Skip to main content
SpringerLink
Log in

A method for condition monitoring and fault diagnosis in electromechanical system

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Condition monitoring of electrical machines has received considerable attention in recent years. Many monitoring techniques have been proposed for electrical machine fault detection and localization. In this paper, the feasibility of using a nonlinear feature extraction method noted as Kernel independent component analysis (KICA) is studied and it is applied in self-organizing map to classify the faults of induction motor. In nonlinear feature extraction, we employed independent component analysis (ICA) procedure and adopted the kernel trick to nonlinearly map the Gaussian chirplet distributions into a feature space. First, the adaptive Gaussian chirplet distributions are mapped into an implicit feature space by the kernel trick, and then ICA is performed to extract nonlinear independent components of the Gaussian chirplet distributions. A thorough laboratory study shows that the diagnostic methods provide accurate diagnosis, high sensitivity with respect to faults, and good diagnostic resolution.

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

Access this article

Log in via an institution

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
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14

Similar content being viewed by others

References

  1. Kowalski CT, Orlowska-Kowalska T (2003) Neural networks application for induction motor faults diagnosis. Math Comput Simul 63:435–448

    Article  MathSciNet  MATH  Google Scholar 

  2. Eisenmann RC Sr, Eisenmann RC Jr (1997) Machinery malfunction diagnosis and correction. Prentice-Hall, NJ

    Google Scholar 

  3. Vas P (1999) Artificial-intelligence-based electrical machines and drives. Oxford University Press, Oxford

    Book  Google Scholar 

  4. Yen Gary G, Kuo-Chung L (2000) Wavelet packet feature extraction for vibration monitoring. IEEE Trans Ind Electron 47:650–667

    Article  Google Scholar 

  5. Guo QJ, Yu HB, Xu AD (2006) A hybrid PSO-GD based intelligent method for machine diagnosis. Digit Signal Process 16:402–418

    Article  Google Scholar 

  6. Bastiaans MJ (1980) Gabor’expansion of a signal into Gaussian elementary signals. Proc IEEE 68:538–539

    Article  Google Scholar 

  7. Cohen L (1989) Time–frequency distribution—a review. Proc IEEE 77:941–981

    Article  Google Scholar 

  8. Cohen L (1995) Time–frequency analysis. Prentice-Hall, Englewood Cliffs

    Google Scholar 

  9. Loughlin P,Pitton J, Atlas L (1993) Bilinear time–frequency representations: new insights and properties. IEEE Trans Sig Proc 41:750–767

    Article  MATH  Google Scholar 

  10. Comon P (1994) Independent component analysis—a new concept? Signal Process 36:287–314

    Article  MATH  Google Scholar 

  11. Hyvärinen A, Karhunen J, Oja E (2001) Independent component analysis. Wiley, New York

    Google Scholar 

  12. Jutten C, Herault J (1991) Blind separation of sources, part I: an adaptive algorithm based on neuromimetic architecture. Signal Process 24:1–10

    Article  MATH  Google Scholar 

  13. Hurri J, Hyvärinen A, Karhunen J, Oja E (1996) Image feature extraction using independent component analysis. In: Proceedings of 1996 IEEE Nordic Signal Processing Symposium, Espoo, Finland, pp 475–478

  14. Olshausen BA, Field DJ (1996) Emergence of simple-cell receptive field properties by learning a sparse code for natural images. Nature 381:607–609

    Article  Google Scholar 

  15. Amari S, Cichocki A (1998) Adaptive blind signal processing—Neural network approaches. Proc IEEE 86:2026–2048

    Article  Google Scholar 

  16. Vigrio R (1997) Extraction of ocular artifacts from EEG using independent component analysis. Electroenceph Clin Neurophysiol 103:395–404

    Article  Google Scholar 

  17. Vigrio R, Jousmäki V, Hämäläinen M, Hari R, Oja E (1998) Independent component analysis for identification of artifacts in magnetoencephalographic recordings. Advances in neural information processing systems, vol 10. MIT Press, Cambridge, pp 229–235

  18. Vigrio R, Jousmäki V, Oja E (1998) Independent component analysis in wave decomposition of auditory evoked fields. In: International conference on artificial neural networks (ICANN’98). Skövde, Sweden, pp 287–292

  19. Jung TP, Humphries C, Lee T-W, Makeig S, McKeown MJ, Iragui V, Sejnowski T (1998) Extended ICA removes artifacts from electroencephalographic recordings. Adv Neural Inf Process Syst 10:894–900

    Google Scholar 

  20. Barros AK, Mansour A, Ohnishi N (1998) Adaptive blind elimination of artifacts in ECG signals. In: Proceedings of 1998 workshop on independenc and artificial neural networks, Tenerife, Spain, pp 1380–1386

  21. McKeown M, Makeig S, Brown S, Jung T-P, Kindermann S, Bell A, Iragui V, Sejnowski T (1998) Blind separation of functional magnetic resonance imaging (fMRI) data. Hum Brain Mapp 6:368–372

    Article  Google Scholar 

  22. Ziehe A, Mller K, Nolte G, Mackert B-M, Curio G (2000) Artifact reduction in magnetoneurography based on time-delayed second-order correlations. IEEE Trans Biomed Eng 10:75–87

