Aiming at the problems of difficult extraction and low detection accuracy of weak signals of bearings at early period,a method for early weak fault diagnosis of bearings was proposed based on stochastic resonance.Based on the sensitivity of permutation entropy criterion to periodic signals,a new signal filtering method was proposed to perform preliminary filtering.Secondly,stochastic resonance algorithm was used for fault signal to noise auxiliary enhancement; taking signal-to-noise ratio as the objective function,the sparrow search algorithm was used to optimize the stochastic resonance system parameters:k,a,b,h.The optimized parameters were sent to the stochastic resonance system for detection.The simulation results show that this method can be used to effectively detect the unknown weak fault signal in strong noise.