摘要
近年来,随着微电网技术的持续发展,电力用户对其供电可靠性的要求也不断提高,因此微电网故障诊断研究也变得越来越重要。提出了一种基于极大重叠离散小波变换(MODWT)和反向传播(BP)神经网络的微电网故障诊断新方法,并通过仿真与算例进行了验证。结果表明:该方法能快速、准确地识别出故障类型,且不受故障初始相位角和过渡电阻等因素的影响;与现有的基于离散小波变换和反向传播神经网络的诊断方法相比,所提出的方法可以提供更好的故障分类精度。
Recent years have seen continual development of microgrid technologies and higher demands on the reliability of power supply by its customers.Research on microgrid fault diagnosis is becoming increasingly important.In this paper,a new method for microgrid fault diagnosis is proposed based on maximum overlap discrete wavelet transform(MODWT)and back propagation(BP)neural network.And it is tested by simulation and numerical examples.Results show that it can quickly and accurately identify the types of fault,and is not affected by the initial phase angle of faults and the transition resistances.Compared with existing diagnosis method based on discrete wavelet transform and back propagation neural network,the proposed method can provide significantly better fault classification accuracy.
作者
陈佳慧
高彦杰
靳一玮
CHEN Jiahui;GAO Yanjie;JIN Yiwei(School of Electronics and Information Engineering,Shanghai University of Electric Power,Shanghai200090,China)
出处
《上海电力大学学报》
CAS
2021年第1期57-60,77,共5页
Journal of Shanghai University of Electric Power
关键词
微电网
极大重叠离散小波变换
反向传播神经网络
故障诊断
microgrid
maximum overlap discrete wavelet transform
back propagation neural network
fault diagnosis