YOLOv3-MSSA based hot spot defect detection for photovoltaic power stations

With the continuous development of the energy industry, photovoltaic power generation is gradually becoming one of the main power generation methods. However, detecting hot spot defects in photovoltaic power stations is challenging. Therefore, enhancing detection efficiency using information technol...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of Measurements in Engineering Jg. 12; H. 1; S. 23 - 39
Hauptverfasser: Gu, Kaiming, Chen, Yong
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Kaunas JVE International Ltd 01.03.2024
Schlagworte:
Algorithms
Defects
Electric power generation
Electric power production
Feature extraction
Geospatial data
Modules
Object recognition
Photovoltaic cells
Power plants
Recall
Research methodology
Solar power plants
China
ISSN:2335-2124, 2424-4635
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract With the continuous development of the energy industry, photovoltaic power generation is gradually becoming one of the main power generation methods. However, detecting hot spot defects in photovoltaic power stations is challenging. Therefore, enhancing detection efficiency using information technology has become a crucial aspect. The study presents a defect detection model for PV power stations using the YOLOv3 (You Only Look Once v3) algorithm. The model incorporates coordinate attention module (CAM) and self-attention module (SAM) to improve feature extraction in low-resolution conditions. The Multi objective Sparrow is employed to achieve multiple objectives. It is very contributing in the detection of low-resolution features. It shows that the research method can reduce the loss value to 0.009 after 400 iterations of the loss curve test. The precision-recall (P-R) curve generated by the research method only starts to drop sharply when the Recall value reaches 0.96. The number of parameters generated by the research method is 3.46×10 6 . The detection accuracy of the research method reaches 98.86 % when there are five defective fault types. The results indicate that the proposed research method offers improved detection speed and higher accuracy in identifying hot spot defects in PV power stations. This technology provides valuable support for hot spot defect detection and presents new opportunities for the field.
AbstractList With the continuous development of the energy industry, photovoltaic power generation is gradually becoming one of the main power generation methods. However, detecting hot spot defects in photovoltaic power stations is challenging. Therefore, enhancing detection efficiency using information technology has become a crucial aspect. The study presents a defect detection model for PV power stations using the YOLOv3 (You Only Look Once v3) algorithm. The model incorporates coordinate attention module (CAM) and self-attention module (SAM) to improve feature extraction in low-resolution conditions. The Multi objective Sparrow is employed to achieve multiple objectives. It is very contributing in the detection of low-resolution features. It shows that the research method can reduce the loss value to 0.009 after 400 iterations of the loss curve test. The precision-recall (P-R) curve generated by the research method only starts to drop sharply when the Recall value reaches 0.96. The number of parameters generated by the research method is 3.46×10 6 . The detection accuracy of the research method reaches 98.86 % when there are five defective fault types. The results indicate that the proposed research method offers improved detection speed and higher accuracy in identifying hot spot defects in PV power stations. This technology provides valuable support for hot spot defect detection and presents new opportunities for the field.
With the continuous development of the energy industry, photovoltaic power generation is gradually becoming one of the main power generation methods. However, detecting hot spot defects in photovoltaic power stations is challenging. Therefore, enhancing detection efficiency using information technology has become a crucial aspect. The study presents a defect detection model for PV power stations using the YOLOv3 (You Only Look Once v3) algorithm. The model incorporates coordinate attention module (CAM) and self-attention module (SAM) to improve feature extraction in low-resolution conditions. The Multi objective Sparrow is employed to achieve multiple objectives. It is very contributing in the detection of low-resolution features. It shows that the research method can reduce the loss value to 0.009 after 400 iterations of the loss curve test. The precision-recall (P-R) curve generated by the research method only starts to drop sharply when the Recall value reaches 0.96. The number of parameters generated by the research method is 3.46×106. The detection accuracy of the research method reaches 98.86 % when there are five defective fault types. The results indicate that the proposed research method offers improved detection speed and higher accuracy in identifying hot spot defects in PV power stations. This technology provides valuable support for hot spot defect detection and presents new opportunities for the field.
With the continuous development of the energy industry, photovoltaic power generation is gradually becoming one of the main power generation methods. However, detecting hot spot defects in photovoltaic power stations is challenging. Therefore, enhancing detection efficiency using information technology has become a crucial aspect. The study presents a defect detection model for PV power stations using the YOLOv3 (You Only Look Once v3) algorithm. The model incorporates coordinate attention module (CAM) and self-attention module (SAM) to improve feature extraction in low-resolution conditions. The Multi objective Sparrow is employed to achieve multiple objectives. It is very contributing in the detection of low-resolution features. It shows that the research method can reduce the loss value to 0.009 after 400 iterations of the loss curve test. The precision-recall (P-R) curve generated by the research method only starts to drop sharply when the Recall value reaches 0.96. The number of parameters generated by the research method is 3.46*[10.sup.6]. The detection accuracy of the research method reaches 98.86% when there are five defective fault types. The results indicate that the proposed research method offers improved detection speed and higher accuracy in identifying hot spot defects in PV power stations. This technology provides valuable support for hot spot defect detection and presents new opportunities for the field. Keywords: YOLOV3, multi objective sparrow search algorithm (MSSA), hot spot defects, photovoltaic power plants, deep belief networks (DBN).
