Acoustic Signal Analysis Methods In The Heavy Freight Train Rolling Bearing Fault Diagnosis

Fault diagnosis technique of the rolling bearing is an engineering science integrating with practice, which is the reason why we should develop it. More and more people attach importance to the acoustic signal technique for its convenience and non-contiguity. This thesis first analyzed the source and spread of the rolling bearing's noise and considered the influence of acoustic attenuation and background noise. Then adopted some modern techniques that can effectively and credibly diagnose the rolling bearing, according to the non-stationary characteristic of signals. The details as follows:According to the non-stationary characteristic of acoustic signals, the analysis of these signals based on the wavelet analysis shows that a minutia of signals can be magnified. Compare this frequency with the fault signals'frequency, we can identify the difference. Improve de-noising function of the non-linear wavelet analysis theory, adopt the layered threshold de-noising method to process the fault signals, and its great effectiveness of de-noising is verified. The power spectrum technique based on the Wavelet Transform can pick up the distinct characteristics of signals'frequency. During picking up the characteristics of signals, the reformative Wavelet Packet Decomposition based on sections is used to subdivide the frequency bands identified the fault easier and un-subdivide others. It is testified by experiment that the parameters are suitable to fault diagnosis of the engine.Application of artificial neural network on fault diagnosis of rolling bearing studied. There are many methods to extract fault signatures based on vibration signal analysis, but every method can only reflect some of fault's characteristies. If only one method is used the effect will not be very good. This Paper contrasts the result of different combinations of fault signatures which are extracted by different methods. At last, this thesis combines wavelet analysis with fractal and neural network to diagnose fault of rolling bearing. If use artificial neural network to diagnose fault of rolling bearing, the workers do not need to master a lot of Professional knowledge and the technology of artificial intelligence will instead the traditional technologies. At the same time, the application of technology of artificial intelligence's in the domain of diagnosis can greatly reduce the depression of maintainer.