RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Voting based ensemble for detecting visual faults in photovoltaic modules using AlexNet features
Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.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 (engelsk)Inngår i: Energy Reports, E-ISSN 2352-4847, Vol. 11, s. 3889-3901Artikkel i tidsskrift (Fagfellevurdert) 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.

sted, utgiver, år, opplag, sider
Elsevier, 2024. Vol. 11, s. 3889-3901
Emneord [en]
Photovoltaic modules, Ensemble method, Unmanned aerial vehicle, Deep learning, Machine learning
HSV kategori
Forskningsprogram
Drift och underhållsteknik
Identifikatorer
URN: urn:nbn:se:ltu:diva-104917DOI: 10.1016/j.egyr.2024.03.044OAI: oai:DiVA.org:ltu-104917DiVA, id: diva2:1847531
Merknad

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

Full text license: CC BY-NC

Tilgjengelig fra: 2024-03-28 Laget: 2024-03-28 Sist oppdatert: 2024-03-28bibliografisk kontrollert

Open Access i DiVA

fulltext(6302 kB)25 nedlastinger
Filinformasjon
Fil FULLTEXT01.pdfFilstørrelse 6302 kBChecksum SHA-512
dcc8f5663661806013a90935bcd19b32cac5a3e4c7e18e5a71d5b8d741cd056daf9ee72e87fa921735bda65ff0eb4da21474650c22218ca34beaa8bb8bba3a12
Type fulltextMimetype application/pdf

Andre lenker

Forlagets fulltekst

Person

Venkatesh, Naveen

Søk i DiVA

Av forfatter/redaktør
Venkatesh, Naveen
Av organisasjonen
I samme tidsskrift
Energy Reports

Søk utenfor DiVA

GoogleGoogle Scholar
Totalt: 25 nedlastinger
Antall nedlastinger er summen av alle nedlastinger av alle fulltekster. Det kan for eksempel være tidligere versjoner som er ikke lenger tilgjengelige

doi
urn-nbn

Altmetric

doi
urn-nbn
Totalt: 354 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf