EMD-CNN model based condition monitoring and fault warning for power overhead optical cable communication

Abstract

Optical fiber communication has become the main communication mode of power communication in China. As the carrier and foundation, the stability and security of power communication optical cable is directly related to the reliability and security of power communication network in China. In this paper, the idea of in-depth learning is introduced into the condition monitoring of communication optical cable, taking the all-dielectric self-supporting optical cable (ADSS) as an example. By transforming the image into picture set and choosing the appropriate depth neural network model to analyse the picture, the condition monitoring of communication optical cable can be realized.