Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Skip to main content
Springer Nature Link
Log in

Classification of faults in gearboxes — pre-processing algorithms and neural networks

  • Articles
  • Published:
Neural Computing & Applications Aims and scope Submit manuscript

Abstract

Classical signal processing techniques when combined with pattern classification analysis can provide an automated fault detection procedure for machinery diagnostics. Artificial neural networks have recently been established as a powerful method of pattern recognition. The neural networkbased fault detection approach usually requires preprocessing algorithms which enhance the fault features, reducing their number at the same time. Various timeinvariant and timevariant signal preprocessing algorithms are studied here. These include spectral analysis, time domain averaging, envelope detection, Wigner-Ville distributions and wavelet transforms. A neural network pattern classifier with preprocessing algorithms is applied to experimental data in the form of vibration records taken from a controlled tooth fault in a pair of meshing spur gears. The results show that faults can be detected and classified without errors.

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

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

References

  1. Cempel C. Vibroacoustical diagnostics of machinery: an outline.Mechanical Systems and Signal Processing 1988; 2(2): 135–151

    Google Scholar 

  2. Cempel C.Vibroacoustic Condition Monitoring. Ellis Horwood, Chichester, 1991

    Google Scholar 

  3. Lyon RH.Machinery Noise and Diagnostics. Butterworths, Boston, 1987

    Google Scholar 

  4. Staszewski WJ, Tomlinson GR. Time-variant methods in machinery diagnostics. In:International Workshop on Safety Evaluation of Time-Variant and Nonlinear Structures Using Identification Approaches, Lambrecht, Germany, 6–9 September 1992

    Google Scholar 

  5. Stewart RM. Some useful data analysis techniques for gearbox diagnostics. Technical Report Paper MHM/R/10/77, Institute of Sound and Vibration, Southampton, 1977

    Google Scholar 

  6. Staszewski WJ. Gearbox vibration diagnostics — an overview. In:Proceedings of the 8th International Congress on Condition Monitoring and Diagnostic Engineering Management (COMADEM-96), Sheffield, England, 16–18 July 1996

    Google Scholar 

  7. Staszewski WJ, Tomlinson GR. Application of the wavelet transform to fault detection in a spur gear.Mechanical Systems and Signal Processing 1994; 8(3): 289–307

    Google Scholar 

  8. Wang WJ, McFadden PD. Early detection of gear failure by time-frequency analysis. part 2: Interpretation of the time-frequency distribution using image processing techniques.Mechanical Systems and Signal Processing 1993; 7(3): 205–215

    Google Scholar 

  9. Wang WJ, McFadden PD. Gear diagnostics by interpreting images of time-frequency energy distribution of vibration signals. In:Proceedings of the 5th International Congress on Condition Monitoring and Diagnostic Engineering Management (COMADEM-93), Bristol, England, 21–23 July 1993

    Google Scholar 

  10. Staszewski WJ, Worden K, Starr AG. Gear fault detection and severity classification using neural networks. In:Proceedings of the 6th International Congress on Condition Monitoring and Diagnostic Engineering Management (COMADEM–94), New Delhi, India, 1994

  11. Worden K, Staszewski WJ, Tomlinson GR. Timefrequency analysis in gearbox fault detection. Part ii: Interpretation of the Wigner-Ville distribution using pattern recognition analysis.Mechanical Systems and Signal Processing 1996 (Submitted).

  12. Randall RB. A new method of modelling gear faults.Trans. ASME, J. Mechanical Design 1982; 104: 259–267

    Google Scholar 

  13. Braun S. The extraction of periodic waveforms by time domain averaging.Acoustica 1975; 32(2): 67–69

    Google Scholar 

  14. McFadden PD. Examination of a technique for the early detection of failure in gears by signal processing of the time domain average of the meshing vibration.Mechanical System and Signal Processing 1987; 1(2): 173–183

    Google Scholar 

  15. McFadden PD, Smith JD. A signal processing technique for detecting local defects in a gear from the signal average of the vibration.Proceedings of the Institute of Mechanical Engineers 1985; 199(C4): 287–292

    Google Scholar 

  16. Mitchell JS.An Introduction to Machinery Analysis and Monitoring, Penn Well Books, Tulsa, Oklahoma, 1981

    Google Scholar 

  17. Langley RS. On various definitions of the envelope of a random process.Journal of Sound and Vibration 1988; 105(3): 503–512

    Google Scholar 

  18. Bracewell RN.The Fourier Transform and its Application, McGraw-Hill, New York, 1978

    Google Scholar 

  19. Dugundji J. Envelopes and pre-envelopes of real waveforms.IRE Transactions on Information Theory 1958; IT-4: 53–57

    Google Scholar 

  20. McFadden PD. Detecting fatigue cracks in gears by amplitude and phase demodulation of the meshing vibration.Transaction of the ASME Journal of Vib. Acoustics, Stress and Rel. in Design 1986; 108: 165–170

    Google Scholar 

  21. McFadden PD. Determining the location of a fatigue crack in a gear from the phase of the change in the meshing vibration.Mechanical System and Signal Processing 1988; 2(4): 403–409

    Google Scholar 

  22. Cempel C, Staszewski WJ. Signal demodulation procedure in machinery diagnostics — a case study. In:VI International IMECO Conference, Prague, Czech Republic, May 1989

  23. Cohen L. Time-frequency distributions — a review.Proceedings of the IEEE 1989; 77(7): 941–981

    Google Scholar 

  24. Claasen TACM, Mecklenbrauker WFG. The Wigner distribution — a tool for time-frequency analysis. Part 1: Continuous time signals.Philips J. Res 1980; 35(3): 217–250

