Research On Intelligent Fault Diagnosis System Of Wind Turbine Bearing

Bearing is the key parts of wind turbine,It plays a decisive role in the normal operation of wind turbines.The research of fault diagnosis of wind turbine bearings has very important significance to reduce the maintenance cost and significant economic losses.The fault of bearing vibration signal is unstable and in strong background noise,The fault features can easily be submerged,especially the speed of wind turbine bearings change frequently,thus bring challenges to the fault diagnosis.Although the wavelet analysis,resonance demodulation and shock pulse method are applied to the bearing,but they all have their own defects,thus it’s an urgent task to develop new bearing fault diagnosis methods.According to the existing problems for the analysis,this paper,with the rolling bearing of wind turbine as subject investigated,studies the morphology filter,local mean decomposition,permutation entropy and BP neural network,as well as their application in rolling bearing diagnosis.With the help of labview,the intelligent fault diagnosis system of rolling bearing is developed.The research contents of this paper are as follows:(1)According to the fault characteristics of rolling bearing,a fault diagnosis method of rolling bearing based on local mean decomposition and BP neural network is proposed,The fault vibration signal of the bearing is collected by the fault simulation experimental platform.(2)The methods of morphology filter,local mean decomposition and neural network are studied in detail.The simulation and experimental data are used to verify the validity and practicability of the proposed methods;(3)The intelligent fault diagnosis system for the rolling bearing of wind turbine is developed with the help of the software.