基于EEMD和BP神经网络的风机齿轮箱故障诊断方法  

Method Offan Fault Diagnosis of Gearbox Based on EEMD and BP Neural Network

作　　者：游子跃 王宁[1] 李明明[2] 李亚强[1] 王皓[3] 

机构地区：[1]吉林大学通信工程学院,长春130022 [2]吉林大学网络中心,长春130022 [3]天津海运职业学院,天津300350

出　　处：《东北电力大学学报》2015年第1期64-72,共9页Journal of Northeast Electric Power University

基　　金：天津市科技兴海项目-海上风电机组的在线监测与故障预警平台研制及产业化(KJXH2012-13)

摘　　要：根据风机齿轮箱故障信号的非平稳特性,提出一种基于总体平均经验模式分解(EEMD)和BP神经网络的风机齿轮箱故障诊断方法。首先,对原始信号进行小波去噪。然后,对故障信号进行EEMD分解,将其分解为多个固有模态函数(Intrinsic Mode Function,简称IMF)之和,选取若干含有主要故障信息的IMF分量做进一步分析。最后,从各IMF分量中提取故障信号能量特征参数,将归一化后的能量特征参数作为BP神经网络输入参数进行故障诊断。实测结果表明:该方法故障诊断准确率达到了99%左右。可以准确、有效的对风机齿轮箱进行故障诊断。According to the non-stationary characteristics of wind turbine gearbox fault signal, propose a method of wind turbine gearbox fault diagnosis based on ensemble empirical mode decomposition （ EEMD） and BP neural network. Firstly,use wavelet to denoise the original signal. Then,use EEMD to decompose the fault signal,which is decomposed into sum of several intrinsic mode functions （ Intrinsic Mode Function,referred to as IMF） ,and select some main fault information for further analysis of IMF components. Finally,extract the en-ergy feature parameters of fault signal from the IMF components,use the normalized energy characteristic pa-rameters as the input parameters of the BP neural network for fault diagnosis of gearbox. Experimental results show that：the method of fault diagnosis accuracy rate has reached about 99%. This method can diagnose fault for wind turbine gearbox accurately and effectively.

关 键 词：风机齿轮箱 故障诊断 EEMD 神经网络 小波变换 LABVIEW 

分 类 号：TH131[机械工程—机械制造及自动化] TH132