基于EMD的电机轴承故障识别研究

将经验模态分解(EMD)和支持向量机(SVM)方法相结合应用于电机滚动轴承故障诊断中,该方法利用EMD将电机滚动轴承振动信号分解为有限个内禀模态函数(IMF)之和,对表征高频信息的IMF分量取其能量作为故障特征向量,以此作为多项式核函数(2阶)SVM分类器的输入参数来区分电机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、有效地对电机滚动轴承的工作状态和故障类型进行分类,实现电机滚动轴承故障自动识别。

Study on Fault Diagnosis of Motor Bearings Based on EMD

A motor roller bearing fault diagnosis method was proposed in which Support Vector Machine(SVM) based on Empirical Mode Decomposition(EMD) was combined.EMD method was used to decompose the motor roller bearing vibration signal into a finite number of Intrinsic Mode Functions(IMFs),then make each IMF component into each energy component that were regarded as the fault characteristic vectors and served as input parameters of Polynomial Kernel SVM classifier to classify working condition of the motor roller bearing.The experimental results show that the proposed approach can classify working condition of motor roller bearings accurately and effectively even in the case of small number of samples and the automation of the motor roller bearing fault diagnosis can be implemented.