Multidimensional approach for the detection of microcracks in solar pv systems

Abstract

Electricity demand is increasing day by day and hence power utilities are slowly shifting towards renewable energy, mainly solar, as it is more reliable and environment friendly. However, solar power generation systems have very low efficiency and this is the major challenge faced by the researchers. Some of the reasons for the low efficiency is the presence of dust particles, bird droppings, shadows, rain droplets, microcracks etc. Out of these, microcracks can be avoided if detected on time whereas remaining parameters have to be addressed on a regular basis as they are issues related to environmental factors. Microcracks are mainly due to manufacturing defects as well as improper handling during transportation and installation. Manual testing of panels for the detection of microcracks is very difficult and time consuming especially for panels of large dimensions and high-power rating. Some methods for the automated detection of cracks are available in the literature. The performance metrics of these methods along with the time taken for the detection of cracks is also available in the literature. This work addresses the process of detection of microcracks using an improved technology which detects the crack within very less time as compared to the existing technologies. Soft computing techniques like machine learning algorithms and deep learning algorithms are used to detect and classify the solar panel images as either cracked or non-cracked. Three different solar panel crack detection methods are discussed and analyzed in the proposed work. newline