Skip to Main Content
In order to detect a weak signal under the condition of intensive noise, the signal and additive white noise were used as input of a bistable stochastic resonance (SR) system. The noise intensity and the system parameters were adjusted adaptively with particle swarm optimization (PSO) algorithm by examining the SR effect on output signal-to-noise ratio (SNR). An improved numerical solution for a bistable SR model based on a fourth order Runge-Kutta algorithm was presented to enhance the SR effect. The simulation results show that the weak signal in an intensive noisy background could be successfully extracted. What is more, the output SNR was increased more than 20 dB comparing with the input SNR. The proposed approach was used to process the vibration signals of roller bearings to find the small faults in an early stage. The result showed that the approach satisfactorily extracts the defect characteristics. It can be seen that the proposed method was superior to the traditional spectra analysis and wavelet transform methods. Such detection approach indicates a promising prospect for mechanical fault monitoring and diagnosis.