Advertisement

Artificial Immune Systems for Data Classification in Planetary Gearboxes Condition Monitoring

  • Edyta Brzychczy
  • Piotr Lipiński
  • Radoslaw Zimroz
  • Patryk Filipiak
Conference paper
Part of the Lecture Notes in Mechanical Engineering book series (LNME)

Abstract

In the paper a problem of diagnostic data classification is discussed. The classic condition monitoring approach requires two examples of machines: one in a good and one in a bad condition. From the industrial perspective such a requirement is often very difficult to fulfill, especially in the case of machines with an unique design. To overcome it, we proposed to use the Artificial Immune System (AIS) based approach to classify multidimensional diagnostic data. AIS allows to recognize a change of the machine condition based on a training phase using the dataset related to a good condition. To validate the proposed procedure and assess efficiency of the condition recognition, an extra data set from another machine (of the same type) in a bad condition was used. In the paper several key issues related to the selection of parameters have been discussed.

Keywords

Planetary gearbox Condition monitoring Non-stationary operations Multidimensional symptom space Artificial immune systems Classification 

Notes

Acknowledgments

This work is partially supported by the statutory grant No. S20096 (R. Zimroz).

References

  1. 1.
    Stander CJ, Heyns PS, Schoombie W (2002) Using vibration monitoring for local fault detection on gears operating under fluctuating load conditions. Mech Syst Sig Process 16(6):1005–1024CrossRefGoogle Scholar
  2. 2.
    Samuel PD, Pines DJ (2005) A review of vibration-based techniques for helicopter transmission diagnostics. J Sound Vib 282(1–2):475–508CrossRefGoogle Scholar
  3. 3.
    Cempel C, Tabaszewski M (2007) Multidimensional condition monitoring of machines in nonstationary operation. Mech Syst Sig Proces 21(3):1233–1241CrossRefGoogle Scholar
  4. 4.
    Bartelmus W, Zimroz R (2009) A new feature for monitoring the condition of gearboxes in nonstationary operating systems. Mech Syst Sig Proces 23(5):1528–1534CrossRefGoogle Scholar
  5. 5.
    Zimroz R, Bartkowiak A (2011) Investigation on spectral structure of gearbox vibration signals by principal component analysis for condition monitoring purposes. J Phys: Conf Series 305(1):012075Google Scholar
  6. 6.
    Bartkowiak A (2010) Anomaly, novelty, one-class classification: a short introduction. In: Ajith A et al (ed) Proceedings of computer information systems and industrial management applications 2010, vol 1–6 Ostrava. (IEEE Xplore doi: 10.1109/CISIM.2010.5643699)
  7. 7.
    Bartkowiak A, Zimroz R (2011) Outliers analysis and one class classification approach for planetary gearbox diagnosis. J Phys: Conf Series 305(1):012031Google Scholar
  8. 8.
    Cen J, Shao L, Zhang Q, Xu B (2009) Fault diagnosis research of rotating machinery based on artificial immunity. Coal Mine Machin, vol 3Google Scholar
  9. 9.
    Clifton DA, Bannister PR, Tarassenko LA (2006) Application of an intuitive novelty metric for jet engine condition monitoring. In: Ali M, Dapoigny R (eds) IEA/AIE LNAI 4031, pp 1149–1158Google Scholar
  10. 10.
    Clifton DA, Clifton LA, Bannister PR (2008) Automated novelty detection in industrial systems. Stud Computat Intell (SCI) 116:269–296. (www.springerlink.com)Google Scholar
  11. 11.
    Montechiesi L, Cocconcelli M, Rubini R (2012) Artificial immune system for condition monitoring based on Euclidean distance minimization. Proceedings of the 2nd international conference on condition monitoring of machinery in non-stationary operations. Hammamet, Tunisia, 26–28 MarGoogle Scholar
  12. 12.
