摘要
研究了永磁同步风力发电机组网侧功率变流器开关器件的开路故障问题,提出一种新的开路故障诊断方法,以实现对单个或两个开关器件同时开路的多种故障进行诊断。首先采集不同故障下网侧功率变流器的电压信号作为原始信号,利用小波变换对此信号进行分解和重构,再对小波变换后得到的数据进行特征分析和判定,将特征分析和判定后的数据作为BP神经网络的输入进行决策分类。仿真结果表明,该方法能够区分网侧功率变流器多开路故障,且诊断准确率高。
On the basis of the research of open circuit fault of switching devices of grid side power converter for the PM⁃SWG(permanent⁃magnet synchronous wind generator)set,a new method of open circuit fault diagnosis is proposed to realize multiple fault diagnosis when single or double switching devices are open at the same time.The voltage signal of the grid side power converter under different faults is collected as the original signal,which is decomposed and reconstructed by wavelet trans⁃form.The data obtained by wavelet transform are subjected to feature analysis and determination.The data after feature analysis and determination are used as the input of BP neural network for decision classification.The simulation results show that this method can distinguish the multiple open circuit faults of the grid side power converter,and its diagnosis accuracy is high.
作者
张靖轩
孙鹤旭
孙泽贤
徐勤奇
邹文仲
ZHANG Jingxuan;SUN Hexu;SUN Zexian;XU Qinqi;ZOU Wenzhong(School of Artificial Intelligence,Hebei University of Technology,Tianjin 300130,China;College of Electrical Engineering,North China University of Science and Technology,Tangshan 063210,China;Nanjing Nari-Relays Electric Co.,Ltd.,Nanjing 211102,China)
出处
《现代电子技术》
2021年第1期162-166,共5页
Modern Electronics Technique
基金
河北省科技计划项目(17214304D)
河北省教育厅科技项目(QN16214510D)。
关键词
风力发电机组
功率变流器
故障诊断
小波变换
神经网络
电压信号分解
wind generator set
power converter
fault diagnosis
wavelet transform
neural network
voltage signal decom⁃position
作者简介
张靖轩(1982—),男,河北唐山人,硕士,讲师,研究方向为风力发电机组功率变流器的故障诊断和故障预测;孙鹤旭(1956—),男,博士生导师,主要从事新能源发电技术的工作。
