Repository logo
 
Publication

Multidefect detection tool for large-scale PV plants: Segmentation and classification

2023Journal article Restricted access
Simple item page
dc.contributor.authorRocha, Daniel
dc.contributor.authorAlves, Joao
dc.contributor.authorLopes, Vitor
dc.contributor.authorTeixeira, Jennifer P.
dc.contributor.authorFernandes, Paulo A.
dc.contributor.authorCosta, Mauro
dc.contributor.authorMorais, Modesto
dc.contributor.authorSalome, Pedro M. P.
dc.date.accessioned2024-03-21T14:45:19Z
dc.date.available2024-03-21T14:45:19Z
dc.date.issued2023
dc.description.abstractUnmanned aerial vehicles (UAVs) with highresolution optical and infrared (IR) imaging have been introduced in recent years to perform inexpensive and fast inspections in operation and maintenance activities of solar power plants, reducing the labor needed, while lowering the on-site inspection time. Even though UAVs can acquire images extremely quickly, the analysis of those images is still a time-consuming procedure that should be performed by a trained professional. Therefore, a computer vision approach may be used to accelerate image analysis. In this work, a dataset of IR images was created from a 10-MW solar power plant and a comparative analysis between mask R- convolutional neural network (CNN) and U-Net was performed for two experiments. Concerning the defective module segmentation, the mask R-CNN algorithm achieved a mean average precision at intersection over union (IoU) = 0.50 of 0.96, using augmentation data. Regarding the segmentation and classification of failure type, the algorithm reached a value of 0.88 considering the same evaluation metric and data augmentation.When compared to the U-Net in terms of IoU, the mask R-CNN outperformed it with 0.87 and 0.83 for the first and second experiments, respectively.pt_PT
dc.description.versioninfo:eu-repo/semantics/publishedVersionpt_PT
dc.identifier.citationD. Rocha et al., "Multidefect Detection Tool for Large-Scale PV Plants: Segmentation and Classification," in IEEE Journal of Photovoltaics, vol. 13, no. 2, pp. 291-295, March 2023, doi: 10.1109/JPHOTOV.2023.3236188pt_PT
dc.identifier.doi10.1109/JPHOTOV.2023.3236188pt_PT
dc.identifier.issn2156-3381
dc.identifier.urihttp://hdl.handle.net/10400.22/25217
dc.language.isoengpt_PT
dc.peerreviewedyespt_PT
dc.publisherIEEEpt_PT
dc.relationUIDB/04730/2020pt_PT
dc.relationNanomaterials with tailored properties based on metal oxide nanolaminates for carrier selective contacts in optoelectronic applications
dc.relationInstitute of Nanostructures, Nanomodelling and Nanofabrication
dc.relationInstitute of Nanostructures, Nanomodelling and Nanofabrication
dc.relation.publisherversionhttps://ieeexplore.ieee.org/document/10024046pt_PT
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/pt_PT
dc.subjectClass of abnormalitypt_PT
dc.subjectConvolutional neural network (CNN)pt_PT
dc.subjectFailure modept_PT
dc.subjectImage classificationpt_PT
dc.subjectImage segmentationpt_PT
dc.subjectLarge-scale photovoltaic (PV) plantpt_PT
dc.subjectThermographic inspectionpt_PT
dc.titleMultidefect detection tool for large-scale PV plants: Segmentation and classificationpt_PT
dc.typejournal article
dspace.entity.typePublication
oaire.awardTitleNanomaterials with tailored properties based on metal oxide nanolaminates for carrier selective contacts in optoelectronic applications
oaire.awardTitleInstitute of Nanostructures, Nanomodelling and Nanofabrication
oaire.awardTitleInstitute of Nanostructures, Nanomodelling and Nanofabrication
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/CEEC IND4ed/2021.02405.CEECIND%2FCP1684%2FCT0001/PT
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDB%2F50025%2F2020/PT
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDP%2F50025%2F2020/PT
oaire.citation.endPage295pt_PT
oaire.citation.issue2pt_PT
oaire.citation.startPage291pt_PT
oaire.citation.titleIEEE Journal of Photovoltaicspt_PT
oaire.citation.volume13pt_PT
oaire.fundingStreamCEEC IND4ed
oaire.fundingStream6817 - DCRRNI ID
oaire.fundingStream6817 - DCRRNI ID
person.familyNameFernandes
person.givenNamePaulo
person.identifier.orcid0000-0002-1860-7797
person.identifier.ridJ-5264-2013
person.identifier.scopus-author-id35568397500
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.nameFundação para a Ciência e a Tecnologia
project.funder.nameFundação para a Ciência e a Tecnologia
project.funder.nameFundação para a Ciência e a Tecnologia
rcaap.rightsclosedAccesspt_PT
rcaap.typearticlept_PT
relation.isAuthorOfPublication75281af2-3dd9-4a53-a2eb-07de6b8e8ba4
relation.isAuthorOfPublication.latestForDiscovery75281af2-3dd9-4a53-a2eb-07de6b8e8ba4
relation.isProjectOfPublication081e0fbf-8e99-4db6-a4df-84e6d975031a
relation.isProjectOfPublicationc32b36ff-076c-4ffb-b7f3-a96e1f391a7d
relation.isProjectOfPublication85b09c86-05c7-4c7d-98f4-6eef4ec8bda3
relation.isProjectOfPublication.latestForDiscoveryc32b36ff-076c-4ffb-b7f3-a96e1f391a7d

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
2023 DRocha_Multidefect Detection Tool for Large Scale PV Plants Segmentation and Classification.pdf
Size:
1017.2 KB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

ISEP – DFI – Artigos
ISEP – CIETI – Artigos