110 kV Power Cable External Disturbance Optical Fiber Sensing Detection and Identification Method Based on ResNeXt and Attention Mechanism

Abstract

Power cable is a core equipment for the operation of power transmission and distribution systems. Effective detection and identification of external disturbances of power cable is of great significance to the stable operation of power transmission and distribution systems. Optical fiber sensor has the characteristics of antielectromagnetic interference and small size and is widely used in built-in detection of equipment. Based on 110 kV power cable and optical fiber Mach-Zehnder interferometer (MZI), the signal difference between built-in optical fiber and external optical fiber is compared, and the effectiveness of built-in optical fiber detection is verified. Subsequently, the detection performance of built-in optical fiber under four different external disturbances is studied, and the signal denoising method based on slime mould algorithm-variational mode decomposition (SMA-VMD) is used for the built-in optical fiber detection signal to obtain 1-D data with improved quality. The Gramian angular field (GAF) is used for time-frequency joint analysis to expand the 1-D information into a 2-D image for ResNeXt to identify the type of external disturbance. By introducing the attention mechanism, the recognition rate of the system is improved. The results show that the best recognition index of the model can reach 98.35%. This method provides a new idea for the detection of external disturbances of intelligent power cables.