EEMD-PE与ELM相结合的输电线路故障检测方法

Transmission Lines Fault Detection Based on EEMD-PE Coupled with ELM

输电线路发生故障时,故障电流信号中包含了大量用于故障检测的有效信息,由于大多数信号均具有非线性、非平稳性的特点,故难以从中充分提取故障特征,导致现有输电线路故障检测准确率较低。为此,提出了一种输电线路故障检测的新方法。该方法首先利用多小波的消噪性能对原始信号进行消噪,再利用集合经验模态分解(EEMD)对消噪后的信号进行自适应分解,得到一系列本征模态函数(IMFs),并基于排列熵(PE)原理从中提取故障特征向量训练用于故障检测的极限学习机(ELM)。PSCAD/EMTDC仿真结果表明,所提方法对输电线路不同类型故障检测所需时间短、准确率高。

Current signals of transmission lines contain a large amount of effective information for detection of fault.However,it is difficult to extract the fault features completely because of its characteristics of nonlinearity and non-stationarity,which leads to a problem of relatively low accuracy of fault type identification.In order to solve this problem,this paper proposes a new method for detection of transmission line fault.Firstly,EEMD method is used to adaptively decompose the signals into a series of intrinsic mode function(IMF),which are denoised by multi-wavelet method.Then,the fault features contained in IMFs are extracted by permutation entropy.Finally,The ELM classifier is obtained by training sets.The PSCAD/EMTDC simulation results show that the proposed approach is robust and fast for detection of different faults.