Application of Fusion Algorithm of Insulator Partial Discharge Acoustic Characteristics and Image Identification in Electricity Transmission Line Detection

Abstract

Traditional electricity transmission line detection methods usually rely on a single technical means and lack multi-dimensional comprehensive diagnosis, resulting in insufficient accuracy and comprehensiveness in fault identification. This paper constructs an electricity transmission line detection model based on the insulator partial discharge acoustic characteristics and image identification technology to improve the accuracy and intelligence level of fault detection. During model building, the acoustic characteristics and image data of insulator partial discharge are first obtained through the equipment. After data preprocessing, it is input into the convolutional neural networks (CNN) and recurrent neural networks (RNN) for training. Through parameter optimization, the model shows high efficiency and accuracy in electricity transmission line fault detection. Experimental results show that the model exhibits good efficiency and accuracy in electricity transmission line fault detection through parameter adjustment. According to the experimental results, the detection accuracy of the proposed model on various data sets is 93.40%, 91.50%, and 89.20%, respectively, better than that of other control models, and the processing time is 118 seconds, 182 seconds, and 238 seconds, respectively, also better than that of control groups. In conclusion, the model constructed in this paper provides a reliable and effective method for electricity transmission line fault detection and lays a foundation for the advancement of related technologies.