Real-Time and High-Precision Hot Spot Detection by Photovoltaic Drone Inspection

Photovoltaic technology is the mainstream technology in the world at present, and its contribution to energy has also attracted wide attention from all mankind. However, the complex and changeable environment and some unknown factors have seriously affected the use efficiency of photovoltaic systems. Therefore, timely maintenance of the photovoltaic systems and finding out the defects in the photovoltaic panel have become the key to the development of photovoltaic technology. In this paper, through the analysis of infrared thermal imaging data in the defect detection of photovoltaic modules, aiming at the problems of small targets, high density, low detection accuracy, slow efficiency, and poor robustness of infrared defects of photovoltaic modules in the UAV patrol scene, advanced machine vision and deep learning algorithms in the field of artificial intelligence are used to carry out the research on defect detection of photovoltaic modules. In the end, the improved RT-DETR (Real-Time Detection Transformer) model achieved an accuracy of 83.3% in defect localization during detection, and an accuracy of 97.7% in determining the presence of defects in images. The accuracy and real-time performance of defect detection were significantly improved, reducing the daily operation and maintenance costs of photovoltaic power plants and fundamentally improving the power generation efficiency and overall profitability of photovoltaic enterprises.