Application of S＿Kohonen Network in Fault Identification of Circuit Breakers

LIU Yongye; MA Hongzhong; ZHANG Li; QU Bin

doi:10.13296/j.1001-1609.hva.2020.03.030

您当前的位置：

首页 >

文章列表页 >

Application of S＿Kohonen Network in Fault Identification of Circuit Breakers

更新时间：2025-04-26

- Application of S＿Kohonen Network in Fault Identification of Circuit Breakers
- High VoltageApparatus Vol. 56, Issue 3, Pages: 203-209(2020)
- 作者机构：
  
  1. 河海大学能源与电气学院
  2. 国网天津市电力公司电力科学研究院
- 作者简介：
- 基金信息：
- DOI：10.13296/j.1001-1609.hva.2020.03.030
  CLC： TM561
- Published：2020
- 稿件说明：
移动端阅览
[1]刘勇业,马宏忠,张利,屈斌.S＿Kohonen网络在断路器故障识别中的应用[J].高压电器,2020,56(03):203-209.

LIU Yongye, MA Hongzhong, ZHANG Li, et al. Application of S＿Kohonen Network in Fault Identification of Circuit Breakers[J]. High voltageapparatus, 2020, 56(3): 203-209.
[1]刘勇业,马宏忠,张利,屈斌.S＿Kohonen网络在断路器故障识别中的应用[J].高压电器,2020,56(03):203-209. DOI： 10.13296/j.1001-1609.hva.2020.03.030.

LIU Yongye, MA Hongzhong, ZHANG Li, et al. Application of S＿Kohonen Network in Fault Identification of Circuit Breakers[J]. High voltageapparatus, 2020, 56(3): 203-209. DOI： 10.13296/j.1001-1609.hva.2020.03.030.

摘要

针对断路器操动机构常见故障问题

提出将改进的Kohonen网络对断路器典型故障进行诊断研究。首先

在某试验基地建立断路器监测实验平台

模拟操动机构典型故障。然后

分析采集到的合闸振动信号

采用3层小波包变换对降噪后的振动信号进行分解

得到各频段能量占总能量的百分比

利用粗糙集理论对特征参数进行知识约简

降低特征参数的维数。最终保留第1-4及第7频段。将保留的5个特征参数归一化处理后组成特征向量输入到S

ohonen网络

对故障类型进行识别。实验结果表明

故障识别效果较好

且置信度高。

Abstract

Aiming at the issue of common failure problems of circuit breaker

the improved Kohonen network is proposed to diagnose the typical faults of circuit breakers.First

a monitoring experimental platform of circuit breaker is established in a test site

and the typical failure of the operating mechanism is simulated.Then

the closing vibration signal is analyzed and decomposed by three-layer wavelet packet transform after noise reduction to get the percentage of energy in each frequency band in total energy.Then the rough set theory is used to reduce the dimensionality of eigenvectors.At last

the first

second

third

fourth and seventh frequency bands are kept.The five feature parameters that are retained are normalized and then entered into S

onen network to identify the fault type.The experimental result shows that the fault identification effect is better with a high degree of confidence.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Simulation Analysis and Type Identification Method for Lightning Strike Faults on 500 kV Transmission Lines

Fault Classification Method of Circuit Breaker Based on Improved Phase Trajectory Features of Coil Currents

Analysis on Oil Cylinder Cracking of Energy Storage Mechanism for 500 kV Circuit Breaker

Study on Electromagnetic Transient Characteristics During Switching Operation of 750 kV GIS Substation

Adjustment and Optimization Analysis Method of Opening Time for Circuit Breaker

Related Author

LIU Jiajun

LI Chenjing

HOU Tao

XU Haokun

WANG Bo

CHEN Yaqi

FAN Ruixiang

ZOU Yang

Related Institution

School of Electrical Engineering, Xi'an University of Technology

Institute of Electric Power Science, State Grid Jiangxi Electric Power Co., Ltd.

School of Information Engineering, Nanchang Hangkong University

State Grid Henan Electric Power Company

China Power Construction Group Henan Electric Power Survey and Design Institute

⁰