Gear Fault Diagnosis Based on Recurrence Network

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

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.

Original languageEnglish
Title of host publicationProceedings - 2017 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2017
EditorsWei Guo, Jose Valente de Oliveira, Chuan Li, Yun Bai, Ping Ding, Juanjuan Shi
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages514-517
Number of pages4
ISBN (Electronic)9781509040209
DOIs
StatePublished - 9 Dec 2017
Externally publishedYes
Event2017 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2017 - Shanghai, China
Duration: 16 Aug 201718 Aug 2017

Publication series

NameProceedings - 2017 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2017
Volume2017-December

Conference

Conference2017 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2017
Country/TerritoryChina
CityShanghai
Period16/08/1718/08/17

Keywords

  • fault diagnosis
  • nonlinear time series
  • recurrence network
  • rotary machine

Fingerprint

Dive into the research topics of 'Gear Fault Diagnosis Based on Recurrence Network'. Together they form a unique fingerprint.

Cite this