Abstract：Aiming at the problem of fault location difficulty caused by the increase of structural complexity of line-commutated converter (LCC)-modular multilevel converter (MMC) hybrid three- terminal ultra high voltage direct current (UHVDC) transmission line, a single-pole grounding fault location method for UHVDC transmission line based on multi-resolution singular value decomposition (MRSVD) - gated current unit (GRU) neural network is proposed. First, select the fault line and judge the fault line section. Then, the double-terminal voltage fault waveform is decomposed layer by layer and reconstructed by MRSVD. Finally, the GRU neural network model is built to locate the fault, and the model parameters are set by particle swarm optimization (PSO) algorithm to improve the accuracy of fault location. The ±800kV LCC-MMC hybrid three-terminal UHVDC transmission system is built using PSCAD/EMTDC software, and the simulation of different transition resistance values and different fault distances is carried out. The simulation results show that the proposed fault location method has high accuracy and can provide a new solution for single-pole grounding fault location of hybrid three- terminal UHVDC transmission lines.
李志川, 兰生, 魏柯. 基于MRSVD-GRU的混合三端特高压直流输电线路单极接地故障定位方法[J]. 电气技术, 2023, 24(3): 1-8.
LI Zhichuan, LAN Sheng, WEI Ke. Single-pole grounding fault location method of hybrid three-terminal ultra-high voltage direct current transmission line based on MRSVD and GRU. Electrical Engineering, 2023, 24(3): 1-8.
2023, Vol. 24 
