Intelligent Detection Technology of Infrared Image of Substation Equipment Based on Deep Learning Algorithm

The safe and reliable operation of power equipment is the basis to ensure the reliability of power supply. The infrared detection technology of operating equipment has the advantages of no power failure, no contact, high sensitivity and mature technology, which can find equipment defects in time and effectively. However, the conventional manual inspection for infrared detection has the problems of large workload, long time-consuming and low efficiency, which restricts the large-scale popularization and application. Based on the above background, this paper constructs an accurate recognition model of substation equipment infrared image based on improved YOLOv3 algorithm, realizes the automatic real-time positioning of infrared image target image, and puts forward a complete fault diagnosis scheme for current and voltage overheating defects. The field test results show that the infrared image intelligent detection technology based on deep learning algorithm proposed in this paper can effectively realize the fault diagnosis of heating defects of substation equipment. This technology improves the state control ability of substation equipment, which is of great significance to promote the safe and stable operation of substation and improve the reliability of power supply.