基于人工神经网络的电网谐波监测的方法

Study of Harmonics Monitoring Based on Artificial Neural Network

研究人工神经网络用于波形识别是一个新的研究领域。将神经网络这一新方法引入到电网谐波在线监测中,并就它在电网谐波在线监测应用中的一系列关键问题进行了较为系统的分析。提出了一种新型电网谐波在线监测系统模型,通过带通滤波器,采样存储器以及神经网络的在线监测电路,取得谐波信号,最终达到谐波补偿的目的。其在线监测部分主要利用模拟并行测量的基本原理,构造了一个用于电网谐波在线监测的特殊多层前向神经网络。并对其进行了仿真,仿真结果表明所提出的基于人工神经网络的电网谐波在线监测的方法是可行的和有效的。

Wave recognition by artificial neural network is a new research field. In order to monitor operating status of the power system's harmonics with new method, the neural network (NN) approach is introduced. A new model about measuring harmonics on line is proposed. Through band pass filter, sampling store and the circuit of monitoring on line with artificial neural network (ANN), we can obtain the harmonics signal. The result is to compensate harmonics. Through using the basic principle of analog parallel harmonics measurement and a special multilayer feedforward neural network, a corresponding harmonics measurement on line is built. And the procedure for simulating the measurement network is given. The simulation results prove the effectiveness and exactness of the presented approach.