System Research On Fault Diagnosis To The Rolling Bearing Of Freight CAR By AE Signal

The rolling bearing 352226X2-2Z is one of the mechanical parts of freight car, which is easiest to be damaged. Its running state directly influences the security of railway. In order to discovery bearing fault earlier, the research in the previous stage brought forward a diagnosis method with acoustic emission and applied it to fault diagnosis of the rolling bearing. To recognize bearing condition, wavelet analysis was applied to withdraw the peak-value parameter of AE signals in time-domain and frequency-domain. This method offers a way of fault diagnosis. However, energy distribution of AE signal is wider, the research for 900Hz-1.4KHz of AE signals in the earlier period have a certain limitation in obtaining effective information of the signals.In view of above question, this article has carried on the repeated experiments for 352226X2-2Z bearing with the typical condition (normal, inner-ring fault and roller fault). With contrastive analysis of time-domain and frequency-domain of AE signal, this article proposed one kind of damage examination of Wavelet Probabilistic Neural Network (WPNN). This method makes use of wavelet packet analysis to decompose the energy of the signal in different frequency bands and recognizes the condition of rolling bearing of the freight vehicle through Probabilistic Neural Network.The results of research indicate that the condition recognition of rolling bearing, based on wavelet packet analysis to the energy...