Series Arc Fault Detection Method Based on Multi-feature Fusion and SVM

GUO Min; WU Ning; GUO Xiaoxuan; LU Jianbin; CHEN Weidong

doi:10.14044/j.1674-1757.pcrpc.2024.03.018

您当前的位置：

首页 >

文章列表页 >

Series Arc Fault Detection Method Based on Multi-feature Fusion and SVM

Application Technology in the Field of Clean Energy | 更新时间：2024-09-14

- Series Arc Fault Detection Method Based on Multi-feature Fusion and SVM
- Power Capacitor & Reactive Power Compensation Vol. 45, Issue 3, Pages: 137-149(2024)
- 作者机构：
  
  1.广西电网有限责任公司电力科学研究院，南宁　 530023
  2.广西电力装备智能控制与运维重点实验室，南宁　 535023
- 作者简介：
- 基金信息：
- DOI：10.14044/j.1674-1757.pcrpc.2024.03.018
  CLC：
- Published：2024-06，
  
  Received：26 December 2023，
- 稿件说明：
移动端阅览
GUO MIN, WU NING, GUO XIAOXUAN, et al. Series Arc Fault Detection Method Based on Multi-feature Fusion and SVM. [J]. Power capacitor & reactive power compensation, 2024, 45(3): 137-149.
DOI：

GUO MIN, WU NING, GUO XIAOXUAN, et al. Series Arc Fault Detection Method Based on Multi-feature Fusion and SVM. [J]. Power capacitor & reactive power compensation, 2024, 45(3): 137-149. DOI： 10.14044/j.1674-1757.pcrpc.2024.03.018.

摘要

针对现有的传统电气保护装置无法对串联电弧故障进行有效检测的问题，本文提出一种基于多特征融合和改进SVM的串联电弧故障检测方法。首先，通过搭建电弧故障平台进行电弧实验，获得典型负载在电路正常运行及发生电弧故障时的电流信号；然后，对采集到的电流信号进行时域、频域和时频域分析，构建串联电弧特征指标集；最后，将串联电弧特征指标集作为SVM的输入向量，并利用粒子群算法对SVM进行优化，提高分类模型的准确率。测试结果表明，采用本文所提方法进行串联故障电弧识别的准确率达到95%以上。

Abstract

For the problem that the existing traditional electrical protection device cannot effectively detect the series arc fault

a kind of series arc fault detection method based on multi-feature fusion and improved SVM is proposed in this paper. Firstly

the arc experiment is performed by setting up an arc fault platform

the current signal of typical loads during normal operation and arc faults are obtained; Then

the collected current signals are subjected to time domain

frequency domain and time-frequency domain analysis to construct series arc feature index set; Finally

the series arc feature index set is taken as the input vector of SVM

and the particle swarm algorithm is used to optimize the SVM so to improve the accuracy of the classification model. The test results show that the accuracy rate of series faults arc identification using the the method proposed in this paper reaches more than 95%.

关键词

串联电弧故障识别特征提取支持向量机粒子群算法

Keywords

series arc faultfault recognitionfeature extractionSVMPSO

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Series Arc Fault Detection Method Based on Multi-feature Fusion and Random Forest

Analysis of the Influence of MPPT Algorithm on Power Quality for Photovoltaic Grid Connected System

Related Author

LI Shiguang

SHEN Mengxi

ZHANG Mengsha

GAO Zhengzhong

WU Rao

JIA Junzheng

Related Institution

College of Electrical Engineering and Automation,Shandong University of Science and Technology

⁰