摘要
为提高风电变流器的故障诊断准确率,针对双馈式风电变流器IGBT模块的单一开路和双开路故障问题,提出了一种基于变分模态分解和随机森林算法的风电变流器开路故障诊断方法。首先将采集到的三相电流信号进行变分模态分解,再采用各个模态函数分量的峰度、均值、方差来进行数据降维以提取数据特征,最后将提取到的特征输入随机森林模型进行模型训练和故障识别。实验结果表明,相较于其它方法,基于变分模态分解和随机森林算法的故障诊断方法具有更好的故障分类效果。
In order to improve the fault diagn osis accuracy of wind power converter,aiming at the single open circuit and double open circuit faults of IGBT module of doubly fed wind power converter,an open circuit fault diagnosis method of wind power converter based on varia tional modal decomposition and random forest algorithm is proposed.Firstly,the collected three-phase current signal is decomposed by variational mode deco mposition,and then the kurtosis,mean value and variance of each modal fun ction component are used to reduce the dimension of data to extract data features.Finally,the extracted features are input into the random forest model for model training and fault identification.The experimental results show that the fault diagnosis method based on variational modal decomposition and random forest algorithm has better fault classification effect compared with other methods.
作者
杨荣昆
朱尤成
樊瑞
浦绍防
YANG Rong-kun;ZHU You-chen;PAN Rui;PU Shao-fang(Guodian Power Yunnan New Energy Development Co.,Ltd,Dali Yunnan 671000,China)
出处
《计算机仿真》
2024年第7期161-165,共5页
Computer Simulation
关键词
风电变流器
变分模态分解
随机森林算法
Wind power converter
Variational modal decomposition
Random forest algorithm
