Bearing Fault Diagnosis Using Frequency Domain Features and Artificial Neural Networks

  • Amandeep SharmaEmail author
  • Rajvardhan Jigyasu
  • Lini Mathew
  • Shantanu Chatterji
Conference paper
Part of the Smart Innovation, Systems and Technologies book series (SIST, volume 107)


Induction motors are widely used as a workhorse in modern industry. Rolling element bearings constitute an important mechanical component in these motors. Fault detection and diagnosis of bearings are of outmost concerns for prevention of machinery malfunction and abrupt failures. Vibration monitoring is considered as most effective technique for finding bearing-related faults. In this paper, frequency domain features are computed from experimentally collected data from three-phase induction motor and used to classify bearing conditions. Feed-forward back-propagation neural network is used to classify different conditions of bearings with high accuracy. Different number of hidden layer neurons and training algorithms are evaluated for their performance. The proposed procedure requires no pre-processing of vibration signal and proves its effectiveness for bearing fault detection.


Induction motor Bearing faults Fault detection Vibration monitoring Artificial neural network (ANN) 


  1. 1.
    Randall, R.B., Antoni, J.: Rolling element bearing diagnostics—a tutorial. Mech. Syst. Signal Process. 25(2), 485–520 (2011)CrossRefGoogle Scholar
  2. 2.
    Balderston, H.L.: The detection of incipient failure in bearings. Mater Eval. 27(6), 121–128 (1969)Google Scholar
  3. 3.
    Weichbrodt, B., Smith, K.A.: Signature analysis—nonintrusive techniques for incipient failure identification. General Electric Technical Information Series (1970)Google Scholar
  4. 4.
    Tallian, T.E., Gustafsson, O.G.: Progress in rolling bearing vibration research and control. ASLE Trans. 8(3), 195–207 (1965)CrossRefGoogle Scholar
  5. 5.
    Meyer, L.D., Ahlgren, F.F., Weichbrodt, B.: An analytic model for ball bearing vibrations to predict vibration response to distributed defects. Trans. ASME J. Mech. Des. 102, 205–210 (1980)CrossRefGoogle Scholar
  6. 6.
    Li, C.J., Ma, J., Hwang, B.: Bearing condition monitoring by pattern recognition based on bi-coherence analysis of vibrations. In: Proceedings of the Institution of Mechanical Engineers. J. Mech. Eng. Sci. 210(c3), 277–285 (1996)Google Scholar
  7. 7.
    Chaturvedi, G.K., Thomas, D.W.: Bearing fault detection using adaptive noise cancellation. ASME J. Mech. Des. 104(2), 280–289 (1982)CrossRefGoogle Scholar
  8. 8.
    Braun, S., Datner, B.: Analysis of roller/ball bearing vibrations. ASME J. Mech. Des. 101(1), 118–125 (1979)CrossRefGoogle Scholar
  9. 9.
    McFadden, P.D., Smith, J.D.: Vibration monitoring of rolling element bearings by the high frequency resonance technique—a review. Tribol. Int. 17(1), 3–10 (1984)CrossRefGoogle Scholar
  10. 10.
    McCormick, A.C., Nandi, A.K.: Real time classification of rotating shaft loading conditions using artificial neural networks. IEEE Trans. Neural Netw. 8, 748–756 (1997)CrossRefGoogle Scholar
  11. 11.
    Paya, B.A., Esat, I.L., Badi, M.N.M.: Artificial neural network based fault diagnosis of rotating machinery using wavelet transforms as a preprocessor. Mech. Syst. Signal Process. 11(5), 751–765 (1997)CrossRefGoogle Scholar
  12. 12.
    Lei, Y., He, Z., Zi, Y., Hu, Q.: Fault diagnosis of rotating machinery based on a new hybrid clustering algorithm. Int. J. Adv. Manuf. Technol. 35, 968–977 (2008)CrossRefGoogle Scholar
  13. 13.
    Samanta, B., Al-balushi, K.R.: Artificial neural network based fault diagnostics of rolling element bearings using time-domain features. Mech. Syst. Signal Process. 17(2), 317–328 (2003)CrossRefGoogle Scholar
  14. 14.
    Li, B., Goddu, G., Chow, M.: Detection of common bearing faults using frequency-domain vibration signals and a neural network based approach. In: Proceedings of the American Control Conference, Philadelphia, Pennsylvania, pp. 2032–2036 (1998)Google Scholar
  15. 15.
    Yang, D.M., Stronach, A.F., MacConnell, P.: Third-order spectral techniques for the diagnosis of motor bearing condition using artificial neural networks. Mech. Syst. Signal Process. 16(23), 391–411 (2002)CrossRefGoogle Scholar
  16. 16.
    Yang, B.S., Han, T., An, J.L.: ART-KOHONEN neural network for fault diagnosis of rotating machinery. Mech. Syst. Signal Process. 18, 645–657 (2004)CrossRefGoogle Scholar
  17. 17.
    Bishop, C.: Neural Networks for Pattern Recognition. Oxford University Press, New York (1995)zbMATHGoogle Scholar
  18. 18.
    Riedmiller, M., Braun, H.: A direct adaptive method for faster back propagation learning: the RPROP algorithm. In: Proceedings of the IEEE International Conference on Neural Networks, San Francisco, CA, pp. 586–591 (1993)Google Scholar
  19. 19.
    Moller, M.F.: A scaled conjugate gradient algorithm for fast supervised learning. Neural Netw. 6, 525–533 (1993)CrossRefGoogle Scholar
  20. 20.
    Demuth, H.B., Beale, M.: Neural network toolbox for use with MATLAB, user’s guide. The MathWorks Inc., Natick, MA, USA (2004)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  • Amandeep Sharma
    • 1
    Email author
  • Rajvardhan Jigyasu
    • 1
  • Lini Mathew
    • 1
  • Shantanu Chatterji
    • 1
  1. 1.National Institute of Technical Teachers Training and Research (NITTTR)ChandigarhIndia

Personalised recommendations