Skip to main content
Springer Nature Link
Log in

VPMCD based novelty detection method on and its application to fault identification for local characteristic-scale decomposition

  • Published:
Cluster Computing Aims and scope Submit manuscript

Abstract

As a new multi-class discrimination approach, variable prediction model class discrimination (VPMCD) can make full use of the intrinsic relationship among fault features to built variable prediction model for different working conditions and to accomplish multi-class discrimination according to prediction error square sum. It has been effectively used to multi-fault diagnosis when typical fault samples and fault modes can be obtained. However, in most application cases, there only exists normal samples, or there are short of typical fault modes; therefore the variable prediction model is unable to be established and there appear a challenge. Aiming at this problem, VPMCD-based novelty detection (VPMCD-ND) method is put forward in this paper. In VPMCD-ND method, the classifiers are trained only by normal samples firstly. Subsequently, the threshold of prediction error square sum is set according to Chebyshev’s inequality. Lastly, the novelty (from abnormal class) is detected by whether the prediction error square sum is larger than the threshold. Combing with Local characteristic-scale decomposition, a fault diagnosis method is developed and applied to roller bearings. The results show that the proposed VPMCD-ND method not only is more effective than the support vector data description method, but is benefit for online fault diagnosis.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

References

  1. Bubathi Muruganathamn, M.A., Sanjith, B.K., et al.: Roller element bearing fault diagnosis using singular spectrum analysis. Mech. Syst. Signal Process. 35, 150–166 (2013)

    Article  Google Scholar 

  2. Wang, Z., Chen, J., Dong, G., et al.: Constrained independent component analysis and its application to machine fault diagnosis. Mech. Syst. Signal Process. 2011(25), 2501–2512 (2011)

    Article  Google Scholar 

  3. Guangfu, B., Jinji, G., Xuejun, L., et al.: Early fault diagnosis of rotating machinery based on wavelet packets-Empirical mode decomposition feature extraction and neural network. Mech. Syst. Signal Process. 27, 696–711 (2012)

    Article  Google Scholar 

  4. Lei, Y., Lin, J., He, Z., et al.: A review on empirical mode decomposition in fault diagnosis of rotating machinery. Mech. Syst. Signal Process. 2013(35), 108–126 (2013)

    Article  Google Scholar 

  5. Wang, X., Makis, V., Yang, M.: A wavelet approach to fault diagnosis of a gearbox under varying load conditions. J. Sound Vib. 329(9), 1570–1585 (2010)

    Article  Google Scholar 

  6. Jiang, Y., Zhu, H., Li, Z.: A new compound faults detection method for rolling bearings based on empirical wavelet transform and chaotic oscillator. Chaos Solitons Fractals 89, 8–19 (2016)

    Article  Google Scholar 

  7. Jonathan, S.S.: The local mean decomposition and its application to EEG perception data. J. R. Soc. Interface 2(5), 443–454 (2005)

    Article  Google Scholar 

  8. Cheng, J., Yang, Y., Yang, Y.: A rotating machinery fault diagnosis method based on local mean decomposition. Digit. Signal Process. 22(2), 356–366 (2012)

    Article  MathSciNet  Google Scholar 

  9. Lei, Y., He, Z., Zi, Y.: EEMD method and WNN for fault diagnosis of locomotive roller bearings. Expert Syst. Appl. 38, 7334–7341 (2011)

    Article  Google Scholar 

  10. Liu, W.Y., Zhang, W.H., Han, J.G., Wang, G.F.: A new wind turbine fault diagnosis method based on the local mean decomposition. Renew. Energy 48(6), 411–415 (2012)

    Article  Google Scholar 

  11. Frei, M.G., Osorio, I.: Intrinsic time-scale decomposition: time-frequency-energy analysis and real-time filtering of non-stationary signals. Proc. R. Soc. 463, 321–342 (2007)

    Article  MATH  MathSciNet  Google Scholar 

  12. Jinde, Z., Junsheng, C., Yang, Y.: A rolling bearing fault diagnosis approach based on LCD and fuzzy entropy. Mech. Mach. Theory 2013(70), 441–453 (2013)

    Google Scholar 

  13. Luo, S., Cheng, J., Ao, H.: Application of LCD-SVD technique and CRO-SVM method to fault diagnosis for roller bearing. Shock Vib. 2015, 8 (2015)

  14. Mahadevan, S., Shah, S.L.: Fault detection and diagnosis in process data using one-class support vector machines. J. Process Control 19(10), 1627–1639 (2009)

    Article  Google Scholar 

  15. Lian, H.: On feature selection with principal component analysis for one-class SVM. Pattern Recognit. Lett. 33, 1027–1031 (2012)

    Article  Google Scholar 

  16. Desforges, M.J., Jacob, P.J., Cooper, J.E.: Applications of probability density estimation to the detection of abnormal conditions in engineering. Proc. Inst. Mech. Eng. 1998(212), 687–703 (1998)

