Advertisement

Journal of Failure Analysis and Prevention

, Volume 17, Issue 6, pp 1217–1225 | Cite as

Rolling Bearing Fault Feature Extraction Based on Bacteria Foraging Optimization

  • Jianhui Sun
  • Shuai Zhang
Technical Article---Peer-Reviewed
  • 122 Downloads

Abstract

Resonance demodulation technology has been widely applied in the fault diagnosis of rolling bearings because of the high sensitivity, the high reliability, and the effective identification of early damage. Its process includes collecting vibration signals, filtering, envelope demodulation analysis, and judge fault condition, while filtering as the key link directly affects the accuracy and efficiency of fault diagnosis based on resonance demodulation technology. So, there is an important problem in the resonance demodulation technology, which is how to select the optimal filter band rapidly to ensure the least amount of noise in the filter signal. To solve this problem, this paper applies bacteria foraging optimization algorithm (BFO) in the selection of the optimal filtering band. The kurtosis is used as evaluation function to judge the quality of the filter signals. Through the loop operation of three operators (migration, breeding, and chemotaxis), the algorithm converges to the global optimal solution quickly. In the last part of the paper, the feasibility and effectiveness of the application of BFO are tested by simulation signals and practical signals, and the relative merits of the application are concluded.

Keywords

Rolling bearing Fault diagnosis Resonance demodulation technology Bacteria foraging optimization algorithm 

Notes

Acknowledgments

The work described in this paper was supported by a grant from the Naval University of Engineering researching fund (No. 425517k144).

References

  1. 1.
    L.I. Guo-hua, The mechanical fault diagnosis (Chemical Industry Press, Beijing, 2002)Google Scholar
  2. 2.
    Z.H. Wu, N.E. Huang, Ensemble empirical mode decomposition: a noise-assisted data analysis method. Adv. Adapt. Data Anal. 1(1), 1–41 (2009)CrossRefGoogle Scholar
  3. 3.
    D.L. Donoho, Compressed sensing. IEEE Trans. Inf. Theory 52(4), 227–254 (2006)CrossRefGoogle Scholar
  4. 4.
    D.L. Donoho, Y. Tsaig, Extensions of compressed sensing. Signal Process. 86(3), 533–548 (2006)CrossRefGoogle Scholar
  5. 5.
    J. Antoni, R.B. Randall, The spectral kurtosis: application to the vibratory surveillance and diagnostics of rotating machines. Mech. Syst. Signal Process. 20(2), 308–331 (2006)CrossRefGoogle Scholar
  6. 6.
    J. Antoni, Fast computation of the kurtogram for the detection of transient faults. Mech. Syst. Signal Process. 21(1), 108–124 (2007)CrossRefGoogle Scholar
  7. 7.
    Z. Hu, C. Wang, J. Zhu, X. Liu, F. Kong, Bearing fault diagnosis based on an improved morphological filter. Measurement 80, 163–178 (2016)CrossRefGoogle Scholar
  8. 8.
    D. Wang, W.T. Peter, K.L. Tsui, An enhanced Kurtogram method for fault diagnosis of rolling element bearings. Mech. Syst. Signal Process. 35(1–2), 176–199 (2013)CrossRefGoogle Scholar
  9. 9.
    Y. Lei, J. Lin, Z. He, Y. Zi, Application of an improved kurtogram method for fault diagnosis of rolling element bearings. Mech. Syst. Signal Process. 25(5), 1738–1749 (2011)CrossRefGoogle Scholar

Copyright information

© ASM International 2017

Authors and Affiliations

  1. 1.Naval University of Engineering Mechanical EngineeringWuhanChina

Personalised recommendations