Enhancing Photovoltaic Module Fault Diagnosis with Unmanned Aerial Vehicles and Deep Learning-Based Image Analysis

• Published in: International journal of photoenergy 2023-07, Vol.2023, p.1-17
• Main Authors: Jerome Vasanth, J., Naveen Venkatesh, S., Sugumaran, V., Mahamuni, Vetri Selvi
• Format: Article
• Language: English
• Subjects: Algorithms; Artificial intelligence; Classification; Classifiers; Color imagery; Computer vision; Control systems; Datasets; Decision trees; Deep learning; Discoloration; Fault diagnosis; Image analysis; Industrial electronics; Inspection; Machine learning; Machinery condition monitoring; Mechanical components; Photovoltaic cells; Unmanned aerial vehicles
• ISSN: 1110-662X; 1687-529X
• DOI: 10.1155/2023/8665729

Artificial intelligence (AI) has evolved into a powerful tool that has wide-spread application in computer vision such as computer-aided inspection, industrial control systems, and navigation of robots. Monitoring the condition of machineries and mechanical components for the presence of faults with the aid of image-based automated analysis is one major application of computer vision. Diagnosing machinery faults from images can be made feasible with the adoption of deep learning and machine learning techniques. The primary objective of this study is to detect malfunctions in photovoltaic (PV) modules by utilizing a combination of deep learning and machine learning methodologies, with the assistance of RGB images captured via unmanned aerial vehicles. Six test conditions of PV modules such as good panel, snail trail, delamination, glass breakage, discoloration, and burn marks were considered in the study. The overall experimentation was carried out in two phases: (i) deep learning phase and (ii) machine learning phase. In the initial deep learning phase, the final fully connected layer of six pretrained networks, namely, DenseNet-201, VGG19, ResNet-50, GoogLeNet, VGG16, and AlexNet, was utilized to extract PVM image features. During the machine learning phase, feature selection from the extracted features was carried out using the J48 decision tree algorithm. Post selection of features, three families of classifiers such as tree, Bayes, and lazy were applied to determine the best feature extractor-classifier pair. The combination of DenseNet-201 features with k-nearest neighbour (IBK) classifier produced the overall classification accuracy of 100.00% among all other pretrained network features and classifiers considered.