No abstract

Temperature is one of the most common indicators for the health of electrical equipment in the substation. By now, infrared thermography has been an important monitoring tool due to its real-time temperature measurement and noncontact manner. However, at present, portable thermal imagers are usually used to collect and store the status image of single equipment at a certain time, which cannot continuously track the condition of the equipment and the efficiency is very low. In order to solve this problem, our team proposed a method for online condition of electrical equipment based on the visualization and processing of infrared image temperature data. We developed video inspection software, equipped with an infrared camera for automatic inspection to obtain infrared images. After that, the target equipment in a whole image are automatically extracted based on the reference image and the equipment type of each target is classified. Then, in order to visualize temperature data and extract temperature information for different types of equipment, the concepts of heating spot, heating section, and heating area are defined. Finally, diagnosis rules based on relevant related thermal fault diagnosis standards and past experience are proposed to evaluate the condition of each target equipment, using the temperature rise and heat generation percentage. The method has been applied in a real substation and proved its effectiveness.

No abstract

The thermal anomaly area of electrical equipment in the substation is often hidden due to its small thermal area and multiple anomalies overlaid. Accurately identify the thermal area is demanded on the condition detection of electrical equipment, where the anomaly points of electrical equipment in infrared images are generally small and of low resolution. We propose an improved YOLOv4 algorithm for infrared image anomaly area identification, which can detect the thermal generation phenomenon of electrical equipment. We add a new target detection branch to the shallow feature map of 104×104, which can better extract small target semantic information. The training process is enhanced with cosine annealing and mosaic data enhancement. We establish a total of 719 infrared images of five types of thermal anomalies electrical equipment to test our network. The accuracy of our model reach to as high as 96.78%, with a detection speed of 17 f/s and an AP@0.5 of 94.23%. Compared with SSD, YOLOv4 and Faster RCNN, the algorithm in this paper obtains the highest AP@0.5 with 94.23%, which is the best performance compared with the original YOLOv4 model in accuracy. The model is robust to noise and luminance disturbances, and still provides good recognition under disturbances.