Application of spectral kurtosis and vold-Kalman filter based order tracking in wind turbine gearbox fault diagnosis

Abstract

In Order to deal with non-stationary vibration signal of wind turbines gearbox under time-varying conditions, the fault feature extraction method combining spectral kurtosis and Vold — kalman Tracking (Vold — kalman Filter-based Order Tracking, VKF — OT) is put forward. By the method, after set rotation and Meshing frequency as extracting frequency, the order component with speed changes is extracted, then, the vibration amplitude and phase can be obtained directly from the complex envelop of each order component. The experiments prove that this method can retain the transients' information of Gearbox. Calculated spectral kurtosis of two frequencies components, extract the ratio of frequency band energy which corresponding Maximum spectral kurtosis and total energy of the original order signal as fault feature. Finally, the features of 150 groups' vibration signal from wind turbine gear box under different conditions is described by using Gaussian mixture model, and Maximum Bayesian classifier is used to achieve failure recognition. The amount of recognition rate indicates that this method can identify local early weak fault of gear in arbitrary time-varying conditions effectively.