Monitoramento de para-raios de ZnO com uso de redes neurais convolutivas e processamento de imagem
Autor(a) principal: | |
---|---|
Data de Publicação: | 2023 |
Tipo de documento: | Dissertação |
Idioma: | por |
Título da fonte: | Repositório Institucional da UFS |
Texto Completo: | https://ri.ufs.br/jspui/handle/riufs/18482 |
Resumo: | Monitoring and preventive maintenance of high-voltage electrical equipment are vital to prevent failures and ensure the smooth operation of the Power Electrical System. Infrared monitoring stands out for its convenience, safety, and ability to use temperature as a relevant indicator of the structural integrity and components health of the equipment. In this dissertation, a method is proposed for monitoring the operational condition of ZnO lightning arresters based on thermal measurements of the equipment. To achieve this, a convolutional neural network and computer vision processes were used to detect, segment, and extract the thermal profile of these devices. Additionally, an algorithm was employed to align the thermal profiles of the equipment, enabling comparison, identification of similarities, and classification of operational integrity. This allowed for a more accurate and comprehensive evaluation of ZnO lightning arresters, contributing to their continuous monitoring and efficient diagnosis. Thermal imaging of equipment from a 500 kV substation and thermal imaging from laboratory tests were used and analyzed. The laboratory tests included both healthy and intentionally defective equipment. The detection algorithm exhibited good precision rates of 0.861, a recall of 0.855, an mAP50 of 0.903, and an mAP50: 95 of 0.615, enabling an accurate detection and segmentation process. When applying the proposed method, the classification rates were consistent, correctly identifying both equipment in normal operating conditions and faulty equipment, despite variations due to thermal imager measurement errors, fluctuations in distance and angles, and environmental influences. Furthermore, when evaluating healthy equipment and those with applied defects, the proposed method achieved a 100% accuracy in identifying thermal anomalies, along with their localization. |
id |
UFS-2_139a44895ec001b73bb3a1ca73ce8495 |
---|---|
oai_identifier_str |
oai:ufs.br:riufs/18482 |
network_acronym_str |
UFS-2 |
network_name_str |
Repositório Institucional da UFS |
repository_id_str |
|
spelling |
Araújo, Bruno Vinícius SilveiraFerreira, Tarso VilelaXavier, George Victor Rocha2023-10-06T22:30:59Z2023-10-06T22:30:59Z2023-08-18ARAÚJO, Bruno Vinícius Silveira. Monitoramento de para-raios de ZnO com uso de redes neurais convolutivas e processamento de imagem. 2023. 110 f. Dissertação (Mestrado em Engenharia Elétrica) - Universidade Federal de Sergipe, São Cristóvão, 2023.https://ri.ufs.br/jspui/handle/riufs/18482Monitoring and preventive maintenance of high-voltage electrical equipment are vital to prevent failures and ensure the smooth operation of the Power Electrical System. Infrared monitoring stands out for its convenience, safety, and ability to use temperature as a relevant indicator of the structural integrity and components health of the equipment. In this dissertation, a method is proposed for monitoring the operational condition of ZnO lightning arresters based on thermal measurements of the equipment. To achieve this, a convolutional neural network and computer vision processes were used to detect, segment, and extract the thermal profile of these devices. Additionally, an algorithm was employed to align the thermal profiles of the equipment, enabling comparison, identification of similarities, and classification of operational integrity. This allowed for a more accurate and comprehensive evaluation of ZnO lightning arresters, contributing to their continuous monitoring and efficient diagnosis. Thermal imaging of equipment from a 500 kV substation and thermal imaging from laboratory tests were used and analyzed. The laboratory tests included both healthy and intentionally defective equipment. The detection algorithm exhibited good precision rates of 0.861, a recall of 0.855, an mAP50 of 0.903, and an mAP50: 95 of 0.615, enabling an accurate detection and segmentation process. When applying the proposed method, the classification rates were consistent, correctly identifying both equipment in normal operating conditions and faulty equipment, despite variations due to thermal imager measurement errors, fluctuations in distance and angles, and environmental influences. Furthermore, when evaluating healthy equipment and those with applied defects, the proposed method achieved a 100% accuracy in identifying thermal anomalies, along with their localization.O monitoramento e a manutenção preventiva de equipamentos elétricos de alta tensão são vitais para prevenir falhas e garantir o pleno funcionamento do Sistema Elétrico de Potência. O monitoramento por infravermelho se destaca por sua praticidade, segurança e capacidade de usar a temperatura como um indicador relevante da integridade estrutural e dos componentes dos equipamentos. Nesta dissertação, é proposto um método para o monitoramento da condição operacional de para-raios de óxido de zinco (ZnO) a partir de medições térmicas do equipamento. Para isso, utilizou-se uma rede neural convolucional e processos de visão computacional com o objetivo de detectar, segmentar e extrair o perfil térmico destes equipamentos. Além disso, foi empregado um algoritmo para alinhar os perfis térmicos dos equipamentos, possibilitando a comparação, identificação de similaridades e classificação da integridade operacional. Dessa forma, foi possível uma avaliação mais acurada e abrangente de para-raios de ZnO, contribuindo para o seu monitoramento contínuo e diagnóstico eficiente. Termografias de equipamentos de uma subestação de 500 kV e termografias de ensaios laboratoriais foram usadas e analisadas. Os ensaios em laboratório incluíram equipamentos saudáveis e com defeitos intencionais. O algoritmo de detecção apresentou bons índices de precisão de 0,861, recall de 0,855, mAP50 de 0,903 e mAP50: 95 de 0,615, possibilitando um processo de detecção e segmentação preciso. Ao aplicar o método proposto, os índices de classificação foram condizentes, indicando corretamente tanto os equipamentos em condição normal de operação quanto os equipamentos defeituosos, apesar das variações devido ao erro de medição do termovisor, flutuações na distância e angulação e influências ambientais. Outrossim, avaliando os equipamentos saudáveis e com defeitos aplicados, o método proposto obteve assertividade de 100% na identificação da anomalia térmica, além de sua localização.São CristóvãoporCorrentes elétricasPara-raiosRedes neurais (Computação)Sistemas imageadoresDetecçãoMonitoramentoTermografiaVisão computacionalDetectionMonitoringSurge arrestersThermographyComputer visionENGENHARIAS::ENGENHARIA ELETRICAMonitoramento de para-raios de ZnO com uso de redes neurais convolutivas e processamento de imageminfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisPós-Graduação em Engenharia ElétricaUniversidade Federal de Sergipe (UFS)reponame:Repositório Institucional da UFSinstname:Universidade Federal de Sergipe (UFS)instacron:UFSinfo:eu-repo/semantics/openAccessLICENSElicense.txtlicense.txttext/plain; charset=utf-81475https://ri.ufs.br/jspui/bitstream/riufs/18482/1/license.txt098cbbf65c2c15e1fb2e49c5d306a44cMD51ORIGINALBRUNO_VINICIUS_SILVEIRA_ARAUJO.pdfBRUNO_VINICIUS_SILVEIRA_ARAUJO.pdfapplication/pdf3900082https://ri.ufs.br/jspui/bitstream/riufs/18482/2/BRUNO_VINICIUS_SILVEIRA_ARAUJO.pdf94a5af461a4bb0ab59aa6d555b83375bMD52riufs/184822023-10-06 19:31:04.882oai:ufs.br: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Repositório InstitucionalPUBhttps://ri.ufs.br/oai/requestrepositorio@academico.ufs.bropendoar:2023-10-06T22:31:04Repositório Institucional da UFS - Universidade Federal de Sergipe (UFS)false |
dc.title.pt_BR.fl_str_mv |
Monitoramento de para-raios de ZnO com uso de redes neurais convolutivas e processamento de imagem |
title |
Monitoramento de para-raios de ZnO com uso de redes neurais convolutivas e processamento de imagem |
spellingShingle |
Monitoramento de para-raios de ZnO com uso de redes neurais convolutivas e processamento de imagem Araújo, Bruno Vinícius Silveira Correntes elétricas Para-raios Redes neurais (Computação) Sistemas imageadores Detecção Monitoramento Termografia Visão computacional Detection Monitoring Surge arresters Thermography Computer vision ENGENHARIAS::ENGENHARIA ELETRICA |
title_short |
Monitoramento de para-raios de ZnO com uso de redes neurais convolutivas e processamento de imagem |
title_full |
Monitoramento de para-raios de ZnO com uso de redes neurais convolutivas e processamento de imagem |
title_fullStr |
Monitoramento de para-raios de ZnO com uso de redes neurais convolutivas e processamento de imagem |
title_full_unstemmed |
Monitoramento de para-raios de ZnO com uso de redes neurais convolutivas e processamento de imagem |
title_sort |
Monitoramento de para-raios de ZnO com uso de redes neurais convolutivas e processamento de imagem |
author |
Araújo, Bruno Vinícius Silveira |
author_facet |
Araújo, Bruno Vinícius Silveira |
author_role |
author |
dc.contributor.author.fl_str_mv |
Araújo, Bruno Vinícius Silveira |
dc.contributor.advisor1.fl_str_mv |
Ferreira, Tarso Vilela |
dc.contributor.advisor-co1.fl_str_mv |
Xavier, George Victor Rocha |
contributor_str_mv |
Ferreira, Tarso Vilela Xavier, George Victor Rocha |
dc.subject.por.fl_str_mv |
Correntes elétricas Para-raios Redes neurais (Computação) Sistemas imageadores Detecção Monitoramento Termografia Visão computacional Detection Monitoring Surge arresters Thermography Computer vision |
topic |
Correntes elétricas Para-raios Redes neurais (Computação) Sistemas imageadores Detecção Monitoramento Termografia Visão computacional Detection Monitoring Surge arresters Thermography Computer vision ENGENHARIAS::ENGENHARIA ELETRICA |
dc.subject.cnpq.fl_str_mv |
ENGENHARIAS::ENGENHARIA ELETRICA |
description |
Monitoring and preventive maintenance of high-voltage electrical equipment are vital to prevent failures and ensure the smooth operation of the Power Electrical System. Infrared monitoring stands out for its convenience, safety, and ability to use temperature as a relevant indicator of the structural integrity and components health of the equipment. In this dissertation, a method is proposed for monitoring the operational condition of ZnO lightning arresters based on thermal measurements of the equipment. To achieve this, a convolutional neural network and computer vision processes were used to detect, segment, and extract the thermal profile of these devices. Additionally, an algorithm was employed to align the thermal profiles of the equipment, enabling comparison, identification of similarities, and classification of operational integrity. This allowed for a more accurate and comprehensive evaluation of ZnO lightning arresters, contributing to their continuous monitoring and efficient diagnosis. Thermal imaging of equipment from a 500 kV substation and thermal imaging from laboratory tests were used and analyzed. The laboratory tests included both healthy and intentionally defective equipment. The detection algorithm exhibited good precision rates of 0.861, a recall of 0.855, an mAP50 of 0.903, and an mAP50: 95 of 0.615, enabling an accurate detection and segmentation process. When applying the proposed method, the classification rates were consistent, correctly identifying both equipment in normal operating conditions and faulty equipment, despite variations due to thermal imager measurement errors, fluctuations in distance and angles, and environmental influences. Furthermore, when evaluating healthy equipment and those with applied defects, the proposed method achieved a 100% accuracy in identifying thermal anomalies, along with their localization. |
publishDate |
2023 |
dc.date.accessioned.fl_str_mv |
2023-10-06T22:30:59Z |
dc.date.available.fl_str_mv |
2023-10-06T22:30:59Z |
dc.date.issued.fl_str_mv |
2023-08-18 |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/masterThesis |
format |
masterThesis |
status_str |
publishedVersion |
dc.identifier.citation.fl_str_mv |
ARAÚJO, Bruno Vinícius Silveira. Monitoramento de para-raios de ZnO com uso de redes neurais convolutivas e processamento de imagem. 2023. 110 f. Dissertação (Mestrado em Engenharia Elétrica) - Universidade Federal de Sergipe, São Cristóvão, 2023. |
dc.identifier.uri.fl_str_mv |
https://ri.ufs.br/jspui/handle/riufs/18482 |
identifier_str_mv |
ARAÚJO, Bruno Vinícius Silveira. Monitoramento de para-raios de ZnO com uso de redes neurais convolutivas e processamento de imagem. 2023. 110 f. Dissertação (Mestrado em Engenharia Elétrica) - Universidade Federal de Sergipe, São Cristóvão, 2023. |
url |
https://ri.ufs.br/jspui/handle/riufs/18482 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.publisher.program.fl_str_mv |
Pós-Graduação em Engenharia Elétrica |
dc.publisher.initials.fl_str_mv |
Universidade Federal de Sergipe (UFS) |
dc.source.none.fl_str_mv |
reponame:Repositório Institucional da UFS instname:Universidade Federal de Sergipe (UFS) instacron:UFS |
instname_str |
Universidade Federal de Sergipe (UFS) |
instacron_str |
UFS |
institution |
UFS |
reponame_str |
Repositório Institucional da UFS |
collection |
Repositório Institucional da UFS |
bitstream.url.fl_str_mv |
https://ri.ufs.br/jspui/bitstream/riufs/18482/1/license.txt https://ri.ufs.br/jspui/bitstream/riufs/18482/2/BRUNO_VINICIUS_SILVEIRA_ARAUJO.pdf |
bitstream.checksum.fl_str_mv |
098cbbf65c2c15e1fb2e49c5d306a44c 94a5af461a4bb0ab59aa6d555b83375b |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 |
repository.name.fl_str_mv |
Repositório Institucional da UFS - Universidade Federal de Sergipe (UFS) |
repository.mail.fl_str_mv |
repositorio@academico.ufs.br |
_version_ |
1802110723929669632 |