Detection Method for Heating Fault of Voltage Transformer in 220 kV Substation Based on Infrared and Ultraviolet

Excessive use of voltage transformers in 220 kV substations can lead to heating faults; therefore, a detection method based on infrared and ultraviolet radiation is proposed to ensure safe substation operation. Infrared and ultraviolet images of the voltage transformer were collected using infrared and ultraviolet imaging technologies, and a median filtering algorithm was applied to denoise the infrared images. After removing redundant information, the temperature and discharge characteristics related to infrared and ultraviolet radiation were calculated, and the resulting characteristic data were input into a radial basis function neural network. The parameters of the neural network were optimized using a quantum particle swarm optimization algorithm, improving the detection capability for heating faults in voltage transformers at 220 kV substations. Experimental results show that this method can effectively detect heating faults in voltage transformers. By analyzing the infrared and ultraviolet characteristics of the fault location, the heating fault can be identified and repaired in time, ensuring the safe operation of the substation.