Fault Diagnosis of Transmission Rolling Bearing Based on EMD De-noising and BP Neural Network
As one of the most stringent components in automobile driver system,transmission rolling bearing with-stands high mechanical load and thermal load during transferring the driving force.The research on fault diagnosis of transmission rolling bearings is of great significance for improving the safety of vehicles.According to the characteristics and requirements of rolling bearing vibration fault diagnosis,a new method of fault diagnosis based on empirical mode de-composition(EMD)and BP neural network is proposed in this paper.First,the vibration signals are decomposed into a series of intrinsic mode functions(IMF)with main characteristic information by EMD,and then the characteristic signals of bearing faults are extracted by IMF information entropy,combined with BP neural network classifier,it can effectively diagnose and identify the fault of transmission rolling bearing,and the recognition accuracy is over 80.0％.
Transmission rolling bearingEMD de-noisingKurtosis criterionShannon entropyBP neural network
万方数据
维普
