Computer vision and artificial intelligence for anomaly detection in photovoltaic panels/ Visao computacional e inteligencia artificial para a deteccao de anomalias em paineis fotovoltaicos/ Vision por computador e inteligencia artificial para la deteccion de anomalias en paneles fotovoltaicos

Power generation through photovoltaic technology has become an essential source of electricity in the world in recent years. In Brazil, it is already the second most immense installed power in the electrical matrix, and, as a result, anomalies in photovoltaic panels tend to become a source of losses...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:GeSec : Revista de Gestão e Secretariado Jg. 15; H. 12
Hauptverfasser: Nichida, Cleiber, Domingos, Jose Luis, da Silveira, Carlos Roberto, Jr, Gomes, Raphael Aquino, Alves, Ricardo Henrique, Cremon, Edipo Henrique, Afonso, Renato, Jr
Format: Journal Article
Sprache:Portugiesisch
Veröffentlicht: Sindicato das Secretarias e Secretarios do Estado de Sao Paulo 01.12.2024
Schlagworte:
Artificial intelligence
Computer organization
Electric power production
Machine vision
ISSN:2178-9010, 2178-9010
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Power generation through photovoltaic technology has become an essential source of electricity in the world in recent years. In Brazil, it is already the second most immense installed power in the electrical matrix, and, as a result, anomalies in photovoltaic panels tend to become a source of losses because they are elements exposed to the actions of nature. Techniques for detecting problems in panels have been studied, and among these, the use of thermographic images collected with the help of drones stands out. In this work, a solution is developed using computer vision and artificial intelligence techniques for detecting and classifying anomalies. It aims to assist operation and maintenance teams in deciding what type of intervention to carry out, thus optimizing their work and mitigating more significant losses. The average result of the Recall metric was over 95% accuracy, demonstrating the viability of its use for developing a solution for the photovoltaic system maintenance market. Keywords: Computer Vision. Convolutional Neural Network. Infrared Thermography. Operation and Maintenance. Photovoltaic Panel. A geracao de energia por meio de tecnologia fotovoltaica tornou-se uma importante fonte de eletricidade no mundo nos ultimos anos. No Brasil ja e a segunda maior potencia instalada na matriz eletrica e, com isso, anomalias nas placas fotovoltaicas tendem a se tornar fonte de perdas por serem elementos expostos as acoes da natureza. Tecnicas de deteccao de problemas nos paineis vem sendo estudadas e dentre essas, destaca-se o uso de imagens termograficas coletadas com auxilio de drones. No presente trabalho e desenvolvida a solucao utilizando visao computacional e tecnicas de inteligencia artificial para a deteccao e classificacao de anomalias, visando o auxilio as equipes de operacao e manutencao para a tomada de decisao sobre qual o tipo de intervencao a ser realizada, otimizando assim seu trabalho e mitigando maiores perdas no processo. O resultado medio da metrica Recall foi de mais de 95% de acerto, demonstrando a viabilidade de seu uso para o desenvolvimento de uma solucao para o mercado de manutencao de sistemas fotovoltaicos. Palavras-chave: Operacao e Manutencao. Paineis Fotovoltaicos. Redes Neurais Convolucionais. Termografia Infravermelha. Visao computacional. La generacion de energia mediante tecnologia fotovoltaica se ha convertido en los ultimos anos en una importante fuente de electricidad en el mundo. En Brasil, ya es la segunda potencia instalada en la matriz electrica y, como resultado, las anomalias en los paneles fotovoltaicos tienden a convertirse en fuente de perdidas por ser elementos expuestos a las acciones de la naturaleza. Se han estudiado tecnicas de deteccion de problemas en paneles y entre ellas destaca el uso de imagenes termicas recogidas con ayuda de drones. En este trabajo, la solucion se desarrolla utilizando tecnicas de vision computacional e inteligencia artificial para la deteccion y clasificacion de anomalias, con el objetivo de ayudar a los equipos de operacion y mantenimiento en la toma de decisiones sobre el tipo de intervencion a realizar, optimizando asi su trabajo y mitigando mayores perdidas en el proceso. El resultado promedio de la metrica Recall fue mas del 95% correcto, lo que demuestra la viabilidad de su uso para desarrollar una solucion para el mercado de mantenimiento de sistemas fotovoltaicos. Palabras clave: Operacion y Mantenimiento. Paneles Fotovoltaicos. Redes Neuronales Convolucionales. Termografia Infrarroja. Vision por Computador.
