Binary Classification of Defective Solar PV Modules Using Thermography

Kamran Ali Khan Niazi, Wajahat Akhtar, Hassan Abbas Khan, Sarmad Sohaib, Ahmad Kamal Nasir

Research output: Contribution to book/anthology/report/conference proceedingConference abstract in proceedingResearchpeer-review

6 Citations (Scopus)
227 Downloads (Pure)


Photovoltaic (PV) modules are subject to various internal or external stresses due to their operation in solar PV based power systems. Therefore, monitoring and maintenance are critical issues to ensure reliability of PV modules which in turn would affect the reliability of any PV system. In this paper, we categorize operational solar panels into two categories (Defective and Non-Defective panels) using a machine learning technique i.e. texture features through thermography assessment. Further, the panels are also categorized for diagnostic perspective using nBayes classifier. Results from an investigation for a 42.24 kWp PV system showed a mean recognition rate of 98.4% for a set of 260 test samples.
Original languageEnglish
Title of host publicationProceedings of the 2018 IEEE 7th World Conference on Photovoltaic Energy Conversion (WCPEC) (A Joint Conference of 45th IEEE PVSC, 28th PVSEC & 34th EU PVSEC)
Number of pages5
Publication dateJun 2018
ISBN (Print)978-1-5386-8530-3
ISBN (Electronic)978-1-5386-8529-7
Publication statusPublished - Jun 2018
Event7th World Conference on Photovoltaic Energy Conversion - Hilton Waikoloa Village, Waikoloa, United States
Duration: 10 Jun 201815 Jun 2018


Conference7th World Conference on Photovoltaic Energy Conversion
LocationHilton Waikoloa Village
CountryUnited States
Internet address


  • PV solar panel
  • thermal imaging (TI)
  • hotspots machine learning
  • nBayes classifier

Fingerprint Dive into the research topics of 'Binary Classification of Defective Solar PV Modules Using Thermography'. Together they form a unique fingerprint.

Cite this