Application of Wavelet Neural Networks on Vibration Fault Diagnosis for Wind Turbine Gearbox

摘要

This paper applies an Artificial Neural Networks (ANN) method -Wavelet Neural Networks (WNN) on fault diagnosis for a wind turbine gearbox. A gearbox is one of the most important units in a wind turbine drive train. It is significant to study fault diagnosis of gearbox conditions. First this paper presents the principles and advantages of Wavelet Neural Networks. Second this paper specifies the vibration mechanism of the gearbox and the feature parameter group reflecting fault feature, and then the standard fault samples (training samples) and simulation samples (testing samples) are obtained. Third this paper applies the WNN method to perform diagnosing. The accurate diagnostic results have proved the effectiveness of the method for vibration fault diagnosis of gearbox. Finally, the relative advantages of the WNN method are contrasted with those of BPNN method.