摘要
针对轴承传动本身具有非线性而在传统故障诊断中又被忽略掉的问题,提出了基于分形和混沌等非线性几何不变量的轴承故障诊断方法。该方法对测得的轴承振动时间序列去噪以后进行相空间重构,然后计算重构信号的分形维数、Lypunove指数、K熵、关联距离熵等多个几何不变量,并以此作为轴承故障诊断特征量,输入到径向基神经网络,对轴承故障进行模式识别。实验结果表明该方法能有效区别轴承各种故障状态,且为旋转机械的故障诊断提供了一种新方法。
Aiming at the nonlinearity which exits in bearing transmission but is ignored in fault diagnosis traditionally,a method of fault diagnosis of bearing based on nonlinear time series of geometrical invariants applying the theory of chaos and fractal was put forward.In the method noises were reduced by using wavelet transform and the phase space of bearing vibration time series was reconstructed.The nonlinear geometrical invariants such as correlation dimension,max Lyapunov exponent,K entropy and relative corr...
出处
《振动与冲击》
EI
CSCD
北大核心
2009年第11期130-133,209,共5页
Journal of Vibration and Shock
基金
国家自然科学基金资助项目(50775219)
关键词
轴承
故障诊断
非线性
混沌
分形
bearing
fault diagnosis
nonlinearity
chaos
fractal
