Fault diagnosis of rolling bearings based on graph spectrum amplitude entropy of visibility graph

In order to extract the non-stationary and non-linear fault features of rolling bearing vibration signals more accurately and effectively, complex network and graph signal processing (GSP) techniques were introduced into the field of mechanical fault diagnosis, and a method of rolling bearing fault diagnosis based on the graph spectrum amplitude entropy of visibility graph(GSAEVG) was proposed. Firstly, the vibration signal of rolling bearing was transformed into visibility graph signal; then, the visibility graph signal was transformed from vertex domain to graph spectrum domain by graph Fourier transform (GFT), and graph spectrum amplitude entropy (GSAE) was calculated as the fault characteristic parameter; finally, Mahalanobis distance (MD) discriminant function was used as a classifier to recognize different types of faults. From the analysis results of actual rolling bearing vibration signals, it can be seen that the fault diagnosis method based on the graph spectrum amplitude entropy of visibility graph can be used to identify rolling bearing faults accurately and effectively. © 2021, Editorial Office of Journal of Vibration and Shock. All right reserved.