access icon free Rolling element bearing fault diagnosis based on non-local means de-noising and empirical mode decomposition

The presence of faults in the bearings of rotating machinery is usually observed with impulses in the vibration signals. However, the vibration signals are generally non-stationary and usually contaminated by noise because of the compounded background noise present in the measuring device and the effect of interference from other machine elements. Therefore in order to enhance monitoring condition, the vibration signal needs to be properly de-noised before analysis. In this study, a novel fault diagnosis method for rolling element bearings is proposed based on a hybrid technique of non-local means (NLM) de-noising and empirical mode decomposition (EMD). An NLM which removes the noise with minimal signal distortion is first employed to eliminate or at least reduce the background noise present in the measuring device. This de-noised signal is then decomposed into a finite number of stationary intrinsic mode functions (IMF) to extract the impulsive fault features from the effect of interferences from other machine elements. Finally, envelope analyses are performed for IMFs to allow for easier detection of such characteristic fault frequencies. The results of simulated and real bearing vibration signal analyses show that the hybrid feature extraction technique of NLM de-noising, EMD and envelope analyses successfully extract impulsive features from noise signals.

Inspec keywords: fault diagnosis; rolling bearings; signal denoising

Other keywords: stationary intrinsic mode functions; rolling element bearing; feature extraction; background noise; fault diagnosis; envelope analyses; nonlocal means; minimal signal distortion; impulsive fault features; empirical mode decomposition; de-noising

Subjects: Mechanical components; Production equipment

References

    1. 1)
    2. 2)
    3. 3)
      • 27. Santhana Raj, A., Murali, N.: ‘Morlet wavelet UDWT denoising and EMD based bearing fault diagnosis’, Electronics, 2013, 17, (1), pp. 18.
    4. 4)
    5. 5)
    6. 6)
    7. 7)
      • 29. Buades, A., Coll, B., Morel, J.M.: ‘A non-local algorithm for image denoising’. IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, June 2005, pp. 2025.
    8. 8)
    9. 9)
    10. 10)
    11. 11)
    12. 12)
    13. 13)
    14. 14)
    15. 15)
    16. 16)
    17. 17)
      • 2. Mitchell, J.C.: ‘Introduction to machinery analysis and monitoring’ (PennWell, Tulsa, OK, 1993).
    18. 18)
      • 21. Junsheng, C., Dejie, Y., Yu, Y.: ‘A fault diagnosis approach for roller bearings based on EMD method and AR model’, Mech. Syst. Signal Process., 2006, 42, (2), pp. 10921102.
    19. 19)
    20. 20)
    21. 21)
    22. 22)
    23. 23)
    24. 24)
      • 8. Randall, R.B.: ‘Frequency analysis’ (Bruel & Kjaer, 1987).
    25. 25)
    26. 26)
      • 30. Tasdizen, T.: ‘Principal neighborhood dictionaries for nonlocal means image denoising’, IEEE Trans. Image Process., 2000, 18, (12), pp. 449458.
    27. 27)
    28. 28)
    29. 29)
    30. 30)
    31. 31)
    32. 32)
      • 33. Loparo, K.A.: ‘Bearing data center’, http://www.eecs.case.edu/laboratory/bearing, Case Western Reserve University, accessed 2013.
    33. 33)
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-smt.2014.0023
Loading

Related content

content/journals/10.1049/iet-smt.2014.0023
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading