Logo do repositório
 
Publicação

Hypertuned-YOLO for interpretable distribution power grid fault location based on EigenCAM

2024-06Artigo científico Acesso aberto
Ver registo simples
dc.contributor.authorStefenon, Stefano Frizzo
dc.contributor.authorSeman, Laio Oriel
dc.contributor.authorKlaar, Anne Carolina Rodrigues
dc.contributor.authorOvejero, Raúl García
dc.contributor.authorLeithardt, Valderi Reis Quietinho
dc.contributor.institutionCTS - Centro de Tecnologia e Sistemas
dc.contributor.institutionUNINOVA-Instituto de Desenvolvimento de Novas Tecnologias
dc.contributor.pblAin Shams University
dc.date.accessioned2024-09-30T22:34:46Z
dc.date.available2024-09-30T22:34:46Z
dc.date.issued2024-06
dc.descriptionThis work was supported by “Caracterización, análisis e intervención en la prevención de riesgos laborales en entornos de trabajo tradicionales mediante la aplicación de tecnologías disruptivas”. De la Consejeria de Empleo e Industria, under project 2022/00384/001. Publisher Copyright: © 2024 The Author(s)
dc.description.abstractEnsuring the reliability of electrical distribution networks is a pressing concern, especially given the power outages due to surface contamination on insulating components. Surface contamination can elevate surface conductivity, thereby resulting in failures that can lead to power shutdowns. Addressing this challenge, this paper proposes an approach for real-time monitoring of electrical distribution grids to prevent such incidents. A hypertuned version of the you only look once (YOLO) model is tailored for this application. We refine the model's hyperparameters by integrating a genetic algorithm to maximize its detection performance. The EigenCAM technique enhances the visual interpretability of the model's outcomes, providing operators with actionable insights for maintenance and monitoring tasks. Benchmark tests reveal that the proposed Hypertuned-YOLO outperforms Detectron (Masked R-CNN), YOLOv5, and YOLOv7 models. The Hypertuned-YOLO achieves an F1-score of 0.867 and a mAP@0.5 of 0.922, validating its robustness and efficacy.en
dc.description.versionpublishersversion
dc.description.versionpublished
dc.format.extent11
dc.format.extent8764732
dc.identifier.doi10.1016/j.asej.2024.102722
dc.identifier.issn2090-4479
dc.identifier.otherPURE: 100329988
dc.identifier.otherPURE UUID: 87086fff-d910-46f2-87bb-7c5ba9fc93bc
dc.identifier.otherScopus: 85188210094
dc.identifier.otherWOS: 001261986800001
dc.identifier.urihttp://hdl.handle.net/10362/172770
dc.identifier.urlhttps://www.scopus.com/pages/publications/85188210094
dc.language.isoeng
dc.peerreviewedyes
dc.relationFunding Information: info:eu-repo/grantAgreement/FCT/Concurso de avaliação no âmbito do Programa Plurianual de Financiamento de Unidades de I&D (2017%2F2018) - Financiamento Base/UIDB%2F00066%2F2020/PT
dc.relationinfo:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDP%2F00066%2F2020/PT
dc.relationCentre of Technology and Systems
dc.subjectConvolutional neural networks
dc.subjectEigenCAM
dc.subjectPower grids
dc.subjectYou only look once
dc.subjectGeneral Engineering
dc.titleHypertuned-YOLO for interpretable distribution power grid fault location based on EigenCAMen
dc.typejournal article
degois.publication.issue6
degois.publication.titleAin Shams Engineering Journal
degois.publication.volume15
dspace.entity.typePublication
oaire.awardNumberUIDP/00066/2020
oaire.awardTitleCentre of Technology and Systems
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDP%2F00066%2F2020/PT
oaire.fundingStream6817 - DCRRNI ID
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.nameFundação para a Ciência e a Tecnologia
rcaap.rightsopenAccess
relation.isProjectOfPublication1d2038a0-e83e-4e7d-b885-ec08a407735c
relation.isProjectOfPublication.latestForDiscovery1d2038a0-e83e-4e7d-b885-ec08a407735c

Ficheiros

Principais
A mostrar 1 - 1 de 1
Miniatura
Nome:
Hypertuned-YOLO_for_interpretable_distribution_power_grid_fault_location.pdf
Tamanho:
8.36 MB
Formato:
Adobe Portable Document Format
Ver/Abrir

Coleções

Home collection (FCT)