Research on a fault diagnosis method of rolling bearings using variation mode decomposition and deep belief network

Abstract

The working conditions of rolling bearings during the running change in real time. Aiming at the problem of fault diagnosis of rolling bearing under complex working conditions, a new fault diagnosis (VHDBN) method based on variation mode decomposition (VMD), Hilbert transform (HT) and deep belief network (DBN) is proposed in this paper. Firstly, the proposed fault diagnosis method performs the VMD decomposition for the time domain signal in order to obtain a series of intrinsic mode functions (IMFs), and Hilbert envelope spectrum is obtained by Hilbert transform. The Hilbert envelope spectrum is used to construct the feature matrix, which is used as an input of the DBN network in order to obtain a fault diagnosis model. In order to test and verify the effectiveness of the proposed fault diagnosis method, the experimental data of rolling bearings under variable load is used in here. The experimental results show that the VMD-Hilbert envelope spectrum can better reflect the fault characteristics than the time domain spectrum, and the proposed fault diagnosis method under variable load has higher recognition accuracy than other comparison methods.