Fault recognition of wind turbine bearings based on wavelet and fractal theory
SUN Zi-qiang
CHEN Chang-zheng
MENG Qiang
ZHOU Bo
Abstract：In order to solve the problems that the vibration signals of wind turbine bearings are easily modulated and polluted by the environmental noises and have such characteristics as low signal-to-noise ratio,non-linearity and non-stationarity,the corresponding study was performed with a fault recognition method based on wavelet and fractal theory.Through adopting the wavelet packet decomposition,the delay time and embedding dimension of phase space were determined with the mutual information method and Cao algorithm,respectively.The working state of wind turbine bearings was determined according to the correlation dimension changes of different frequency bands.The proposed method is independent on the working dynamical model for wind turbine,and is sensitive to the information state change of overall system.With the field experiments,it is found that the proposed method can better solve the hard distinguishing problem in the faults of wind turbine bearings,and provide the important reference for more detailed study on the vibration signals of wind turbine bearings.
Keywords：wind turbinefault recognitioncorrelation dimensionwavelet packetfractalmutual information methodbearingphase space
Publication Date：2014-01-01
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：5( 666-670 )