基于反馈神经网络的电压暂降特征量实时检测方法

Voltage sag real-time detection method based on feedback neural network

动态电压恢复器(DVR)主要用于补偿电压暂降,而实现电压暂降特征量快速、准确地检测是电压暂降补偿的前提。本文提出了一种基于反馈型神经网络的电压暂降快速、实时检测方法,探讨了该方法的建模问题和仿真技术。该方法利用反馈神经网络实现了在误差最小条件下的电压暂降检测,检测精度高、响应速度快、实时性好,为实现快速、准确电压暂降检测提供了一种新方法。仿真结果证明了该方法的有效性和优良性能。

A dynamic voltage restorer （DVR） that can keep voltage sags away from sensitive loads is mainly used for compensating the voltage sags.However,the real-time detection of voltage sags is required as this information is normally embedded within the core of a main DVR control scheme.A new scheme for real-time detecting voltage sags is proposed in this paper based on feedback neural network,which is able to compute the phase shift and voltage reduction of the supply voltage.The average delay model has better stability,and the detect model can make good real-time detection.Simulation results show that the dynamic process of detecting waveforms is fast,the proposed scheme is an efficacious way to detect voltage sags,and its validity is validated by the simulation results.