AbstractList Power generation through photovoltaic technology has become an essential source of electricity in the world in recent years. In Brazil, it is already the second most immense installed power in the electrical matrix, and, as a result, anomalies in photovoltaic panels tend to become a source of losses because they are elements exposed to the actions of nature. Techniques for detecting problems in panels have been studied, and among these, the use of thermographic images collected with the help of drones stands out. In this work, a solution is developed using computer vision and artificial intelligence techniques for detecting and classifying anomalies. It aims to assist operation and maintenance teams in deciding what type of intervention to carry out, thus optimizing their work and mitigating more significant losses. The average result of the Recall metric was over 95% accuracy, demonstrating the viability of its use for developing a solution for the photovoltaic system maintenance market.
Power generation through photovoltaic technology has become an essential source of electricity in the world in recent years. In Brazil, it is already the second most immense installed power in the electrical matrix, and, as a result, anomalies in photovoltaic panels tend to become a source of losses because they are elements exposed to the actions of nature. Techniques for detecting problems in panels have been studied, and among these, the use of thermographic images collected with the help of drones stands out. In this work, a solution is developed using computer vision and artificial intelligence techniques for detecting and classifying anomalies. It aims to assist operation and maintenance teams in deciding what type of intervention to carry out, thus optimizing their work and mitigating more significant losses. The average result of the Recall metric was over 95% accuracy, demonstrating the viability of its use for developing a solution for the photovoltaic system maintenance market. Keywords: Computer Vision. Convolutional Neural Network. Infrared Thermography. Operation and Maintenance. Photovoltaic Panel. A geracao de energia por meio de tecnologia fotovoltaica tornou-se uma importante fonte de eletricidade no mundo nos ultimos anos. No Brasil ja e a segunda maior potencia instalada na matriz eletrica e, com isso, anomalias nas placas fotovoltaicas tendem a se tornar fonte de perdas por serem elementos expostos as acoes da natureza. Tecnicas de deteccao de problemas nos paineis vem sendo estudadas e dentre essas, destaca-se o uso de imagens termograficas coletadas com auxilio de drones. No presente trabalho e desenvolvida a solucao utilizando visao computacional e tecnicas de inteligencia artificial para a deteccao e classificacao de anomalias, visando o auxilio as equipes de operacao e manutencao para a tomada de decisao sobre qual o tipo de intervencao a ser realizada, otimizando assim seu trabalho e mitigando maiores perdas no processo. O resultado medio da metrica Recall foi de mais de 95% de acerto, demonstrando a viabilidade de seu uso para o desenvolvimento de uma solucao para o mercado de manutencao de sistemas fotovoltaicos. Palavras-chave: Operacao e Manutencao. Paineis Fotovoltaicos. Redes Neurais Convolucionais. Termografia Infravermelha. Visao computacional. La generacion de energia mediante tecnologia fotovoltaica se ha convertido en los ultimos anos en una importante fuente de electricidad en el mundo. En Brasil, ya es la segunda potencia instalada en la matriz electrica y, como resultado, las anomalias en los paneles fotovoltaicos tienden a convertirse en fuente de perdidas por ser elementos expuestos a las acciones de la naturaleza. Se han estudiado tecnicas de deteccion de problemas en paneles y entre ellas destaca el uso de imagenes termicas recogidas con ayuda de drones. En este trabajo, la solucion se desarrolla utilizando tecnicas de vision computacional e inteligencia artificial para la deteccion y clasificacion de anomalias, con el objetivo de ayudar a los equipos de operacion y mantenimiento en la toma de decisiones sobre el tipo de intervencion a realizar, optimizando asi su trabajo y mitigando mayores perdidas en el proceso. El resultado promedio de la metrica Recall fue mas del 95% correcto, lo que demuestra la viabilidad de su uso para desarrollar una solucion para el mercado de mantenimiento de sistemas fotovoltaicos. Palabras clave: Operacion y Mantenimiento. Paneles Fotovoltaicos. Redes Neuronales Convolucionales. Termografia Infrarroja. Vision por Computador.
