Fault Diagnosis of Rolling Bearings in VMD and GWO-ELM

Abstract Strong noise, nonlinearity, and complex frequency are the remarkable symbols of vibration signals when rolling bearing failure. So a new method that improved accuracy fault diagnosis is proposed based on variational mode decomposition (VMD) grey wolf algorithm optimized extreme learning machine (GWO-ELM). The signal decomposed by VMD, Intrinsic Mode Component (IMF) used for fuzzy entropy calculation to construct multi-scale complexity eigenvector. pattern recognition carried out in afterward. parameter selection problem VMD analysed through experimental data bearing, noise robustness verified. Through bearings site, comparison results shows GWO-ELM model can effectively identify abnormal conditions, has faster training speed diagnosing faults.