Sound-aided fault feature extraction method for rolling bearings based on stochastic resonance and time-domain index fusion

Abstract

The vibration signals of rolling bearings contain a large amount of running information, and have been widely applied in fault diagnosis and status monitoring. However, the fault features decay significantly in the transmission paths, which reduces the detection efficiency. This paper fuses the time-domain vibration and sound signals, and proposes a fault feature extraction method based on the fusion signal. A new indicator is set to show the fusion performance, and a sliding Hanning window is put on the time axis for the optimal fusion signal. The ant colony algorithm is used for the optimization of parameters in stochastic resonance system, and the final output signal is obtained at the highest signal-to-noise ratio. Experimental results show that the fault feature extraction performance gets greatly increased through the proposed method, and the feature enhancement is closely related with the parameters of the Hanning window. The phase difference between the vibration and sound signals is eliminated in the time-domain signal fusion, making the method capable of processing vibration and sound signals collected with time difference. This study proposes a new approach for fault diagnosis, and helps in the status monitoring of bearing systems.