Autonomous fault diagnosis of commercially available PV modules using high-end deep learning frameworks

Abstract

Conventional methods of fault diagnosis for PV Systems are quite challenging and inefficient, particularly with regards to large-scale PV arrays. Early and effective diagnosis of system faults is also imperative in order to minimize cost and sustainable damage. Hence, over the recent years, numerous effective and efficient monitoring and diagnostic techniques to detect faults in PV systems have been studied and propositioned. As such, autonomous fault diagnosis and classification of PV systems has taken the PV domain by storm and has spectacularly developed in eminence; attaining substantial significance in the domain of deep learning. Over the last few years, various deep learning frameworks have been studied and proposed in the detection & classification of faults in PV modules with the aid of thermal images. Some of the most prominent deep learning frameworks constitutes of ANN & CNN. This study involves utilization of Convolutional Neural Networks (CNN), namely, VGG-16/VGG-19 and EfficientNet, in order to assess their performance and reliability in diagnosing module defects through significant hotpots within PV modules by employing pre-processed thermal images.