Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Voting based ensemble for detecting visual faults in photovoltaic modules using AlexNet features
Luleå University of Technology, Department of Civil, Environmental and Natural Resources Engineering, Operation, Maintenance and Acoustics.ORCID iD: 0000-0002-4034-8859
School of Mechanical Engineering (SMEC), Vellore Institute of Technology, Chennai, India.
Department of Ocean Operations and Civil Engineering, Norwegian University of Science and Technology (NTNU), Ålesund 6009, Norway; Department of Sustainable Systems Engineering (INATECH), University of Freiburg, Freiburg 79110, Germany.
2024 (English)In: Energy Reports, E-ISSN 2352-4847, Vol. 11, p. 3889-3901Article in journal (Refereed) Published
Abstract [en]

This study proposes a novel approach utilizing a voting-based ensemble technique to diagnose visible faults in photovoltaic (PV) modules from aerial images captured by unmanned aerial vehicles (UAVs), leveraging AlexNet features. The proposed method focuses on classifying commonly occurring visual faults such as glass breakage, snail trails, burn marks, delamination and discoloration. Two voting-based ensemble models, a two-class ensemble (combining support vector machines and k-nearest neighbor) and a three-class ensemble (integrating support vector machines, J48, and k-nearest neighbor) were developed and evaluated against individual machine learning classifiers. Results indicate that the two-class ensemble outperforms the three-class ensemble and other individual classifiers, achieving an accuracy of 98.30%. This approach not only enhances fault diagnosis accuracy but also reduces inspection costs and instrument monitoring efforts contributing to the sustainable and efficient operation of PV systems.

Place, publisher, year, edition, pages
Elsevier, 2024. Vol. 11, p. 3889-3901
Keywords [en]
Photovoltaic modules, Ensemble method, Unmanned aerial vehicle, Deep learning, Machine learning
National Category
Computer Sciences
Research subject
Operation and Maintenance Engineering
Identifiers
URN: urn:nbn:se:ltu:diva-104917DOI: 10.1016/j.egyr.2024.03.044OAI: oai:DiVA.org:ltu-104917DiVA, id: diva2:1847531
Note

Validerad;2024;Nivå 2;2024-03-28 (hanlid);

Full text license: CC BY-NC

Available from: 2024-03-28 Created: 2024-03-28 Last updated: 2024-03-28Bibliographically approved

Open Access in DiVA

fulltext(6302 kB)30 downloads
File information
File name FULLTEXT01.pdfFile size 6302 kBChecksum SHA-512
dcc8f5663661806013a90935bcd19b32cac5a3e4c7e18e5a71d5b8d741cd056daf9ee72e87fa921735bda65ff0eb4da21474650c22218ca34beaa8bb8bba3a12
Type fulltextMimetype application/pdf

Other links

Publisher's full text

Authority records

Venkatesh, Naveen

Search in DiVA

By author/editor
Venkatesh, Naveen
By organisation
Operation, Maintenance and Acoustics
In the same journal
Energy Reports
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 30 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 358 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf