基于变分模态分解与精细复合多尺度散布熵的发电机匝间短路故障诊断

Fault diagnosis of generator interturn short circuit fault based on variational mode decomposition and refined composite multiscale dispersion entropy

针对多极发电机匝间短路故障诊断与识别难度高的问题,提出了变分模态分解与精细复合多尺度散布熵结合的方法处理发电机定子振动信号。所提方法应用变分模态分解将原始信号分解为多个模态分量,并依据峭度和相关系数原则选取2个不同分量进行信号的重构,应用精细复合多尺度散布熵来进行重构信号的分类及故障识别。对3对极发电机匝间短路故障前、后定子振动数据的处理效果表明,所提方法可以对发电机匝间短路故障进行有效识别与诊断,与其他多尺度熵方法相比具有一定优越性。

To overcome the difficulty of diagnosis and identification of interturn short circuit fault in multipole generator,a method combining VMD(Variational Mode Decomposition)and RCMDE(Refined Composite Multiscale Dispersion Entropy)is proposed to process the stator vibration signal of generator.VMD is used to decompose the original signal into multiple modal components,and two different components are selected based on the principles of kurtosis and correlation to reconstruct the signal,and RCMDE is used for reconstructed signal classification and fault identification.The proposed method is used to process the stator vibration signal of 3 pole-pair generator before and after interturn short circuit fault,the results show that the proposed method can effectively identify and diagnose the generator interturn short circuit fault and has certain advantages compared with multiscale entropy methods.