Bearing Fault Diagnosis with Impulsive Noise Based on EMD and Cyclic Correntropy

  • Yu-Ze Wang
  • Yong QinEmail author
  • Xue-Jun Zhao
  • Shun-Jie Zhang
  • Xiao-Qing Cheng
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 617)


Periodic pulses are an important fault feature of rolling bearings, so the ability to accurately and efficiently identify pulse components is important for bearing fault diagnosis. Due to the complicated wheel-rail contact relationship in actual train operation, it often generates many impulse noises which similar to the fault signal structure. Unfortunately, spectral kurtosis (SK) methods often fail to effectively diagnose under impulse noise. In order to solve this problem, this paper proposes a bearing fault diagnosis method based on Empirical Mode Decomposition (EMD) and cyclic correntropy (CCE) function. Compared with the SK method, the method proposed in this paper can effectively suppress the influence of impulse noise. Moreover, this paper also proposes a fault diagnosis evaluation index \( KR_{s} \) to quantitatively compare the diagnostic effects of different methods. Simulations and real data of the train axle are utilized to demonstrate the feasibility and effectiveness of the proposed method and index.


Train bearing fault diagnosis Impulsive noise Correntropy EMD Cyclostationary Fault evaluation index 



This research is supported by the National Key Research and Development Program of China (Grant No. 2016YFB1200505-014), National Natural Science Foundation of China (Grant No. 61833002).


