基于线性神经网络的谐波检测方法研究

发布时间：2018-01-17 13:29

本文关键词：基于线性神经网络的谐波检测方法研究　出处：《电测与仪表》2014年22期 　论文类型：期刊论文

【摘要】：在比较了当今多种谐波检测方法的优缺点基础上,提出了基于线性神经网络的谐波检测方法。构造了谐波检测的网络模型,对利用该方法进行谐波检测的原理做了简单的介绍。文中运用最小均方差算法(LMS)调节网络权值W,使得误差指标达到最小值。最后构造含有奇次谐波的负载电流函数,利用MATLAB软件分别运用加汉宁窗的快速傅里叶变换(FFT)方法和构造的自适应线性神经网络方法进行仿真实验。通过实验结果表明,基于自适应线性神经网络方法的谐波检测技术具有更好的检测精度。
[Abstract]:On the basis of comparing the advantages and disadvantages of various harmonic detection methods, the harmonic detection method based on linear neural network is proposed, and the network model of harmonic detection is constructed. The principle of harmonic detection using this method is briefly introduced. In this paper, the minimum mean square error algorithm (LMS) is used to adjust the network weight W. Finally, the load current function with odd harmonics is constructed. The simulation experiments are carried out by using the fast Fourier transform (FFT) method with the Hanning window and the adaptive linear neural network method by using the MATLAB software. The experimental results show that the proposed method is effective and efficient. The harmonic detection technique based on adaptive linear neural network has better detection accuracy.
【作者单位】：东北电力大学电气工程学院;国电蚌埠发电有限公司;
【分类号】：TM935;TP183
【正文快照】： 0引言近年来,非线性负荷以及电力电子装置愈加广泛应用于电力系统中,使得谐波问题变得越来越严重。谐波的存在使设备容易过热,增加相应设备附加损耗,降低设备效率和利用率,还会使继电保护装置和自动装置误动或者拒动,有时甚至造成事故,大大降低了保护装置工作的可靠性,从而严

【参考文献】