A Single-Terminal Fault Location Method for HVDC Transmission Lines Based on a Hybrid Deep Network

High voltage direct current (HVDC) transmission systems play an increasingly important role in long-distance power transmission. Realizing accurate and timely fault location of lines is extremely for the safe operation systems. With development modern data acquisition deep learning technology, methods have feasibility engineering application location. The traditional single-terminal traveling wave method used HVDC However, many challenges exist when a high impedance occurs including sampling frequency dependence difficulty to determine velocity identify heads. In order resolve these problems, this work proposed hybrid convolutional neural network (CNN) long short-term memory (LSTM) model system containing mixed cables overhead line segments. Simultaneously, variational mode decomposition–Teager energy operator feature improve effect training. 2D-CNN was employed as classifier segments, LSTM regressor integrated segment information achieve precise experimental results demonstrate that has accuracy location, with effects types, noise, frequency, different topologies consideration.