半月刊

ISSN 1000-1026

CN 32-1180/TP

+高级检索 English
基于并联卷积神经网络的多端直流输电线路故障诊断
作者:
作者单位:

东北大学信息科学与工程学院,辽宁省 沈阳市 110819

作者简介:

通讯作者:

基金项目:


Fault Diagnosis of Multi-terminal HVDC Transmission Line Based on Parallel Convolutional Neural Network
Author:
Affiliation:

College of Information Science and Engineering, Northeastern University, Shenyang 110819, China

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
    摘要:

    针对多端直流输电(MTDC)线路故障时存在故障电流上升速度快、峰值大、不易定位等特点,提出一种兼顾快速性与准确性的MTDC线路故障诊断方法。首先,分析MTDC线路故障信号波形的幅值特征和频率特征,研究基于信号波形幅值变化特征的MTDC线路故障幅值特征提取方法和基于小波包分析的MTDC系统故障频率特征提取方法,进而形成基于幅值-频率特征的MTDC线路故障诊断方法。其次,构建具有故障分类支路和故障定位支路的双支路结构卷积神经网络——并联卷积神经网络(P-CNN),提出基于迁移学习的P-CNN训练方法。最后,仿真验证基于P-CNN的MTDC线路故障诊断方法满足故障诊断的快速性,验证其并联结构相比于其他人工智能故障诊断方法更具有准确性和可拓展性。

    Abstract:

    In view of the fault characteristics of multi-terminal HVDC (MTDC) transmission lines, such as rapid rising speed, large peak value of fault current and difficulty in fault location, a fault diagnosis method for MTDC system with both rapidity and accuracy is proposed. Firstly, the amplitude and frequency characteristics of fault signal waveforms of MTDC transmission line faults are analyzed. The extraction methods for fault amplitude and frequency features of MTDC transmission line faults are studied separatedly based on amplitude variation characteristics of signal waveforms and wavelet packet analysis.Then, the fault diagnosis method of MTDC transmission system based on amplitude-frequency characteristics is formed. Secondly, the parallel convolutional neural network (P-CNN) with fault classification and fault location branch is constructed, and the training method of P-CNN based on transfer learning is proposed. Finally, the simulation verifies that the fault diagnosis method of MTDC system based on P-CNN meet the fast requirements, and the parallel structure is more accurate and expandable than other artificial intelligence fault diagnosis methods.

    表 4 幅值-频率互补效果验证Table 4 Validation of amplitude-frequency complementarity effects
    表 3 人工智能算法故障诊断结果Table 3 Fault diagnosis results of artificial intelligence algorithms
    表 1 故障与直流电气信号关系Table 1 The relationship between faults and DC electrical signals
    图1 四端直流输电系统拓扑Fig.1 Topology of four-terminal HVDC transmission system
    图2 MTDC故障特征灰度图Fig.2 Gray diagram of MTDC fault characteristics
    图3 P-CNN结构图Fig.3 Structure diagram of P-CNN
    图4 P-CNN训练过程简图Fig.4 Simplified training process diagram of P-CNN
    图5 正极接地故障的电气信号波形图Fig.5 Electrical signal waveforms of positive grounding faults
    图 直流正极接地故障Fig. DC positive grounding fault
    图 直流负极接地故障Fig. DC negative grounding fault
    图 直流两极短路故障Fig. DC bipolar short circuit fault
    图 交流单相接地故障Fig. AC Single Phase Grounding Fault
    图 交流两相短路故障Fig. AC Two-Phase Short Circuit Fault
    图 交流三相短路故障Fig. AC Three-phase Short Circuit Fault
    参考文献
    相似文献
    引证文献
引用本文

王浩,杨东升,周博文,等.基于并联卷积神经网络的多端直流输电线路故障诊断[J/OL].电力系统自动化,http://doi.org/10.7500/AEPS20191124003.
WANG Hao,YANG Dongsheng,ZHOU Bowen,et al.Fault Diagnosis of Multi-terminal HVDC Transmission Line Based on Parallel Convolutional Neural Network[J/OL].Automation of Electric Power Systems,http://doi.org/10.7500/AEPS20191124003.

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2019-11-24
  • 最后修改日期:2020-03-12
  • 录用日期:2019-12-04
  • 在线发布日期:
  • 出版日期: