基于小波包和Elman神经网络异步电机转子断条故障诊断方法.docVIP

基于小波包和Elman神经网络异步电机转子断条故障诊断方法 　　摘要:提出了一种基于小波包分析(WPA)和Elman神经网络的异步电机转子断条故障诊断方法。针对异步电机转子断条故障时定子电流出现的边频分量 进行小波包分析,提取动态条件下各频带能量作为故障特征向量,削弱了负载变化及噪声对诊断准确性的影响;采用Elman神经网络对故障进行识别,并对Elman网络进行改进,在关联层增加了自反馈增益因子,提高了网络性能;以频带能量作为Elman神经网络识别故障的特征向量,建立从特征向量到电机转子断条故障之间的映射。试验结果表明:基于小波包分析提取的故障特征明显,由WPA和Elman神经网络构成的诊断系统,能有效地识别出转子断条故障,故障诊断准确率高。 　　关键词:转子断条,故障诊断,小波包分析,Elman神经网络 　　Method of Fault Diagnosis for Induction Machine Rotor Broken Bar Based on Wavelet Package and Elman Neural Network 　　Wang Xuhong1,2,He Yigang1 　　( 1 School of Electrical and Information Engineering, Hunan University, Changsha, 410082 ,China 　　2 School of Electrical and Information Engineering, Changsha University of Science and Technology, Changsha,410076,China) 　　Abstract A fault diagnosis method is presented for motor rotor broken bar fault based on wavelet package analysis (WPS) and Elman neural network. The sideband frequencycurrent which reflects the broken bar fault is analyzed with the technology of wavelet package decomposition. The frequency segment power under operating states are abstracted as fault characteristic vectors which weaken the influences of variable load and noise. Elman neural network is adopted to identify the broken bar fault. To improve its performance , Elman neural network is modified by adding a self-feedback gain factor in the context nodes.Energy of various frequency bands acting as the fault characteristic vector is input into the modified Elman neural network to realize the mapping between the feature vector and the fault mode.Experiment results show that the fault characteristic vectors abstracted by WPA are evident.The diagnosis system based on wavelet package and Elman neural network could identify motor rotor broken bar fault efficiently and accurately. 　　Key words: rotor broken bar; fault diagnosis; wavelet package analysis (WPS); Elman neural network 　　1 引言 　　转子断条是笼型异步电动机常见故障之一,占异步电机故障种类的10%左右[1]。电动机在长期运行中,尤其是大容量高压电机,由于周期性间歇运行或频繁起动,造成转子上电磁应力急剧变化,加之热应力、环境应力和机械应力等的