishDate	2022
institution	Swansea University
issn	0378-7796
doi_str_mv	10.1016/j.epsr.2022.108795
publisher	Elsevier BV
college_str	Faculty of Science and Engineering
hierarchytype
hierarchy_top_id	facultyofscienceandengineering
hierarchy_top_title	Faculty of Science and Engineering
hierarchy_parent_id	facultyofscienceandengineering
hierarchy_parent_title	Faculty of Science and Engineering
department_str	School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Mechanical Engineering{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Mechanical Engineering
document_store_str	1
active_str	0
description	Power quality disturbances (PQDs) consist in deviation of voltage and current waveforms from the ideal sinusoid at fundamental frequency, and need to be monitored to ensure a reliabile electrical supply. While, traditionally, power quality monitoring has been performed using signal processing techniques, coupled with shallow Machine Learning classifiers or wave change detection methods, more recently, new approaches, based on Deep Learning, have been proposed. These methods have the potential to achieve high classification accuracy and to remove the need of extensive data pre-processing, hence being more suitable for real-time deployments. However, high classification performance has been only demonstrated using synthetically generated data. In order to address limitations related to processing time and accuracy, this paper proposes a novel end-to-end framework for automated detection of PQDs based on Deep Transfer Learning. The proposed approach uses a small set of images of voltage waveforms to train the model and classify different types of PQDs. This method leverages on the high performance of existing pre-trained models for image classification and shows consistent high accuracy for data with varying resolution. The proposed methodology provides a pathway towards effective deployment of Deep Learning in power quality monitoring systems and real-time applications.
published_date	2022-12-01T04:20:03Z
_version_	1763754328077631488
score	11.012678

An image-based deep transfer learning approach to classify power quality disturbances

Similar Items