Detection of Faulty Solar Panels Using Artificial Intelligence and Machine Learning Methods

One of the most promising approaches for detecting faults in solar panels is using computer vision techniques based on deep learning algorithms. Deep learning has proven to be highly effective in image classification tasks, and several studies have demonstrated its potential for detecting faults in solar panels. This paper, proposes a method for the classification of faulty solar panels using Convolutional Neural Networks (CNNs). CNN based on the encoder method is used for extracting features from the faulty and non-faulty images which received from the PV solar systems. Four classes that have 0%, 33%, 66%, and 100% defective rates have been considered to train the machine learning method. The Decision Tree, Support Vector Machine (SVM), KNN, Ensemble, and Discriminant methods were used for the machine learning and the accuracy for these methods has been obtained as 94.88%, 76.20%, 97.45%, 98.34%, and 80.23%, respectively.