Fault diagnosis of bearing based on nonlinear time series of geometrical invariants
Yangang Wang · Zhendong yu chongji · 2009
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 correlation distance entropy were calculated and then input to a neural network,regarding them as the feature values of bearing fault.The experimental results show that the method can implement the fault diagnosis of bearing,and furthermore provides a new approach for fault diagnosis of rotating machinery.