Fault diagnosis of MMC-MTDC based on traveling wave characteristics and KOA-CNN-BiGRU-AM

YU Bo

English Version Reader LoginJournal Login

您当前的位置：

首页 >

文章列表页 >

Fault diagnosis of MMC-MTDC based on traveling wave characteristics and KOA-CNN-BiGRU-AM

更新时间：2025-10-23

- Fault diagnosis of MMC-MTDC based on traveling wave characteristics and KOA-CNN-BiGRU-AM
- Vol. 44, Issue 2, Pages: 185-196(2025)
- 作者机构：
  
  三峡大学电气与新能源学院,湖北,宜昌,443002
- 作者简介：
- 基金信息：
- DOI：
  CLC： TP18;TM712;TM773
- Published：2025
- 稿件说明：
移动端阅览
YU Bo. Fault diagnosis of MMC-MTDC based on traveling wave characteristics and KOA-CNN-BiGRU-AM[J]. 2025, 44(2): 185-196.
DOI：

YU Bo. Fault diagnosis of MMC-MTDC based on traveling wave characteristics and KOA-CNN-BiGRU-AM[J]. 2025, 44(2): 185-196. DOI：

摘要

针对多端柔性直流电网（multi-terminal direct current grid based on modular multilevel converter

MMC-MTDC）故障诊断存在的人工整定阈值过程复杂、高阻故障不易检测的问题，提出一种基于行波特征的诊断方法。首先，通过分析系统的故障特征，得出边界元件对高频信号的阻滞作用；其次，利用经验模态分解（empirical mode decomposition

EMD）对功率进行分解，得到本征模态函数（intrinsic mode function

IMF）分量，将其能量值作为故障特征量训练由卷积神经网络（convolutional neural network

CNN）和双向门控循环单元（bidirectional gated recurrent unit

BiGRU）组成的CNN-BiGRU网络；然后，采用开普勒优化算法（Kepler optimization algorithm

KOA）和注意力机制（attention mechanism

AM）对CNN-BiGRU网络进行改进，实现MMC-MTDC的故障诊断；最后，在PSCAD/EMTDC中搭建仿真模型。结果表明，该方法不仅可以实现母线故障和线路故障的检测，还可以在满足保护可靠性和速动性的前提下

解决高阻故障保护易拒动的问题。

Abstract

Based on travelling wave features

a diagnostic method is proposed to address the complexity of manual threshold setting process and the difficulty of detecting high-resistance faults in the fault diagnosis of multi-terminal direct current grid based on modular multilevel converter （MMC-MTDC）. Firstly

the blocking effect of boundary elements on high-frequency signals is identified by analyzing the fault characteristics of the system. Secondly

empirical mode decomposition （EMD） is employed to decompose power signals into intrinsic mode function （IMF）

and the energy values of the IMF is utilized as fault features to train the CNN-BiGRU network composed of convolutional neural network （CNN） and bidirectional gated recurrent unit （BiGRU）. On this basis

the Kepler optimization algorithm （KOA） and attention mechanism （AM） are employed to enhance the CNN-BiGRU network to realize the fault diagnosis of the MMC-MTDC. Finally

the simulation model is built in PSCAD/EMTDC. The results show that the method can not only realize the detection of bus faults and line faults but also solve the problem of easy refusal of protection under the high resistance state while meeting the requirements of protection reliability and speed.

关键词

Keywords

references

Views

303

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

A Fault Self-diagnosis Mechanism for Multiplexing Optical Channels of Relay Protection

Fault-tolerant Control System of PWM RectifierBased on NCAV and Circuit Equivalent Replacement

Fault diagnosis algorithm for wind power rectifier based on real-time current amplitude

Bipolar short circuit protection strategy for MMC based medium voltage DC distribution network

Distribution network fault diagnosis technology based on synchronous waveforms

Related Author

CAI Bo

QIN Wei

HUANG Kai

LYU Jiale

XU Mingming

LIU Wenze

QIAN Guochao

YUAN Mingzhe

Related Institution

National Energy Power Control and Protection Research and Development Center(Nanjing NR Electric Co., Ltd.)

Nanjing University of Science and Technology

School of Energy and Power Engineering, Nanjing University of Science and Technology

School of Electrical Engineering, Southeast University

State Grid Henan Power Company Electric Power Research Institute

AI问答

⁰