Research on Fault Diagnosis Method of Rolling Bearing Based on Resonance Sparse Decomposition

Based on the fault characteristics and vibration characteristics of bearings, a resonance sparse decomposition method is proposed. To overcome the difficulty of parameter selection in traditional resonance sparse decomposition method, the PSO algorithm is used to improve it. At the same time, the simulated annealing algorithm is used to improve the PSO algorithm, and the improved PSO optimization resonance sparse decomposition method is obtained. The fault signal is decomposed into a high resonance component and low resonance component, and then the low resonance component is transformed by the Hilbert transform. Compared with the resonance sparse decomposition method optimized by a genetic algorithm (GA), the fault feature frequency can be extracted more effectively, and the fault can be classified accurately.