Fault Feature Extraction in Rolling Bearings Using Time-Frequency Analysis and Optimized Variational Mode Decomposition

Abstract

This paper focuses on the analysis of rolling bearing vibration signal, presenting a comprehensive investigation into vibration signal analysis and fault signal feature extraction methods. The research primarily investigates a Variational Modal Decomposition (VMD) method, with enhancements made through the Tucked Swarm Algorithm (TSA) optimization and the use of Maximum Correlated Kurtosis Deconvolution (MCKD). It proposes a method for identifying the optimal parameter configurations for VMD. The proposed method is applied to analyze the rolling bearing vibration signal, and its efficacy in feature extraction has been validated through comparative analysis. This study employs a feature extraction methodology using kurtosis, envelope spectral kurtosis, and other indicators as basic features of vibration signals. It constructs a multi-feature feature vector dataset and utilizes the Least Squares Support Vector Machine (LSSVM) as a fault type classifier, to validate the effectiveness of the proposed feature extraction method. The results demonstrate that the fault identification accuracy achieved by the proposed method consistently exceeds 96%.