Enhanced Detection of Solar Panel Defects Using VGG16-Based Convolutional Neural Networks

Aakash Gupta, Bhavisha Shah and Muhammad Zaid Katlariwala

International Journal of Scientific Research in Science and Technology, 2025, vol. 12, issue 3, 1255-1262

Abstract: Solar energy is a renewable energy source that is expanding rapidly, and it is essential to ensure that solar panel installations are correctly monitored and maintained to ensure that they are operating at their full potential. Detection of various situations and irregularities in solar panel arrays may be accomplished through automated image classification algorithms, which hold great potential. Within the scope of this research, we offer a technique for categorizing images of solar panels that uses the VGG16 convolutional neural network (CNN) architecture. The dataset was taken from Kaggle, which contained 891 Images. The dataset was divided into six categories: Bird drop, Clean, Dusty, electrical damage, physical damage, and snow-covered. In this research, we implemented solar panel image classification using VGG16, a convolutional neural network and achieved a remarkable accuracy of 97.88%. This research exhibited performance compared to the state-of-the-art methods.

Keywords: Solar Panel; Machine Learning; Image Classification; VGG16; Deep Learning (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://ijsrst.com/home/article/view/IJSRST25123136 Abstract page (text/html)
https://ijsrst.com/home/article/download/IJSRST25123136/IJSRST25123136 Full text (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:etm:ijsrst:v12:y2025:i3:id:946

DOI: 10.32628/IJSRST25123136

Access Statistics for this article

More articles in International Journal of Scientific Research in Science and Technology from Technoscience Academy
Bibliographic data for series maintained by Pankaj Sharma ().