| Summary: | While gearbox in power plant generator set often work in the environment of high speed,high load and poor lubrication,it is of great significance to study the effective monitor and fault diagnosis of working condition. As to nonstationary feature of fault signal in gearbox,the fault diagnosis method based on wavelet packet decomposition（ WPD） and BP neural network is presented. The measured fault signal is decomposed by the wavelet packet to obtain the energy feature information as the input vector,and the BP neural network is used as the classifier to identify and diagnose it. Through analysis of gearbox under four types of normal condition,tooth surface wear,missing teeth and compound fault,show that the fault diagnosis method can distinguish the fault type in gearbox.
|
|---|