基于多特征融合和SVM的串联电弧故障检测方法

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

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。

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%.