With the continuous development of the energy industry, photovoltaic power generation is gradually becoming one of the main power generation methods. However, detecting hot spot defects in photovoltaic power stations is challenging. Therefore, enhancing detection efficiency using information technology has become a crucial aspect. The study presents a defect detection model for PV power stations using the YOLOv3 (You Only Look Once v3) algorithm. The model incorporates coordinate attention module (CAM) and self-attention module (SAM) to improve feature extraction in low-resolution conditions. The Multi objective Sparrow is employed to achieve multiple objectives. It is very contributing in the detection of low-resolution features. It shows that the research method can reduce the loss value to 0.009 after 400 iterations of the loss curve test. The precision-recall (P-R) curve generated by the research method only starts to drop sharply when the Recall value reaches 0.96. The number of parameters generated by the research method is 3.46*[10.sup.6]. The detection accuracy of the research method reaches 98.86% when there are five defective fault types. The results indicate that the proposed research method offers improved detection speed and higher accuracy in identifying hot spot defects in PV power stations. This technology provides valuable support for hot spot defect detection and presents new opportunities for the field.
Audience Academic
Author Gu, Kaiming
Chen, Yong
Author_xml – sequence: 1
  givenname: Kaiming
  surname: Gu
  fullname: Gu, Kaiming
– sequence: 2
  givenname: Yong
  surname: Chen
  fullname: Chen, Yong
BookMark eNp1kUtLAzEUhYMo-Fy7HXDlYmqeM5NlEV9YKVhduAqZzI1G2smYpFX_val1oyCBnJB7vjzu2Ufbve8BoWOCR5QIKc5eFzCimLIRZZw0W2iPcspLXjGxndeMiZISynfRUYyuxZzXnEvZ7KHbp-lkumLl3Ww2LlodoStefCrikKcOLJi1pCzO94X1oRhy2a_8PGlnisG_Qyhi0utyPEQ7Vs8jHP3oAXq8vHg4vy4n06ub8_GkNKxhqZSiYSBbajsjaG2AG2gsgLSkagk3xErS0QrLpgbTQge64UI3UFsrMYMK2AE62Zw7BP-2hJjUq1-GPl-pGOa4qvLXaHaNNq5nPQfleutT0CaPDhbO5PZZl_fHtcSYCcZkBk5_AdmT4CM962WM6mZ2_9t7tvGa4GMMYNUQ3EKHT0Ww-k5E5UTUOhH1nUgmxB_CuE3f8rPc_F_uC-Y9kSI
CitedBy_id crossref_primary_10_1049_cth2_12732
crossref_primary_10_3390_fishes10060273
Cites_doi 10.1016/j.solener.2021.07.037
10.3233/JIFS-200778
10.21608/mjeer.2021.146237
10.1007/s12652-019-01212-6
10.18280/ijdne.150504
10.1080/00224065.2021.1948372
10.1021/acsaem.1c03206
10.1109/JPHOTOV.2021.3059425
10.47852/bonviewJCCE2202319
10.1177/09544062211019774
10.1002/pip.3191
10.24425/mms.2022.138548
10.1504/IJCVR.2020.10027325
10.47852/bonviewAIA2202524
10.1108/IJPCC-05-2020-0046
10.47852/bonviewAIA2202303
10.1002/pip.3479
10.1109/JPHOTOV.2020.3045680
10.26689/pbes.v4i3.2203
10.17586/2226-1494-2020-20-3-418-424
10.47852/bonviewJCCE2202192
10.1016/j.ifacol.2020.12.1994
ContentType Journal Article
Copyright COPYRIGHT 2024 JVE International Ltd.
Copyright JVE International Ltd. Mar 2024
Copyright_xml – notice: COPYRIGHT 2024 JVE International Ltd.
