Classification of Solar Cell Cracks Using Deep Learning

Abstract

This study evaluates the efficacy of a Deep Learning model in classifying solar cell images with and without cracks, crucial for early detection and maintenance of photovoltaic systems. The model demonstrates high overall accuracy (94%) and sensitivity (91%), indicating its proficiency in recognizing images with cracks while minimizing false positives. Receiver Operating Characteristic (ROC) analysis supports the model's robust discrimination between positive and negative cases, with an Area Under the Curve (AUC) of 0.93. Despite promising results, opportunities for improvement include dataset expansion to encompass diverse solar cell conditions and types of cracks. Real-world deployment considerations, such as integration into automated monitoring systems, pose challenges requiring further research. The study underscores the importance of ongoing development to enhance model performance for practical application in solar cell inspection and maintenance.