Skip to main content

Fault diagnosis of spur gearbox based on random forest and wavelet packet decomposition

Abstract

This paper addresses the development of a random forest classifier for the multi-class fault diagnosis in spur gearboxes. The vibration signal’s condition parameters are first extracted by applying the wavelet packet decomposition with multiple mother wavelets, and the coefficients’ energy content for terminal nodes is used as the input feature for the classification problem. Then, a study through the parameters’ space to find the best values for the number of trees and the number of random features is performed. In this way, the best set of mother wavelets for the application is identified and the best features are selected through the internal ranking of the random forest classifier. The results show that the proposed method reached 98.68% in classification accuracy, and high efficiency and robustness in the models.

This is a preview of subscription content, access via your institution.

References

  1. Walha L, Fakhfakh T, Haddar M. Backlash effect on dynamic analysis of a two-stage spur gear system. Journal of Failure Analysis and Prevention, 2006, 6(3): 60–68

    Article  Google Scholar 

  2. Abbes M S, Fakhfakh T, Haddar M, et al. Effect of transmission error on the dynamic behaviour of gearbox housing. International Journal of Advanced Manufacturing Technology, 2007, 34(3–4): 211–218

    Article  Google Scholar 

  3. Tian Z, Zuo M, Wu S. Crack propagation assessment for spur gears using model-based analysis and simulation. Journal of Intelligent Manufacturing, 2012, 23(2): 239–253

    Article  Google Scholar 

  4. Ebersbach S, Peng Z. Fault diagnosis of gearbox based on monitoring of lubricants, wear debris, and vibration. In: Wang Q, Chung Y W, eds. Encyclopedia of Tribology. New York: Springer, 2013, 1059–1064

    Chapter  Google Scholar 

  5. Rgeai M, Gu F, Ball A, et al. Gearbox fault detection using spectrum analysis of the drive motor current signal. In: Kiritsis D, Emmanouilidis C, Koronios A, et al., eds. Engineering Asset Lifecycle Management. London: Springer, 2010, 758–769

    Chapter  Google Scholar 

  6. Hong L, Dhupia J S. A time domain approach to diagnose gearbox fault based on measured vibration signals. Journal of Sound and Vibration, 2014, 333(7): 2164–2180

    Article  Google Scholar 

  7. Rafiee J, Arvani F, Harifi A, et al. Intelligent condition monitoring of a gearbox using artificial neural network. Mechanical Systems and Signal Processing, 2007, 21(4): 1746–1754

    Article  Google Scholar 

  8. Sanchez R, Arpi A, Minchala L. Fault identification and classification of spur gearbox with feed forward back propagation artificial neural network. In: Proceedings of the 2012 Andean Region International Conference. Washington, D.C.: IEEE, 2012, 215

    Chapter  Google Scholar 

  9. Barakat M, Lefebvre D, Khalil M, et al. Parameter selection algorithm with self-adaptive growing neural network classifier for diagnosis issues. International Journal of Machine Learning and Cybernetics, 2013, 4(3): 217–233

    Article  Google Scholar 

  10. Yang B S, Han T, An J L. ART-KOHONEN neural network for fault diagnosis of rotating machinery. Mechanical Systems and Signal Processing, 2004, 18(3): 645–657

    Article  Google Scholar 

  11. Jiang Z, Fu H, Li L. Support vector machine for mechanical faults classification. Journal of Zhejiang University SCIENCE A, 2005, 6 (5): 433–439

    Article  Google Scholar 

  12. Jiao B, Xu Z. Multi-classification LSSVM application in fault diagnosis of wind power gearbox. In: Zhang T, ed. Mechanical Engineering and Technology. Berlin: Springer, 2012, 125: 277–283

    Article  Google Scholar 

  13. Kang Y, Wang C, Chang Y. Gear fault diagnosis in time domains by using Bayesian networks. In: Melin P, Castillo O, Ramirez E, et al., eds. Analysis and Design of Intelligent Systems using Soft Computing Techniques. Berlin: Springer, 2007, 41: 618–627

    Article  Google Scholar 

  14. Breiman L, Friedman J, Olshen R, et al. Classification and regression trees. The Wadsworth and Brooks-Cole statisticsprobability series. Boca Raton: Chapman & Hall, 1984

    Google Scholar 

  15. Breiman L. Random forests. Machine Learning, 2001, 45(1): 5–32

    MATH  Article  Google Scholar 

  16. Criminisi A, Shotton J. Classification forests. In: Criminisi A, Shotton J, eds. Decision Forests for Computer Vision and Medical Image Analysis. London: Springer, 2013, 25–45

    Chapter  Google Scholar 

  17. Han X, Yang B S, Lee S J. Application of random forest algorithm in machine fault diagnosis. In: Mathew J, Kennedy J, Ma L, et al., eds. Engineering Asset Management. London: Springer, 2006, 779–784

    Chapter  Google Scholar 

  18. Yang B S, Di X, Han T. Random forests classifier for machine fault diagnosis. Journal of Mechanical Science and Technology, 2008, 22 (9): 1716–1725

    Article  Google Scholar 

  19. Karabadji N, Khelf I, Seridi H, et al. Genetic optimization of decision tree choice for fault diagnosis in an industrial ventilator. In: Fakhfakh T, Bartelmus W, Chaari F, et al., eds. Condition Monitoring of Machinery in Non-Stationary Operations. Berlin: Springer, 2012, 277–283

    Chapter  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Diego Cabrera.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Cabrera, D., Sancho, F., Sánchez, RV. et al. Fault diagnosis of spur gearbox based on random forest and wavelet packet decomposition. Front. Mech. Eng. 10, 277–286 (2015). https://doi.org/10.1007/s11465-015-0348-8

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11465-015-0348-8

Keywords

  • fault diagnosis
  • spur gearbox
  • wavelet packet decomposition
  • random forest