– notice: Copyright JVE International Ltd. Mar 2024
DBID AAYXX
CITATION
ISR
7TB
7U5
8FD
FR3
KR7
L7M
DOI 10.21595/jme.2023.23418
DatabaseName CrossRef
Gale In Context: Science
Mechanical & Transportation Engineering Abstracts
Solid State and Superconductivity Abstracts
Technology Research Database
Engineering Research Database
Civil Engineering Abstracts
Advanced Technologies Database with Aerospace
DatabaseTitle CrossRef
Civil Engineering Abstracts
Solid State and Superconductivity Abstracts
Engineering Research Database
Technology Research Database
Mechanical & Transportation Engineering Abstracts
Advanced Technologies Database with Aerospace
DatabaseTitleList CrossRef
Civil Engineering Abstracts
DeliveryMethod fulltext_linktorsrc
EISSN 2424-4635
EndPage 39
ExternalDocumentID A790035339
10_21595_jme_2023_23418
GeographicLocations China
GeographicLocations_xml – name: China
GroupedDBID AAYXX
ALMA_UNASSIGNED_HOLDINGS
CITATION
M~E
ISR
7TB
7U5
8FD
FR3
KR7
L7M
ID FETCH-LOGICAL-c383t-9583e9b2fdc527ce4ce8fee9f16b14c1f91d260987ecbedea845a8e7ff903e6e3
ISICitedReferencesCount 2
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001220546600001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2335-2124
IngestDate Mon Jun 30 07:18:46 EDT 2025
Tue Apr 16 05:11:04 EDT 2024
Sat Sep 28 21:03:24 EDT 2024
Tue Nov 18 22:35:05 EST 2025
Sat Nov 29 03:51:06 EST 2025
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 1
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c383t-9583e9b2fdc527ce4ce8fee9f16b14c1f91d260987ecbedea845a8e7ff903e6e3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
OpenAccessLink https://www.extrica.com/article/23418/pdf
PQID 3040664992
PQPubID 2049544
PageCount 17
ParticipantIDs proquest_journals_3040664992
gale_infotracacademiconefile_A790035339
gale_incontextgauss_ISR_A790035339
crossref_primary_10_21595_jme_2023_23418
crossref_citationtrail_10_21595_jme_2023_23418
PublicationCentury 2000
PublicationDate 2024-03-01
PublicationDateYYYYMMDD 2024-03-01
PublicationDate_xml – month: 03
  year: 2024
  text: 2024-03-01
  day: 01
PublicationDecade 2020
PublicationPlace Kaunas
PublicationPlace_xml – name: Kaunas
PublicationTitle Journal of Measurements in Engineering
PublicationYear 2024
Publisher JVE International Ltd
Publisher_xml – name: JVE International Ltd
References key-10.21595/jme.2023.23418-cit3
key-10.21595/jme.2023.23418-cit2
key-10.21595/jme.2023.23418-cit5
key-10.21595/jme.2023.23418-cit4
key-10.21595/jme.2023.23418-cit1
key-10.21595/jme.2023.23418-cit14
key-10.21595/jme.2023.23418-cit13
key-10.21595/jme.2023.23418-cit16
key-10.21595/jme.2023.23418-cit15
key-10.21595/jme.2023.23418-cit18
key-10.21595/jme.2023.23418-cit17
key-10.21595/jme.2023.23418-cit19
key-10.21595/jme.2023.23418-cit7
key-10.21595/jme.2023.23418-cit10
key-10.21595/jme.2023.23418-cit21
key-10.21595/jme.2023.23418-cit6
key-10.21595/jme.2023.23418-cit20
key-10.21595/jme.2023.23418-cit9
key-10.21595/jme.2023.23418-cit12
key-10.21595/jme.2023.23418-cit23
key-10.21595/jme.2023.23418-cit8
key-10.21595/jme.2023.23418-cit11
key-10.21595/jme.2023.23418-cit22
References_xml – ident: key-10.21595/jme.2023.23418-cit8
  doi: 10.1016/j.solener.2021.07.037
– ident: key-10.21595/jme.2023.23418-cit22
  doi: 10.3233/JIFS-200778
– ident: key-10.21595/jme.2023.23418-cit5
  doi: 10.21608/mjeer.2021.146237
– ident: key-10.21595/jme.2023.23418-cit7
  doi: 10.1007/s12652-019-01212-6
– ident: key-10.21595/jme.2023.23418-cit9
  doi: 10.18280/ijdne.150504
– ident: key-10.21595/jme.2023.23418-cit15
  doi: 10.1080/00224065.2021.1948372
– ident: key-10.21595/jme.2023.23418-cit1
