基于多重分形与SVM的异步电动机轴承故障诊断

针对异步电动机轴承的故障诊断问题,提出一种基于多重分形与支持向量机(SVM,support vector machine)相结合的故障诊断方法.根据轴承振动信号的非线性、非平稳特性,利用多重分形方法对信号进行分析.计算广义维数、极大值、谱宽度、偏斜度等参数,将其作为故障特征向量输入SVM中.利用凯斯西储大学的实验数据对诊断方法进行验证,将获得的多重分形参数输入二叉树SVM完成故障的模式识别.结果表明多重分形与二叉树SVM相结合的诊断方法可行性好,诊断精度高.

Fault Diagnosis of Induction Motor Bearing Based on Multifractal and SVM

A fault diagnosis method based on multifractal and support vector machine(SVM) is proposed for the fault diagnosis of induction motor bearing.The signal is analyzed by using multifractal method according to the nonlinear and non stationary characteristics of the bearing vibration signal.The parameters such as the generalized dimension,the maximum value,the spectral width and the degree of skewness are calculated and used as the fault feature vector to input into SVM.The experimental data of the Case Western Reserve University are used to verify the diagnosis method,the obtained multifractal parameters are input to the binary tree SVM to complete the fault pattern recognition.The results show that the combination of multifractal and binary tree SVM is feasibility,and has high diagnosis accuracy.