摘要
针对双馈风机机械振动故障监测存在的信噪比低、故障监测分类差和时间长的问题,提出基于多源传感的智能双馈风机机械振动故障监测方法。首先采用信息熵度量智能双馈风机振动信号变化情况,获取信号在时频域上的信息熵特征,融合多源传感信号信息特征;然后引入全局搜索因子改进人工蜂群算法,通过改进的人工蜂群算法优化支持向量机;最后将提取并融合后的振动信号特征输入训练后的支持向量机,完成智能双馈风机机械振动故障监测。实验结果表明,所提方法的去噪效果和故障监测分类效果好、监测时间短。
Aiming at the problems of low signal-to-noise ratio,poor fault monitoring classification and long time in the mechanical vibration fault monitoring of doubly fed fans,a method for monitoring the mechanical vibration fault of the intelligent DFIG based on multi-source sensing is proposed.Firstly,information entropy is used to measure the change of the vibration signal of the intelligent doubly-fed fan,the information entropy characteristics of the signal in the time-frequency domain are obtained,and the information characteristics of multi-source sensor signals are fused;then a global search factor is introduced to improve the artificial bee colony method,and the support vector machine is optimized by the improved artificial bee colony method;finally,the extracted and fused vibration signal features are input into the trained support vector machine to complete the mechanical vibration fault monitoring of the intelligent doubly-fed fan.The experimental results show that the proposed method has good denoising effect and fault monitoring classification effect,and the monitoring time is short.
作者
谭振国
曾佳佳
牛国智
邓睿
刘旭东
TAN Zhenguo;ZENG Jiajia;NIU Guozhi;DENG Rui;LIU Xudong(Changsha Production and Operation Center,Wuling Electric Power Co.,Ltd.,Changsha 410004,China;Production Technology Department,Changsha Production and Operation Center,Wuling Electric Power Co.,Ltd.,Changsha 410004,China;New Energy Branch of Wuling Electric Power Co.,Ltd.,Changsha 410004,China)
出处
《机械与电子》
2024年第6期32-37,共6页
Machinery & Electronics
关键词
多源传感
智能双馈风机
机械振动故障
故障监测
支持向量机
multi-source sensing
intelligent doubly-fed fan
mechanical vibration fault
fault monitoring
support vector machine