  1. 1.
    Zeng Gang F (2010) Research on detection method of weak fault signal of rolling bearing. Chengdu University of TechnologyGoogle Scholar
  2. 2.
    Ming Y, Chen J, Dong G (2011) Weak fault feature extraction of rolling bearing based on cyclic Wiener filter and envelope spectrum. Mech Syst Sig Process 25:1773–1785CrossRefGoogle Scholar
  3. 3.
    Randall RB, Antoni J (2011) Rolling bearing diagnostics—a tutorial. Mech Syst Sig Process 25:485–520CrossRefGoogle Scholar
  4. 4.
    Antoni J, Randall RB (2006) The spectral kurtosis: application to the vibratory surveillance and diagnostics of rotating machines. Mech Syst Sig Process 20:308–331CrossRefGoogle Scholar
  5. 5.
    Antoni J (2006) The spectral kurtosis: a useful tool for characterizing non-stationary signals. Mech Syst Sig Process 20:282–307CrossRefGoogle Scholar
  6. 6.
    Antoni J (2007) Fast computation of the kurtogram for the detection of transient faults. Mech Syst Sig Process 21:108–124CrossRefGoogle Scholar
  7. 7.
    Smith WA, Fan Z, Peng Z, Li H, Randall RB (2016) Optimised Spectral Kurtosis for bearing diagnostics 456 under electromagnetic interference. Mech Syst Sig Process 75:371–394CrossRefGoogle Scholar
  8. 8.
    Antoni J (2016) The infogram: Entropic evidence of the signature of repetitive transients. Mech Syst Sig Process 465(74):73–94CrossRefGoogle Scholar
  9. 9.
    Gardner WA (1986) The spectral correlation theory of cyclostationary time-series. IEEE Trans Sig Process 11(7):13–36Google Scholar
  10. 10.
    Gardner WA (1987) Spectralcorrelation of modulated signals: PART I-analog modulation. IEEE Trans Commun 35(6):584–594CrossRefGoogle Scholar
  11. 11.
    Gardner WA (1991) Exploitation of spectral redundancy in cyclostationary signals. IEEE Trans Sig Process 16(2):14–36CrossRefGoogle Scholar
  12. 12.
    Antoni J, Bonnardot F (2004) Cyclostationary modelling of rotating machine vibration signals. Mech Syst Sig Process 18(6):1285–1314CrossRefGoogle Scholar
  13. 13.
    Antoni J, Xin G, Hamzaoui N (2017) Fast computation of the spectral correlation. Mech Syst Sig Process 92(474):248–277CrossRefGoogle Scholar
  14. 14.
    Gómez-Chova L, Jenssen R, Camps-Valls G (2012) Kernel entropy component analysis for remote sensing image clustering. IEEE Trans Geosci Remote Sens Lett 9(2):312–316CrossRefGoogle Scholar
  15. 15.
    Santamaria I, Pokharel PP, Principe JC (2006) Generalized correlation function: definition, properties, and application to blind equalization. IEEE Trans Sig Process 54(6):2187–2197CrossRefGoogle Scholar
  16. 16.
    Luan S, Qiu T, Zhu Y (2016) Cyclic correntropy and its spectrum in frequency estimation in the presence of impulsive noise. Sig Process 120:503–508CrossRefGoogle Scholar
  17. 17.
    Huang NE, Shen Z, Long SR, Wu MC, Shih HH, Zheng Q, Yen N-C, Tung CC, Liu HH (1998) The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proc R Soc A Math Phys Eng Sci 454:903–995MathSciNetCrossRefGoogle Scholar
  18. 18.
    Zhang J (2010) Comparative study on the performance of commonly used methods for suppressing the end effect of empirical mode decomposition. Yunnan University, KunmingGoogle Scholar
  19. 19.
    Zhang X, Pan H, Zhang Y (2014) Gearbox fault diagnosis based on particle filter and HHT. Combined Mach Tool Autom Process Technol 71–74Google Scholar
  20. 20.
    Liu B, Yan L, Zhou D (2006) A comparative study of several classical similarity measures. Comput Appl Res 23(11):1–3Google Scholar
  21. 21.
    Wang P, Qiu T, Jin F (2018) A tough DOA estimation method based on sparse representation under impulse noise [J]. Acta Electronica Sinica 46(07):1537–1544Google Scholar
  22. 22.
    Liu W, Pokharel PP, Príncipe JC (2007) Correntropy: Properties and applications in non-Gaussian signal processing. IEEE Trans Sig Process 55:5286–5298Google Scholar
  23. 23.
    Jeong KH, Liu WF, Han S et al (2009) The correntropy MACE filter. Pattern Recognit 42(5):871–885CrossRefGoogle Scholar
  24. 24.
    Gunduz A, Principe JC (2009) Correntropy as a novel measure for nonlinearity tests. Sig Process 89(1):14–23CrossRefGoogle Scholar
  25. 25.
    Chen B, Xing L, Zhao H, Zheng N, Principe JC (2016) Generalized correntropy for robust adaptive filtering. IEEE Trans Sig Process 64:3376–3387MathSciNetCrossRefGoogle Scholar
  26. 26.
    Silverman BW (1986) Density estimation for statistics and data analysis. Chapman & Hall, London, UKCrossRefGoogle Scholar
  27. 27.
    Antoni J, Randall R (2003) A stochastic model for simulation and diagnostics of rolling element bearings with localized faults. J Vib Acoust 125:282–289CrossRefGoogle Scholar
  28. 28.
    Wang Y, Kang S, Jiang Y et al (2012) Classification of fault location and the degree of performance degradation of a rolling bearing based on an improved hyper-sphere-structured multi-class support vector machine. Mech Syst Sig Process 29:404–414CrossRefGoogle Scholar
  29. 29.
    Case Western Reserve University Bearing Data Center Website.
  30. 30.
    Loparo K (2003) Bearings Vibration Data Set. Case Western Reserve University, Cleveland, OH, USAGoogle Scholar
  31. 31.
    Smith Wade A, Randall Robert B (2015) Rolling element bearing diagnostics using the Case Western Reserve University data: a benchmark study. Mech Syst Sig Process 64–65:100–131CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  • Yu-Ze Wang
    • 1
    • 2
  • Yong Qin
    • 1
    Email author
  • Xue-Jun Zhao
    • 1
    • 2
  • Shun-Jie Zhang
    • 1
    • 2
  • Xiao-Qing Cheng
    • 1
  1. 1.State Key Laboratory of Rail Traffic Control and SafetyBeijing Jiaotong UniversityBeijingChina
  2. 2.School of Traffic and TransportationBeijing Jiaotong UniversityBeijingChina

Personalised recommendations