Aiming at the nonlinear and non-stationary characteristics of rolling bearing vibration signals， a fault diagnosis method based on parameter optimization variational modal decomposition （VMD）， multi-scale permutation entropy （MPE） and particle swarm-cuckoo search fusion algorithm optimized Elman neural network is proposed. Aiming at the problem that the number of modal components and the penalty factor are difficult to determine in VMD， the whale optimization algorithm is introduced to make it autonomously search for the optimal solution. The VMD with the optimal parameters is used to decompose the simulation signal of the rolling bearing fault， and the envelope spectrum analysis of the optimum modal component is carried out， and then the coincidence degree of the simulated fault frequency with the actual value is compared to verify the feasibility of the method. Considering that MPE has the advantage of being able to explore dynamic changes in the signal， it is combined with parameter optimization VMD to obtain the MPE value of each modal component of the rolling bearing vibration signal. Part of the entropy value is selected to construct the feature vector and put in the three-dimensional space to observe its difference， so that it can well characterize different fault types. Aiming at the problem of low recognition accuracy of the Elman neural network， the particle swarm optimization （PSO） algorithm and the cuckoo search （CS） algorithm are combined to jointly optimize the weights and thresholds of the Elman network to improve the convergence accuracy and diagnosis accuracy of the network. The experimental collection and Case Western Reserve University's rolling bearing vibration signals are observed as the research objects， and the proposed method is used for analysis. The results show that the proposed method can not only decompose the signal adaptively and extract effective fault features， but also accurately realize the classification and recognition of fault modes， and the fault recognition rate is improved.