摘要
针对现有被动孤岛检测法检测盲区大、准确率不高的问题,提出了一种小波包(Wavelet Packet Transform,WPT)、变分模态分解(Variational Mode Decomposition,VMD)和BP神经网络相结合的孤岛检测法.采集光伏电站公共耦合点(PCC)处工况数据,并利用WPT对电压波形中的特定频率成分进行滤波;采用VMD将滤波信号分解为具有不同中心频率的模态分量,并将其合成所需的电压特征向量;利用BP神经网络对工况数据进行学习分类,判断是否发出并网断路器跳闸信号.通过PSCAD/MATLAB联合仿真,验证了所提孤岛检测法的有效性,并探究了不同干扰工况下该检测法的抗干扰性能.
An intelligent islanding detection method based on the combination of Wavelet Packet Transform(WPT),Variational Mode Decomposition(VMD)and BP neural network is proposed aiming at solving the problem of large non-detection zone and low accuracy during passive islanding detection.Signal data at the Point of Common Coupling(PCC)of PV station is sampled,and the WPT is used to filter out the specific frequency components.The voltage signals are decomposed to many modes which have different center frequency by VMD,then the voltage vectors are obtained by introducing the concept of Shannon entropy.The BP neural network is used to learn the characteristics of different operation conditions.The results of PSCAD/MATLAB simulation show the effectiveness of proposed method and high reliability even under disturbing operation conditions.
作者
王增雯
黄文聪
常雨芳
WANG Zengwen;HUANG Wencong;CHANG Yufang(Hubei Key Laboratory for High-efficiency Utilization of Solar Energy and Operation Control of Energy Storage System,Hubei University of Technology,Wuhan 430068,China)
出处
《中南民族大学学报（自然科学版）》
CAS
北大核心
2023年第6期759-767,共9页
Journal of South-Central University for Nationalities：Natural Science Edition
基金
国家自然科学基金资助项目(61903129)。
关键词
被动孤岛检测法
小波包变换
变分模态分解
BP神经网络
分布式电站
passive islanding detection
wavelet packet transform
variational mode decomposition
BP neural network
distributed generator