    Google Scholar 

  25. Claasen TACM, Mecklenbrauker WFG. The Wigner distribution — a tool for time-frequency analysis. Part 2: Discrete time signals.Philips J. Res. 1980; 35(4/5): 276–300

    Google Scholar 

  26. Claasen TACM, Mecklenbrauker WFG. The Wigner distribution — a tool for time-frequency analysis. Part 3: Relations with other time-frequency transformations.Philips J. Res. 1980; 35(6): 372–389

    Google Scholar 

  27. Staszewski WJ.The Application of time-variant analysis to gearbox fault detection. PhD Thesis, University of Manchester, Department of Engineering, 1994

  28. Forrester BD. Use of the Wigner-Ville distribution in helicopter transmission fault detection. In:Proc. of the Australian Symposium on Signal Processing and Applications — ASSPA 89 Adelaide, Australia, 17–19 April 1989, pp. 77–82

  29. Meng Q, Qu L. Rotating machinery fault diagnosis using Wigner distribution.Mechanical Systems and Signal Processing 1991; 5(3): 155–166

    Google Scholar 

  30. McFadden PD, Wang WJ. Analysis of gear vibration signatures by the weighted Wigner-Ville distribution. In:Proceedings of the Fifth International Conference on Vibrations in Rotating Machinery, Bath, UK, September 1992

  31. Gabor D. Theory of communication.J. Inst. Electr. Eng 1946; 93(3): 429–457

    Google Scholar 

  32. Helstrom CW. An expansion of a signal in gaussian elementary signals.IEEE Trans. on Inf. Theory 1966; IT-12: 81–82

    Google Scholar 

  33. Chui ChK.An Introduction to Wavelets: Wavelets Analysis and its Applications, vol 1, Academic Press, Boston, 1992

    Google Scholar 

  34. Chui ChK, editor.Wavelets: A Tutorial in Theory and Applications. Wavelets Analysis and its Applications, vol 2, Academic Press, Boston, 1992

    Google Scholar 

  35. Daubechies I. The wavelet transform — a method for time-frequency localization. In: Haykin S, editor,Advances in Spectrum Analysis and Array Processing. vol I., Prentice Hall, Englewood Cliffs, NJ, 1991

    Google Scholar 

  36. Grossmann A, Kronland-Martinet R, Morlet J. Reading and understanding continuous wavelet transform. In: Combes JM, Grossmann A, Tchamitchian Ph, editors,Wavelets. Time-Frequency Methods and Phase Space, Springer-Verlag, Berlin, 1989

    Google Scholar 

  37. Kronland-Martinet R, Grossmann A. Application of time-frequency and time-scale methods (wavelet transform) to the analysis, synthesis and transformation of natural sounds. In: Piccialli A, Deppoli G, Roads C, editors,Representation of Musical Signals, MIT Press, Cambridge, MA, 1991

    Google Scholar 

  38. Grossman A, Morlet J. Decompositions of functions into wavelets of constant shape, and related transforms. In: Streit L, editor,Mathematics and Physics, Lecture on Recent Results, World Scientific, Singapore, 1985

    Google Scholar 

  39. Kronland-Martinet R, Morlet J. analysis of sound through wavelet transforms.International Journal of Pattern Recognition and Artificial Intelligence 1987; 1(2): 273–302

    Google Scholar 

  40. Staszewski WJ, Worden K. Classification of faults in spur gears. In:The World Congress on Neural Networks; Portland, Oregon, 11–15 July 1993

  41. Wang WJ, McFadden PD. Application of the wavelet transform to gearbox vibration analysis. In:The 16th Annual Energy-Sources Technology Conference and Exhibition, Structural Dynamics and Vibration, Houston, TX, 31 January–4 February 1993

  42. Staszewski WJ, Tomlinson GR. Report on the application of the signal demodulation procedure to the detection of broken and cracked teeth utilizing the pyestock fzg spur gear test rig. Technical report, University of Manchester, Department of Engineering, 1992

  43. Schalkoff R.Pattern Recognition. Statistical, Structural and Neural Approaches, John Wiley, New York, 1992

    Google Scholar 

  44. Bishop CM.Neural Networks for Pattern Recognition, Clarendon Press, Oxford, 1995

    Google Scholar 

  45. Worden K.MLP —A User Manual (obtainable via k.worden@sheffield.ac.uk), 1996

  46. Richard MD, and Lippmann RP. Neural network classifiers estimate bayesiana posteriori probabilities.Neural Computation 1991; 3: 461–483

    Google Scholar 

  47. DTI.Neural Computing Learning Solutions: Best Practice Guideline for Developing Neural Computing Applications, 1994

Download references

Author information

Authors and Affiliations

  1. Dynamics Research Group, Department of Mechanical Engineering, University of Sheffield, Mappin Street, S1 3JD, Sheffield, UK

    W. J. Staszewski & K. Worden

Authors
  1. W. J. Staszewski
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. K. Worden
    View author publications

    You can also search for this author in PubMed Google Scholar

Rights and permissions

Reprints and permissions

About this article

Cite this article

Staszewski, W.J., Worden, K. Classification of faults in gearboxes — pre-processing algorithms and neural networks. Neural Comput & Applic 5, 160–183 (1997). https://doi.org/10.1007/BF01413861

Download citation

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF01413861

Keywords

Search

Navigation