Transmission Shaft Fault Diagnosis Based on Variational Modal Decomposition (VMD) Feature Fusion

Abstract

It is difficult to achieve an excellent result to accomplish the transmission shaft fault diagnosis with single feature, so thadt a feature fusion fault diagnosis method is proposed. First, the preprocessed vibration signal is decomposed by variational mode decomposition (VMD), and the Intrinsic mode function (IMF) is obtained; Then, singular value, sample entropy and approximate entropy are obtained as features and fused; Finally, the fused feature is used as the classification object of SVM for fault diagnosis. In this paper, the feasibility of this method is verified by the transmission of experimental data. The experiment included five conditions, and the diagnostic accuracy was 99%.