摘要
将支持向量机(Support V ectorM ach ine,简称SVM)、经验模态分解(Em p irica lM ode D ecom pos ition,简称EM D)方法和AR(A u to-R egress ive,简称AR)模型相结合应用于滚动轴承故障诊断中。该方法首先对滚动轴承振动信号进行经验模态分解,将其分解为多个内禀模态函数(In trins ic M ode Function,简称IM F)之和,然后对每一个IM F分量建立AR模型,最后提取模型的自回归参数和残差的方差作为故障特征向量,并以此作为SVM分类器的输入参数来区分滚动轴承的工作状态和故障类型。实验结果表明,该方法在小样本情况下仍能准确、有效地对滚动轴承的工作状态和故障类型进行分类,从而实现了滚动轴承故障诊断的自动化。
A roller bearing fault diagnosis method was proposed in which Support Vector Machine （SVM） and Auto-Regressive （AR） model based on Empirical Mode Decomposition （EMD） were combined. EMD method was used to decompose the roller bearing vibration signal into a finite number of Intrinsic Mode Functions （IMFs） ,then the AR model of each IMF component was established ,finally ,the auto-regressive parameters and the variance of remnant were regarded as the fault characteristic vectors and served as input parameters of SVM classifier to classify working condition of the roller bearing. The experimental results show that the proposed approach can classify working condition of roller bearings accurately and effectively even in the case of small number of samples and the atomization of the roller bearing fault diagnosis can be implemented.
出处
《航空动力学报》
EI
CAS
CSCD
北大核心
2006年第3期575-580,共6页
Journal of Aerospace Power
基金
国家自然科学基金资助(50275050)
高等学校博士点专项科研基金资助(20020532024)
关键词
航空
航天推进系统
经验模态分解
AR模型
支持向量机
滚动轴承
故障诊断
aerospace propulsion system
empirical mode decomposition
auto-regressive model
support vector machines
roller bearings
fault diagnosis
