scrollbar

Recurrence Plots and Cross Recurrence Plots

RPs at a Glance Variations of RPs Quantification Introduction CRPs/JRPs Dynamical Invariants Pitfalls Further Reading Bibliography Software Related Methods RP Of The Day Symposium Forum Email List Imprint Privacy Disclaimer Accessibility

Hosted by:



Proceedings of the International Conference On Sensing Sensing, Diagnostics, Prognostics, and Control (SDPC 2017), 514–517p. (2017) DOI:10.1109/SDPC.2017.103

Gear Fault Diagnosis Based on Recurrence Network

J. Meng, L. Y. Zhao, R. Q. Yan

Gear is one of the most important components in rotary machine systems. The vibration signals generated from gearbox show strong nonlinearity or chaotic behavior. To identify the complex nonlinear behavior of gear faults, recurrence network is introduced to extract features of gear vibration under different conditions. Quantitative characteristics (such as mean degree centrality, global clustering coefficient, or assortativity of the recurrence network) related to the dynamical complexity of a time series are chosen to help classify the different faults. Experimental study on four different gear conditions has proved that the recurrence network provides a good alternative approach to characterize gear fault.