基于随机森林算法的风电变流器开路故障诊断
Open Circuit Fault Diagnosis of Wind Power Converter Based on Random Forest Algorithm
杨荣昆 1朱尤成 1樊瑞 1浦绍防1
作者信息
- 1. 国电电力云南新能源开发有限公司,云南 大理 671000
- 折叠
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.
Abstract
In order to improve the fault diagnosis accuracy of wind power converter,aiming at the single open cir-cuit 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 variational modal decomposition and random forest algorithm is proposed.Firstly,the collected three-phase current signal is decomposed by variational mode decomposition,and then the kurto-sis,mean value and variance of each modal function component are used to reduce the dimension of data to extract da-ta features.Finally,the extracted features are input into the random forest model for model training and fault identifi-cation.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.
关键词
风电变流器/变分模态分解/随机森林算法Key words
Wind power converter/Variational modal decomposition/Random forest algorithm引用本文复制引用
出版年
2024
NETL
NSTL
万方数据