    Montechiesi L, Cocconcelli M, Rubini R (2012) Application of the artificial immune systems for bearings diagnostics in servomotors. Proceedings of the international conference on noise and vibration engineering (ISMA2012). Leuven, BelgiumGoogle Scholar
  13. 13.
    Surace C, Worden K (2010) Novelty detection in a changing environment: a negative selection approach. Mech Syst Sig Process 24:1114–1128CrossRefGoogle Scholar
  14. 14.
    Worden K, Staszewski WJ, Hensman JJ (2011) Natural computing for mechanical systems research: a tutorial overview. Mech Syst Sig Process 25:4–111CrossRefGoogle Scholar
  15. 15.
    Jolliffe IT (2002) Principal component analysis, 2nd edn. Springer, New YorkMATHGoogle Scholar
  16. 16.
    Bishop CM (2007) Pattern recognition and machine learning. Springer, New YorkGoogle Scholar
  17. 17.
    Bartkowiak A, Zimroz R (2012) Data dimension reduction and visualization with application to multidimensional gearbox diagnostics data: comparison of several methods. Diffus Defect Data Pt B: Solid State Phenom 180:177–184Google Scholar
  18. 18.
    Zimroz R, Bartkowiak A (2012) Two simple multivariate procedures for monitoring planetary gearboxes in non-stationary operating conditions. Mech Syst Signal Process (in press). http://dx.doi.org/10.1016/j.ymssp.2012.03.022
  19. 19.
    Bartkowiak A, Zimroz R (2012b) Curvilinear dimensionality reduction of data for gearbox condition monitoring. Przeglad Elektrotechniczny 88(10B):268–271Google Scholar
  20. 20.
    Moya M, Hush D (1996) Network constraints and multi- objective optimization for one-class classification. Neural Netw 9(3):463–474CrossRefGoogle Scholar
  21. 21.
    Chandola V, Banerjee A, Kumar V (2009) Anomaly detection: a survey. ACM Comput Surv 41(3):15CrossRefGoogle Scholar
  22. 22.
    Burnet F (1974) Clonal selection and after. Theoretical immunology. Marcel Dekker Inc., New YorkGoogle Scholar
  23. 23.
    Dasgupta D, Zhou J (2007) Revisiting negative selection algorithms. Evol Comput 15(2):223–251Google Scholar
  24. 24.
    Castro de LN, Zuben von FJ (2000) The clonal selection algorithm with engineering applications, GECCO 2000Google Scholar
  25. 25.
    Hunt JE, Cooke DE (2002) Learning using an artificial immune system. J Netw Comput Appl 19(2):189–212CrossRefGoogle Scholar
  26. 26.
    Castro de LN, Timmis JI (2002) An artificial immune network for multimodal function optimization, CEC 2002Google Scholar
  27. 27.
    Forrest S, Perelson AS, Allen L, Cherukuri R (1994) Discrimination in a computer. In: Proceedings of IEEE symposium on research in security and privacy, pp 202–212Google Scholar
  28. 28.
    Gonzales F, Dasgupta D, Nino LF (2003b) A randomized real-value negative selection algorithm, ICARIS 2003Google Scholar
  29. 29.
    Ayara M, Timmis J, Lemos de R, Castro de I, Duncan R (2002) Negative selection: how to generate detectors, ICARIS 2002Google Scholar
  30. 30.
    Gonzales F, Dasgupta D, Gomez J (2003) The effect of binary rules in negative selection, GECCO 2003Google Scholar
  31. 31.
    Dasgupta D, Yu S, Majumdar N (2005) MILA - Multi-Level Immune Learning Algorithm and its application to Anomaly Detection. Soft Comput J 9(3):172–184 (Online Publication was in December 2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2014

Authors and Affiliations

  • Edyta Brzychczy
    • 1
  • Piotr Lipiński
    • 2
  • Radoslaw Zimroz
    • 3
  • Patryk Filipiak
    • 2
  1. 1.Faculty of Mining and GeoengineeringAGH University of Science and TechnologyCracowPoland
  2. 2.Institute of Computer ScienceUniversity of WroclawWroclawPoland
  3. 3.Diagnostics and Vibro-Acoustics Science LaboratoryWroclaw University of TechnologyWroclawPoland

Personalised recommendations