    Article  Google Scholar 

  23. Jahn O, Cichocki A (1999) Identification and elimination of artifacts from MEG signals using efficient independent components analysis. In: 11th International conference on biomagnetism BIOMAG-98, Sendai, Japan, Tohoku University Press, Japan, pp 224–227

  24. Torkkola K (1999) Blind separation for audio signals: are we there yet? In: International workshop on independent component analysis and blind separation of signals (ICA’99), Aussois, France, pp 239–244

  25. Yang J, Gao XM, Zhang D, Yang JY (2005) Kernel ICA: an alternative formulation and its application to face recognition. Pattern Recognit 38:1784–1787

    Article  MATH  Google Scholar 

  26. Liu QS, Cheng J, Lu HQ, Ma SD (2004) Modeling face appearance with kernel independent component analysis. FG2004, Seoul, Korea, pp 761–766

    Google Scholar 

  27. Kohonen T (2001) Self-organizing maps, 3rd edn. Springer, Berlin, Germany, pp 138–140

    MATH  Google Scholar 

  28. Kohonen T (1982) Self-organized formation of topologically correct feature maps. Biol Cybernet 43:59–69

    Article  MathSciNet  MATH  Google Scholar 

  29. Kohonen T, Kaski S, Lagus K, Salojärvi J, Honkela J, Paatero V, Saarela A (2000) Self-organizing of a massive document collection. IEEE Trans Neural Netw 11:574–585

    Article  Google Scholar 

  30. Chang CH, Xu PF, Xiao R, Srikanthan T (2005) New adaptive color quantization method based on self-organizing maps. IEEE Trans Neural Netw 16:237–249

    Article  Google Scholar 

  31. Mann S, Haykin S (1995) The chirplet transform: physical considerations. IEEE Trans Signal Process 43:2745–2461

    Article  Google Scholar 

  32. Gabor D (1946) Theory of communication. J Inst Electr Eng 93:429–457

    Google Scholar 

  33. Mann S, Haykin S (1992) ‘Chirplets’ and ‘warblets’: novel timefrequency methods. Electron Lett 28:114–116

    Article  Google Scholar 

  34. Mallat S, Zhang Z (1993) Matching pursuit with time-frequency dictionaries. IEEE Trans Signal Process 41:3397–3415

    Article  MATH  Google Scholar 

  35. Qian S, Chen D (1993) Signal representation in adaptive Gaussian functions and adaptive spectrogram. In: Proceedings of twenty-seventh annu. conf. inform. sci. syst, Baltimore, MD, pp 59–65

  36. Qian S, Chen D (1994) Signal representation using adaptive normalized Gaussian functions. Signal Process 36:1–11

    Article  MathSciNet  MATH  Google Scholar 

  37. Yin Q, Qian S, Feng A (2002) A fast refinement for adaptive Gaussian chirplet decomposition. IEEE Trans Signal Process 50:1298–1306

    Article  MathSciNet  Google Scholar 

  38. Hyvarinen A (1999) Survey on independent component analysis. Neural Comput Surv 2:94–128

    Google Scholar 

  39. Bell AJ, Sejnowski TJ (1997) The independent components of natural scence are edge filters. Vision Res 37:3327–3328

    Article  Google Scholar 

  40. Francis RB, Jordan MI (2002) Kernel independent component analysis. J Mach Learn Res 3:1–48

    Google Scholar 

  41. Schälkopf B, Smola A, Müller K (1998) Non-linear component analysis as a kernel eigenvalue problem. Neural Comput 10:1299–1319

    Article  Google Scholar 

  42. Kliman GB, et al (1988) Non-invasive detection of broken rotor bars in operating induction motors. IEEE Trans Energy Converv 3:873–879

    Article  Google Scholar 

  43. Elkasabgy NM, Eastham AR, Dawson GE (1992) Detection of broken bars in the cage rotor on an induction machine. IEEE Trans Ind Appl IA-22:165–171

    Article  Google Scholar 

  44. Ultsch A, Siemon HP (1990) Kohonen’s self organizing feature maps for exploratory data analysis. In: Proceedings of international neural networks. Kluwer Academic Press, Paris, pp 305–308

  45. Iivarinen J, Kohonen T, Kangas J, Kaski S (1994) Visualizing the clusters on the self-organizing map. In: Proceedings of the conference on artificial intelligence research in Finland. Finnish Artificial Intelligence Society, Helsinki, Finland, pp 122–126

Download references

Author information

Authors and Affiliations

  1. Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, Liaoning, 110016, China

    Qianjin Guo, Haibin Yu, Jingtao Hu & Aidong Xu

  2. Graduate School of the Chinese Academy of Sciences, Beijing, 100039, China

    Qianjin Guo

Authors
  1. Qianjin Guo
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Haibin Yu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jingtao Hu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Aidong Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Qianjin Guo.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Guo, Q., Yu, H., Hu, J. et al. A method for condition monitoring and fault diagnosis in electromechanical system. Neural Comput & Applic 17, 373–384 (2008). https://doi.org/10.1007/s00521-007-0128-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-007-0128-4

Keywords

Search

Navigation