Rolling Bearing Fault Diagnosis Based on Improved PSO-VMD-MCKD
A fault diagnosis method combining variational modal decomposition(VMD)and maximum correlated kur-tosis deconvolution(MCKD)is proposed to overcome the difficulty of extracting fault features from rolling bearing signals in strong noise backgrounds.Firstly,the optimal modal components of the fault signal are selected based on the VMD meth-od.Then,the MCKD algorithm is used to enhance the impact components in the optimal component signal.Finally,the fault frequency of the rolling bearing is extracted through envelope spectrum analysis.The particle swarm optimization(PSO)al-gorithm is used to optimize the parameters α and K in the VMD algorithm and the parameters L and M in the MCKD algo-rithm.The update methods of the inertia factor and learning factor in the PSO algorithm are improved to raise the conver-gence speed of the parameter optimization process.Simulation analysis and experimental results show that the proposed method can effectively extract the fault features of rolling bearings that are submerged in strong noise background.
万方数据
维普
