High-speed Train Axle Box Bearing Fault Diagnosis Method Based on Neural Network and D-S Evidence Theory
In view of the low accuracy of bearing fault diagnosis using a single signal collected by a sensor,a fault diagnosis method based on neural networks and D-S evidence theory is proposed.Firstly,for the non-stationary vibration signal of the high-speed train axial bearing,the wavelet packet is used for 3-level decomposition,and the sum of the square of the reconstructed coefficient amplitude in each frequency band is proposed as the energy feature parameter to construct the fault feature vector.Then,the BP neural network is used to identify the fault features of the bearing,and the recognition result of the BP neural network is finally identified according to the fusion rule of D-S evidence theory.The experimental simulation results show that the fault diagnosis rate of the proposed method reaches 97.5%,which is 2.5%higher than that of the single sensor fault diagnosis method.
axle box bearingwavelet packet decompositionBP neural networkD-S evidence theory
万方数据
维普
