Abstract: The equipment of transmission and substation is susceptible to various faults and local abnormal heating phenomena due to various factors such as surface aging and natural disasters during long-term operation. Therefore, this study focuses on the application of deep learning in fault state detection of power transmission and transformation equipment. The article uses a quadcopter drone equipped with an infrared thermal imager to capture infrared images of power transmission and transformation equipment, and performs preprocessing such as grayscale, denoising, and enhancement on the collected images. Based on deep learning theory, a convolutional neural network model is constructed to input the preprocessed infrared images, identify local abnormal heating targets in the images, and achieve fault state detection of power transmission and transformation equipment. The experimental results show that the designed convolutional neural network model can accurately detect local abnormal heating fault targets in infrared images of power transmission and transformation equipment, verifying the practical application effect of deep learning in fault state detection of power transmission and transformation equipment.