CNN-based automatic detection of photovoltaic solar module anomalies in infrared images: a comparative study

Solar energy is emerging as an environmentally friendly and sustainable energy source. However, with the widespread use of solar panels, how to manage these panels after their end-of-life becomes an important problem. It is known that heavy metals in solar modules can harm the environment and if not managed properly, it can cause great difficulties in waste management. Therefore, regular inspection, maintenance and waste management of solar modules are of great importance. The main objective of the study is to develop a Convolutional Neural Network (CNN) model to detect and classify failures in solar panels. By utilizing a large-scale IR image dataset obtained from real solar fields, the proposed CNN model is designed to effectively detect and classify various faults in photovoltaic (PV) modules. The dataset consists of 20,000 IR images including 12 different situations that occur under different conditions such as partial shading, short circuit, dust accumulation. The study addresses the issues of low-resolution and low-contrast images, class imbalance, and difficulty in tuning model parameters. The impact of resolving these issues on model performance is examined, with a focus on the effects of image preprocessing techniques like histogram equalization, data augmentation, and oversampling, as well as hyperparameter optimization methods such as Hyperband, Optuna, Successive Halving, and Bayesian Optimization. The results of the study show that the proposed model can predict an anomaly module with an average accuracy of 92% and correctly classify 12 anomaly types with an average accuracy of 82%.