    Google Scholar 

  17. Markou, M., Singh, S.: Noveltydetection: a review–part 2:neural network based approaches. Sig. Process. 83(12), 2499–2521 (2003)

    Article  MATH  Google Scholar 

  18. Theofilou, D., Steuber, V., Schutter, E.D.: Novelty detection in Kohonen-like network with a long-term depression learning rule. Neurocomputing 52, 411–417 (2003)

    Article  Google Scholar 

  19. Tax, D.M.J., Duin, R.P.W.: Uniform object generation for optimizing one-class classiers. J. Mach. Learn. 2001(2), 155–173 (2001)

    MATH  Google Scholar 

  20. Dong, M., He, D.: A segmental hidden semi-Markov model (HSMM)-based diagnostics and prognostics framework and methodology. Mech. Syst. Signal Process. 21(5), 2248–2266 (2007)

    Article  Google Scholar 

  21. Miao, Q., Makis, V.: Condition monitoring and classification of rotating machinery using wavelets and hidden Markov models. Mech. Syst. Signal Process. 21, 840–855 (2007)

    Article  Google Scholar 

  22. Zhang, R., Li, T., Xiao, X.: A real-valued negative selection algorithm based on grid for anomaly detection. Abstr. Appl. Anal. 2013(3950), 415–425 (2013)

    MATH  MathSciNet  Google Scholar 

  23. Ling, N., Feng, F.G., Jing, M.: Technique for intrusion detection based on cutting-based real-valued negative selection. Int. J. Secur. Appl. 9(9), 95–104 (2015)

    Google Scholar 

  24. Byungho, H., Sungzoon, C.: Characteristics of auto-associative MLP as a noveltydetector. Proc. IEEE IJCNN Confer. 1999(5), 3086–3091 (1999)

    Google Scholar 

  25. Albrecht, S., Busch, J., Kloppenburg, M., et al.: Generalised radial basis function networks for classication and noveltydetection: self-organisation of optimal Bayesian decision. Neural Netw. 2000(13), 1075–1093 (2000)

    Article  Google Scholar 

  26. Wong, M.L.D., Jack, L.B., Nandi, A.K.: Modified self-organising map for automated novelty detection applied to vibration signal monitoring. Mech. Syst. Signal Process. 20, 593–610 (2006)

    Article  Google Scholar 

  27. Lee, H., Cho, S.: Application of LVQ to novelty detection using outlier training data. Pattern Recognit. Lett. 27, 1572–1579 (2006)

    Article  Google Scholar 

  28. Widodo, A., Yang, B.-S.: Support vector machine in machine condition monitoring and fault diagnosis. Mech. Syst. Signal Process. 21(6), 2560–2574 (2007)

    Article  Google Scholar 

  29. Wang, S., Jianbo, Y., Lapira, E., et al.: A modified support vector data description based novelty detection approach for machinery components. Appl. Soft Comput. 13(2), 1193–1205 (2013)

    Article  Google Scholar 

  30. Hu Lei, H., Niaoqing, Q.G.: Online fault detection algorithm based on double-threshold OCSVM and its application. J. Mech. Eng. 45(3), 169–173 (2009)

    Article  Google Scholar 

  31. Raghuraj, R., Lakshminarayanan, S.: Variable predictive models-A new multivariate classification approach for pattern recognition applications. Patten Recognit. 42(1), 7–16 (2009)

    Article  MATH  Google Scholar 

  32. Luo, S., Cheng, J., Yang, Y.: An intelligent fault diagnosis method for rotating machinery based on multi-scale higher order singular spectrum analysis and GA-VPMCD. Measurement 87, 38–50 (2016)

    Article  Google Scholar 

  33. Yang, Y., Wang, H., Cheng, J., et al.: A fault diagnosis approach for roller bearing based on VPMCD under variable speed condition. Measurement 46(8), 2306–2312 (2013)

    Article  Google Scholar 

Download references

Acknowledgements

All of the authors would like to extend the sincerely gratulation for the support from Cooperative Innovation Center for the Construction& Development of Dongting Lake Ecological Economic Zone, Doctoral Found of Hunan University of Arts and Science (16BSQD22), and Scientific Research Fund of Hunan Provincial Education Department (17A147).

Author information

Authors and Affiliations

  1. Cooperative Innovation Center for the Construction & Development of Dongting Lake Ecological Economic Zone, Hunan University of Arts and Science, Changde, 415000, China

    Songrong Luo

  2. College of Mechanical Engineering, Hunan University of Arts and Science, Changde, 415000, China

    Songrong Luo

  3. College of Mechanical and Vehicle Engineering, Hunan University, Changsha, 410082, China

    Junsheng Cheng

Authors
  1. Songrong Luo
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Junsheng Cheng
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Songrong Luo.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Luo, S., Cheng, J. VPMCD based novelty detection method on and its application to fault identification for local characteristic-scale decomposition. Cluster Comput 20, 2955–2965 (2017). https://doi.org/10.1007/s10586-017-0932-2

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10586-017-0932-2

Keywords