  doi: 10.1021/acsaem.1c03206
– ident: key-10.21595/jme.2023.23418-cit6
  doi: 10.1109/JPHOTOV.2021.3059425
– ident: key-10.21595/jme.2023.23418-cit21
  doi: 10.47852/bonviewJCCE2202319
– ident: key-10.21595/jme.2023.23418-cit4
  doi: 10.1177/09544062211019774
– ident: key-10.21595/jme.2023.23418-cit17
  doi: 10.1002/pip.3191
– ident: key-10.21595/jme.2023.23418-cit20
  doi: 10.24425/mms.2022.138548
– ident: key-10.21595/jme.2023.23418-cit11
  doi: 10.1504/IJCVR.2020.10027325
– ident: key-10.21595/jme.2023.23418-cit16
  doi: 10.47852/bonviewAIA2202524
– ident: key-10.21595/jme.2023.23418-cit10
  doi: 10.1108/IJPCC-05-2020-0046
– ident: key-10.21595/jme.2023.23418-cit19
  doi: 10.47852/bonviewAIA2202303
– ident: key-10.21595/jme.2023.23418-cit3
  doi: 10.1002/pip.3479
– ident: key-10.21595/jme.2023.23418-cit2
  doi: 10.1109/JPHOTOV.2020.3045680
– ident: key-10.21595/jme.2023.23418-cit13
  doi: 10.26689/pbes.v4i3.2203
– ident: key-10.21595/jme.2023.23418-cit14
  doi: 10.17586/2226-1494-2020-20-3-418-424
– ident: key-10.21595/jme.2023.23418-cit18
  doi: 10.47852/bonviewJCCE2202192
– ident: key-10.21595/jme.2023.23418-cit12
  doi: 10.1016/j.ifacol.2020.12.1994
– ident: key-10.21595/jme.2023.23418-cit23
SSID ssib044744998
Score 2.2624192
Snippet With the continuous development of the energy industry, photovoltaic power generation is gradually becoming one of the main power generation methods. However,...
SourceID proquest
gale
crossref
SourceType Aggregation Database
Enrichment Source
Index Database
StartPage 23
SubjectTerms Algorithms
Defects
Electric power generation
Electric power production
Feature extraction
Geospatial data
Modules
Object recognition
Photovoltaic cells
Power plants
Recall
Research methodology
Solar power plants
Title YOLOv3-MSSA based hot spot defect detection for photovoltaic power stations
URI https://www.proquest.com/docview/3040664992
Volume 12
WOSCitedRecordID wos001220546600001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2424-4635
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssib044744998
  issn: 2335-2124
  databaseCode: M~E
  dateStart: 20140101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3db9MwELdg8MALAgGiMJCFECBVGY3tJPZjNXUC0Q9EO9Q9WYljwxCkYU2nPfG3c3acpGUDwQNSFEUXJ47ufr6zL-c7hJ6rjIaK5kmgeKIDUHgq4MaEQUzSQcZDlgiVuWITyXTKl0vx3seqrl05gaQo-MWFKP-rqIEGwrZbZ_9B3O1LgQDXIHQ4g9jh_FeCP5mNZ-c0mMznw761UXn_86rqw-q16ufapSrOdaVVG2NYwu0VKKkqPVX90hZNs_6Fzo93eeY66fyKLpp2K6dhG86zqUM1bM2wlnjod4KcrDzNexsI68KtakvwcfSLq7ILPgKVRSiNAjCGtYtA1zQGb2FxnZSk1bnkEra8AqVX6XWYlwibA-PLN5vZlNADAsaXdyas-W0_ncmj4_FYLkbLxYvye2CLi9mf8L7SynV0gySRsPp78mPUqB3GEgbrPle7sPn-OgmU6_b1bqc785errbibmizuoNteMnhYY-EuuqaLe-jdFg6wwwEGQWOLA1zjALc4wIADvI0D7HCAGxzcR8dHo8Xhm8BXzggU5bQKRMSpFhkxuYpIojRTmhuthQnjLGQqNCLMYSErYHyqTOc65SxKuU6MEQOqY00foL1iVeiHCIMRiqxe1zHPmCY8UwOWGsPzyB406qGDhh9S-bTytrrJVwnLS8dACQyUloHSMbCHXrUPlHVGld83fWYZLG2eksIGQn1KN-u1fDv_IIeJdcHDWkX00EvfyKygY5X6fSXw-Ta12U7L_UZQ0g_YtaRgxeIY5E8e_fn2Y3SrGxD7aK862-gn6KY6r07XZ08don4CIQKQdQ
linkProvider ISSN International Centre
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=YOLOv3-MSSA+based+hot+spot+defect+detection+for+photovoltaic+power+stations&rft.jtitle=Journal+of+Measurements+in+Engineering&rft.au=Gu%2C+Kaiming&rft.au=Chen%2C+Yong&rft.date=2024-03-01&rft.pub=JVE+International+Ltd&rft.issn=2335-2124&rft.eissn=2424-4635&rft.volume=12&rft.issue=1&rft.spage=23&rft_id=info:doi/10.21595%2Fjme.2023.23418&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2335-2124&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2335-2124&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2335-2124&client=summon