柔性直流配电网中接地故障检测技术研究

打开文本图片集

DOI：10.15938/j. emc.2025.04.006

中图分类号：TM77 文献标志码：A 文章编号：1007-449X（2025）04-0054-11

Research on fault detection technology of flexible DC distribution network

ZHENG Feng¹，LU Jiawen¹，LIN Yanzhen²，LIANG Ning （1.School of Electrical Engineering and Automation，Fuzhou University，Fuzhou ，China; 2. State Grid Fujian Electric Power Co.，Ltd.，Fuzhou ，China; 3.Faculty of Electric Power Enginering，Kunming Universityof Science and Technology，Kunming 65050o，China）

Abstract：To solve the problems of flexible DC power distribution system，including flexible operations， multiple fault types，and dificulty in fault identification，a fault detection method based on K-L divergence optimization variational mode decomposition （VMD） and convolution neural network （CNN） combined with Inception was proposed. Firstly，K-L VMD method was used to extract the feature component of the time-domain waveform of the positive transient voltage atthe fault point，and the identification criterion was constructed using the feature modal component. Then，CNN training was performed on the sampled data to obtain the optimal parameters of the model. Finally，a 10kV two-end DC distribution network structure based on modular multilevel converter （MMC）was built using the simulation platform to verify effctiveness of the proposed method. Simulation experiments show that K-L divergence optimization variational mode decomposition has good generalization ability and anti-interference ability to the simulation data. The proposed fault detection method is effective and has strong sensitivity to the identification of various fault types and can accurately identify the fault types.

Keywords：flexible DC distribution network； K-L divergence optimization； variational modal decomposi-tion；convolutional neural network ； fault detection；modular multilevel converter

0引言

随着光伏和储能等分布式电源的快速发展，交流配电网正面临着供电走廊紧张、线路损耗大以及电能质量差等一系列问题。（剩余15821字）