Audience General
Author Nichida, Cleiber
Domingos, Jose Luis
da Silveira, Carlos Roberto, Jr
Cremon, Edipo Henrique
Afonso, Renato, Jr
Alves, Ricardo Henrique
Gomes, Raphael Aquino
Author_xml – sequence: 1
  fullname: Nichida, Cleiber
– sequence: 2
  fullname: Domingos, Jose Luis
– sequence: 3
  fullname: da Silveira, Carlos Roberto, Jr
– sequence: 4
  fullname: Gomes, Raphael Aquino
– sequence: 5
  fullname: Alves, Ricardo Henrique
– sequence: 6
  fullname: Cremon, Edipo Henrique
– sequence: 7
  fullname: Afonso, Renato, Jr
BookMark eNqFjltLAzEQhVep4PUH-BYQfGubpHvLoxRvUPCl-Cqz2UkdySbLZi347027VaoIJg-Zycw53zlNRs47TJJLwSdFkavpCgPqyVpkJOQkzQp-mJxIUZRjxQUf7dXHyUUIbzwepSSX4uTgeu6b9r3Hjq0pkHcMXM2g68mQJrCMXI_W0gqdRmZ8F-e-AfvBauxR9xsFOda--t6vve2BNGvBoQ1T9kwBPNNbf9BxM9rhYLj1I9gHtdDFfrDVUVfjDkUQGDZxTg4pxAzfJD9ANhnamGxHqmP5D8Z-cTbSnyA3xMdfoPPkyIANeLF7z5Ll3e1y_jBePN0_zm8W41VezMYSociLCrM0F9wornOo0ShVKlWhzNOsMkUtK5liKWZalAZlBVJCyo0xgDA7S64G2xVYfCEXM3SgGwr65aaUpeRZWs7i1uSPrXhrbGJYh4bi_57gE7AZtbk
ContentType Journal Article
Copyright COPYRIGHT 2024 Sindicato das Secretarias e Secretarios do Estado de Sao Paulo
Copyright_xml – notice: COPYRIGHT 2024 Sindicato das Secretarias e Secretarios do Estado de Sao Paulo
DBID INF
DOI 10.7769/gesec.v15i12.4570
DatabaseName Gale OneFile: Informe Academico
DatabaseTitleList

DeliveryMethod fulltext_linktorsrc
Discipline Business
EISSN 2178-9010
ExternalDocumentID A828205483
GroupedDBID 5VS
7WY
8FL
91A
ABDBF
ABUWG
ACUHS
ADBBV
AFFHD
AFKRA
ALMA_UNASSIGNED_HOLDINGS
BCNDV
BENPR
BEZIV
BPHCQ
CCPQU
CLZPN
DWQXO
EAD
EAP
EPL
ESX
FRNLG
IAO
INF
K60
K6~
KQ8
M0C
M~E
OK1
PHGZM
PHGZT
PIMPY
PQBIZ
PQBZA
PQQKQ
PROAC
ID FETCH-LOGICAL-g673-2ea767be54610f90c6adef99899be2645bf7d2b24e813c18fe2ba22a40fffaea3
ISSN 2178-9010
IngestDate Tue Nov 11 10:51:47 EST 2025
Tue Nov 04 18:11:41 EST 2025
IsPeerReviewed true
IsScholarly true
Issue 12
Language Portuguese
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-g673-2ea767be54610f90c6adef99899be2645bf7d2b24e813c18fe2ba22a40fffaea3
ParticipantIDs gale_infotracmisc_A828205483
gale_infotracacademiconefile_A828205483
PublicationCentury 2000
PublicationDate 20241201
PublicationDateYYYYMMDD 2024-12-01
PublicationDate_xml – month: 12
  year: 2024
  text: 20241201
  day: 01
PublicationDecade 2020
PublicationTitle GeSec : Revista de Gestão e Secretariado
PublicationYear 2024
Publisher Sindicato das Secretarias e Secretarios do Estado de Sao Paulo
Publisher_xml – name: Sindicato das Secretarias e Secretarios do Estado de Sao Paulo
SSID ssj0000992021
Score 2.2755444
Snippet Power generation through photovoltaic technology has become an essential source of electricity in the world in recent years. In Brazil, it is already the...
