Electrical equipment thermal defect identification method and system

The invention relates to an electrical equipment thermal defect identification method and system, and the method comprises the steps: collecting a visible light image and an infrared light image of to-be-identified electrical equipment, and carrying out the preprocessing of the visible light image and the infrared light image; carrying out image fusion on the pre-processed visible light image and infrared light image to obtain a fused image; and inputting the fused image into an improved YOLOv4 model, outputting a local fused image, inputting the local fused image into a thermal defect identification model, performing continuous optimization by using Bayesian hyper-parameters, and outputting a thermal defect identification result. According to the method, the two kinds of image information data are considered and fused, and the local extraction model and the recognition model are improved, so that the problems that in the prior art, single image information data is used for recognizing the thermal defects of