基于优化神经网络的电网谐波检测方法

为了检测电力系统中的谐波,本文提出了一种基于优化神经网络的电网谐波测量方法.该方法应用一个结构和训练算法都优化了的多层前馈神经网络(MLFNN)对电网中的谐波进行检测,即首先考虑到神经网络的权值记忆负担主要来自谐波幅值和相角的变化,因此先对相角进行确定;再用基于神经网络理论方法对幅值进行检测,并使每一个输出神经元都对应于自己的隐层;然后利用多层前馈神经网络对当前及上一时刻的采样值进行分析,实现了对电网谐波的检测.实验仿真结果证明了该方法的有效性.

Power network harmonic detection methods based on artificial neural network

An artificial neural network approach based on MLFNN for measuring harmonics in force system is proposed. The memory burden of net weight is mainly from the change of amplitude and phase when the MLFNN is applied to harmonic measurement, so harmonic phase should be decided in the firt place. Then the amplitude is measured by neural network algorithm, and make sure every nerve cell has its own frame. Afterwards analyze and calculate the sample value of current as well as the last moment time, and eventually detection of power network harmonic can be achieved. Simulation results show that the harmonic components can be detected in real time and with high precision.