SourceID gale
SourceType Aggregation Database
SubjectTerms Artificial intelligence
Computer organization
Electric power production
Machine vision
Title Computer vision and artificial intelligence for anomaly detection in photovoltaic panels/ Visao computacional e inteligencia artificial para a deteccao de anomalias em paineis fotovoltaicos/ Vision por computador e inteligencia artificial para la deteccion de anomalias en paneles fotovoltaicos
Volume 15
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2178-9010
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000992021
  issn: 2178-9010
  databaseCode: M~E
  dateStart: 20100101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
– providerCode: PRVPQU
  databaseName: ABI/INFORM Collection
  customDbUrl:
  eissn: 2178-9010
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000992021
  issn: 2178-9010
  databaseCode: 7WY
  dateStart: 20100101
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/abicomplete
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ABI/INFORM Global
  customDbUrl:
  eissn: 2178-9010
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000992021
  issn: 2178-9010
  databaseCode: M0C
  dateStart: 20100101
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/abiglobal
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Latin America & Iberia Database
  customDbUrl:
  eissn: 2178-9010
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000992021
  issn: 2178-9010
  databaseCode: CLZPN
  dateStart: 20100101
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/latinamericaiberian
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Central
  customDbUrl:
  eissn: 2178-9010
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000992021
  issn: 2178-9010
  databaseCode: BENPR
  dateStart: 20100101
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/central
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Publicly Available Content Database
  customDbUrl:
  eissn: 2178-9010
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000992021
  issn: 2178-9010
  databaseCode: PIMPY
  dateStart: 20100101
  isFulltext: true
  titleUrlDefault: http://search.proquest.com/publiccontent
  providerName: ProQuest
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9QwEDZ9IMQF8RSFgnxAcIi23XWSTXKsqlKQSlWxVVVOlWNP2kjZeNlkV-Vf8ROZifPaUkE5cFlFefizd-aLx843NmPvhgl4w0QnyG8_GHgkIIzHQg4wNh66ro60rrbpPDsKjo_D8_PoZG39Z5MLs8yCPA-vr6PZfzU1nkNjU-rsP5i7LRRP4DEaHX_R7Ph7J8M3-zQ4Nm3crsY6ryRB1QYd_TU4rYTSTGX2w9FQgmqkj7MrUxp8c5UyVQ6-MLAHpfXNz9JCmkqGviilsrOIYIusSqQMrw6KlhV3pC1Y4XMaarBUFg5M8TqGuCktCNFimQaG6oFDgwZL08LkfwbKGiR6dBUqt02AG1D9wPwQJqAcKw9cUkxNRRxil1kpCVyD6BOKsEuJJtSm-5yjrlJdBeD7GZD6ph0ZmClGBab9zOIcLdJ2_KKlM0mzJaRzWatuMlPUKnf7Kawt59DUKSNf5YwSHJy974s0N_3ZGuHdUL5MSIigaFcfjc3v6l30W4GA2jgHBf251NgJWoh0oqbrG3AgGVbKGtuN33Ku6dz8PonFbZ1mEIxpzdlLKEDtLEd-OhI7nh8Muwih1W3u4fhcYJAfuutsUwR-hP3I5snnLyff2nlNHHFgu2meo62PFRMQzO5vIHUk1IvpTh-zR_VgjO9ZEj1ha7PyKXvQ5II8u_e-4RK3XOLIJd75He9ziSOXeM0l3nIJb-F9LnHLpV1eMYmvMIkD7zt4H4gcnEveMAkPeOveHKa8ZhJfce8KhOqAPOIdj_4GkzU49OgqUM5rHq0CPWenHw9O9z8N6o1VBpfjwB0IkME4iMGnvRaSaKjGUkMSRWEUxYADJD9OAi1i4UE4ctUoTEDEUgiJL_UkkSDdF2wjNzm8ZHysIwyyo1G135nyPJkkEGkp_Jh2tIqDLfaBzHtB_lbOpZJ10g8-TevOXXQOtcW2V-7EXk71Lr-6c0Gv2cOOeNtso5wv4A27r5ZlWszf1u76CwSQNKA
linkProvider ProQuest
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=Computer+vision+and+artificial+intelligence+for+anomaly+detection+in+photovoltaic+panels%2F+Visao+computacional+e+inteligencia+artificial+para+a+deteccao+de+anomalias+em+paineis+fotovoltaicos%2F+Vision+por+computador+e+inteligencia+artificial+para+la+deteccion+de+anomalias+en+paneles+fotovoltaicos&rft.jtitle=GeSec+%3A+Revista+de+Gest%C3%A3o+e+Secretariado&rft.au=Nichida%2C+Cleiber&rft.au=Domingos%2C+Jose+Luis&rft.au=da+Silveira%2C+Carlos+Roberto%2C+Jr&rft.au=Gomes%2C+Raphael+Aquino&rft.date=2024-12-01&rft.pub=Sindicato+das+Secretarias+e+Secretarios+do+Estado+de+Sao+Paulo&rft.issn=2178-9010&rft.eissn=2178-9010&rft.volume=15&rft.issue=12&rft_id=info:doi/10.7769%2Fgesec.v15i12.4570&rft.externalDocID=A828205483
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2178-9010&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2178-9010&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2178-9010&client=summon