Fault classification for Photovoltaic Modules Using Thermography and Machine Learning Techniques

Fault classification and detection are necessary for safety, efficiency and reliability of photovoltaic systems. Regardless of the fact that PV system requires low maintenance due to the absence of moving parts, they are still vulnerable to many faults. Particularly for PV modules, it's problematic to shut them down completely during faults as it will affect their performance and result in early degradation. Additionally, the inability of conventional fault detection methods in early detection of faults leads to higher risk of failure. In this paper thermography and machine learning based PV module fault classification is developed. Texture feature analysis is adapted to study the features of different faulty panel thermal images. The extracted features are trained by implementing Artificial Neural network classifier to develop the fault classifier. The developed algorithm depicted 93.4% training efficiency and 91.7% testing efficiency which is better when compared with the conventional classification techniques.