Journal of Failure Analysis and Prevention

, Volume 16, Issue 5, pp 821–827 | Cite as

A New Signal Processing and Feature Extraction Approach for Bearing Fault Diagnosis using AE Sensors

Technical Article---Peer-Reviewed
  • 237 Downloads

Abstract

In this paper, a new signal processing and feature extraction approach for bearing fault diagnosis using acoustic emission (AE) sensors is presented. The presented approach uses time-frequency manifold analysis to extract time-frequency manifold features from AE signals. It reconstructs a manifold by embedding AE signals into a high-dimensional phase space. The tangent direction of the neighborhood for each point is then used to approximate its local geometry. The variation of the manifolds representing different condition states of the bearing can be revealed by performing multiway principal component analysis. AE signals acquired from a bearing test rig are used to validate the presented approach. The test results have shown that the presented approach can interpret different bearing conditions and is effective for bearing fault diagnosis.

Keywords

Fault Diagnosis Bearing failure Acoustic emission Signal Processing 

References

  1. 1.
    A. Morhain, D. Mba, Bearing defect diagnosis and acoustic emission. Proc Inst Mech Eng Part J 217(4), 257–272 (2003)CrossRefGoogle Scholar
  2. 2.
    D. Mba, The use of acoustic emission for estimation of bearing defect size. J Fail. Anal. Prev. 8(2), 188–192 (2008)CrossRefGoogle Scholar
  3. 3.
    K. Nienhaus, F.D. Boos, K. Garate, R. Baltes, Development of acoustic emission (AE) based defect parameters for slow rotating roller bearings, Journal of Physics: Conference Series, Vol. 364, (1), 2012, June 18–20, Huddersfield, UK.Google Scholar
  4. 4.
    Y. He, X. Zhang, Approximate entropy analysis of the acoustic emission from defects in rolling element bearings. J. Vib. Acous. 134(6), 061012 (2012)CrossRefGoogle Scholar
  5. 5.
    F. Takens, Detecting strange attractors in turbulence. Lect Notes in Math 898, 366–381 (1981)CrossRefGoogle Scholar
  6. 6.
    T. Sauer, J.A. Yorke, M. Casdagli, Embedology. J. Stat. Phys. 65(3–4), 579–616 (1991)CrossRefGoogle Scholar
  7. 7.
    L. Cao, Practical method for determining the minimum bedding dimension of a scalar time series. Phys. D 110(1), 43–50 (1997)CrossRefGoogle Scholar
  8. 8.
    Q. He, Time-frequency Manifold for Nonlinear Feature Extraction in Machinery Fault Diagnosis. Mech. Syst. Signal Process. 35(1), 200–218 (2013)CrossRefGoogle Scholar
  9. 9.
    M. Li, J. Xu, J. Yang, D. Yang, D. Wang, Multiple manifolds analysis and its application to fault diagnosis. Mech. Syst. Signal Process. 23, 2500–2509 (2009)CrossRefGoogle Scholar
  10. 10.
    Z. Zhang, H. Zha, Nonlinear dimension reduction via local tangent space alignment. In: Intelligent Data Engineering and Automated Learning, Springer Berlin, 2003, pp. 477–481Google Scholar
  11. 11.
    S.T. Roweis, L.K. Saul, Nonlinear dimensionality reduction by locally linear embedding. Science 290(5500), 2323–2326 (2000)CrossRefGoogle Scholar
  12. 12.
    M. Belkin, P. Niyogi, Laplacian eigenmaps for dimensionality reduction and data representation. Neural Comput. 15(6), 1373–1396 (2003)CrossRefGoogle Scholar
  13. 13.
    B. Van Hecke, D. He, Y. Qu, On the use of spectral averaging of acoustic emission signals for bearing fault diagnostics. ASME J. Vib. Acous. 136(6), 1–13 (2014)Google Scholar

Copyright information

© ASM International 2016

Authors and Affiliations

  1. 1.Department of Mechanical and Industrial EngineeringUniversity of Illinois at ChicagoChicagoUSA
  2. 2.School of Mechanical Engineering and AutomationNortheastern UniversityShenyangChina
  3. 3.School of Mechanical and Electronic EngineeringWuhan University of TechnologyWuhanChina

Personalised recommendations