A novel framework on intelligent detection for module defects of PV plant combining the visible and infrared images

Solar Photovoltaic (PV) industry has achieved rapid development in recent years. However, it is difficult and costly to detect the micro fault area in a large PV power plant due to environmental factors and missing data. Most faults can be detected by the infrared temperature measurement method, but the infrared camera characteristics constrain it. This paper proposed a novel framework, consisting of image acquirement, image segmentation, fault orientation and defect warning, to remedy the limitations for PV module defects. The visible and infrared PV array images are taken under the same conditions by a dual infrared camera at low altitudes. The deep learning methods, including the fifth version of You Only Look Once (YOLOv5) algorithm and Deep Residual Network (ResNet) algorithm, are introduced to this framework. Hence, this framework has strong capability to suit almost all brightness conditions, by the combination of image segmentation from visible images and fault location on infrared images. The results show that this framework dramatically improves the separation speed of photovoltaic array to 36 Fps and the accuracy of fault detection to 95% by infrared image marked with the segmented area.