A New Method for Rubbing Fault Identification Based on the Combination of Improved Particle Swarm Optimization with Self-Adaptive Stochastic Resonance

To fulfill the effective diagnosis of the rubbing fault between the rotor and the stator, the combination strategy of adaptive weight particle swarm optimization (PSO) and general scale transformation stochastic resonance (GSTSR) is proposed in the paper. Firstly, in view of the self-adaptive weighted PSO featured by high precision and quick convergence, the method has made self-adaptive adjustment of systematic parameters based on PSO algorithm (with signal-noise ratio as fitness function). Secondly, GSTSR can further highlight the characteristic information otherwise covered by noise. Therefore, self-adaptive weighted PSO algorithm is combined with GSTSR to make characteristic extraction of rotor-stator rubbing faults. Finally, a comparative analysis with other methods and the analysis of faults in different states all indicate that the combination of self-adaptive weighted PSO algorithm and GSTSR can enhance rubbing fault characteristics and has effective identification of rotor-stator rubbing faults.