基于EMD和SVM的电力系统故障分类识别

Fault Classification in Power System Using EMD and SVM

近年来,电能质量问题已经成为当今电力工程领域里亟待解决的问题,而电力系统故障诊断分类是改善电能质量和保护电力系统的一个重要环节。提出了一种基于经验模态分解(EMD)和支持向量机(SVM)的电力系统线路故障分类识别方法。采用EMD将传输线电压信号分解成有限个本征模函数(IMF);通过希尔伯特-黄变换(HHT)提取故障特征量,建立SVM模型对10种不同的电力系统故障进行分类。在MATLAB/SIMULINK环境下进行建模仿真分析,结果表明,将EMD和SVM结合在一起可以建立有效的分类器,能够准确地识别各类典型故障。

In recent years,power quality has become the main problem in the power field.Faults classification of power system is the first stage of improving power quality and protecting the system.In this paper,faults classification of power system using Empirical Mode Decomposition(EMD) and Support Vector Machines(SVMs) is proposed.EMD is used for decomposing voltages of transmission line into Intrinsic Mode Functions(IMFs).Hilbert Huang Transform(HHT) is used for extracting fault features from IMFs.A multiple SVM model is designed to classfy 10 faults in the power system.Algorithm is validated using MATLAB/SIMULINK environment.Results demonstrate that the combination of EMD and SVM can be an efficient classifier which can accurately distinguish the faults.