基于振动信号能量熵的轴承故障诊断  

BEARING FAULT DIAGNOSIS METHOD BASED ON ENERGY ENTROPY OF VIBRATION SIGNAL

作　　者：任玉卿 王海瑞[1] 齐磊[1] 李荣远 

机构地区：[1]昆明理工大学信息工程与自动化学院,云南昆明650500

出　　处：《计算机应用与软件》2017年第9期283-287,共5页Computer Applications and Software

基　　金：国家自然科学基金项目(61263023)

摘　　要：轴承大量存在于机械设备当中,轴承的故障也是各种机械故障的主要原因。对轴承故障及时和准确的判断,可以有效地预防由轴承故障引起的事故,减少损失。基于此提出一种基于振动信号能量熵的轴承故障诊断的方法。轴承在不同的工作状态下,轴承振动信号的能量熵不同,也就是能量分布也是不同的,可以通过能量分布的不同判断轴承的状态。首先对轴承的振动信号进行总体平均经验模态分解EEMD(Ensemble Empirical Mode Decomposition),获得若干个本征模函数IMF(Intrinsic Mode Function),然后计算本征模函数能量特征,将能量特征作为输入,可以建立相关向量机判断轴承的状态。通过实验验证,基于振动信号能量熵的故障诊断方法可以有效地应用于轴承的故障诊断。There are a lot of bearings in mechanical equipment,which is the main reason of mechanical failure.Timely and accurate judgment of the bearing fault can effectively prevent the accident caused by the bearing fault and reduce the loss. A Bearing fault diagnosis scheme based on energy entropy is proposed in this paper. Different energy entropy of the bearing vibration signal has different energy distribution in different working condition. The state of the bearing can be judged by the difference of the energy distribution. First,original acceleration vibration signals are decomposed by ensemble empirical mode decomposition（ EEMD） into a finite number of stationary intrinsic mode functions（ IMFs）. To identify the fault pattern and condition,energy feature extracted from a number of IMFs that contained the most dominant fault information could serve as input vectors of relevance vector machine. Practical examples show that the proposed diagnosis approach can identify bearing fault patterns effectively.

关 键 词：总体平均经验模态分解(EEMD) 能量熵 相关向量机(RVM) 故障诊断 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]