Structural Pattern Recognition for Industrial Machine Sounds Based on Frequency Spectrum Analysis

  • Yolanda Bolea
  • Antoni Grau
  • Arthur Pelissier
  • Alberto Sanfeliu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3287)


In order to discriminate different industrial machine sounds contaminated with perturbations (high noise, speech, etc.), a spectral analysis based on a structural pattern recognition technique is proposed. This approach consists of three steps: 1) to de-noise the machine sounds using the Morlet wavelet transform, 2) to calculate the frequency spectrums for these purified signals, and 3) to convert these spectrums into strings, and use an approximated string matching technique, finding a distance measure (the Levenshtein distance) to discriminate the sounds. This method has been tested in artificial signals as well as in real sounds from industrial machines.


Wavelet Coefficient Morlet Wavelet Edit Operation Levenshtein Distance Approximate Match 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Mori, K., Kasashima, N., Yoshioha, T., Ueno, Y.: Prediction of Spalling on a Ball Bearing by Applying the Discrete Wavelet Transform to Vibration Signals. Wear 195(1-2), 162–168 (1996)CrossRefGoogle Scholar
  2. 2.
    Liu, H.-C., Srinath, M.D.: Classification of partial shapes using string-to-string matching. Intell. Robots and Comput. Vision, SPIE Proc. 1002, 92–98 (1989)Google Scholar
  3. 3.
    Bolea, Y., Grau, A., Sanfeliu, A.: Non-speech Sound Feature Extraction based on Model Identification for Robot Navigation. In: Sanfeliu, A., Ruiz-Shulcloper, J. (eds.) CIARP 2003. LNCS, vol. 2905, pp. 221–228. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  4. 4.
    Mallat, S., Zhang, Z.: Matching pursuits with time-frequency dictionaries. IEEE Trans. on Signal Processing 45(12), 3397–3415 (1993)CrossRefGoogle Scholar
  5. 5.
    Donoho, D.-L.: De-noising by soft-thresholding. IEEE Trans. on Information Theory 33(7), 2183–2191 (1999)MathSciNetGoogle Scholar
  6. 6.
    Lin, J.: Feature Extraction of Machine Sound using Wavelet and its Application in Fault Diagnosis. NTD&E International 34, 25–30 (2001)Google Scholar
  7. 7.
    Sankoff, D., Kruskal, J.B. (eds.): Time Warps, String Edit and Macromolecules: The Theory and Practice of Sequence Comparison. Addison-Wesley, Reading (1983)Google Scholar
  8. 8.
    Bunke, H., Sanfeliu, A.: Syntactic and Structural Pattern Recognition Theory and Applications. Series in Computer Science, vol. 7. World Scientific Publ., Singapore (1990)zbMATHGoogle Scholar
  9. 9.
    Goupilland, P., Grossmann, A., Morlet, J.: Cycle octave and related transforms in seismic signal analysis. Geoexploration 23, 85–102 (1984)CrossRefGoogle Scholar
  10. 10.
    Wagner, R.A., et al.: The string-to-string correction problem. J. Ass. Comput. Mach. 21(1), 168–173 (1974)zbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Yolanda Bolea
    • 1
  • Antoni Grau
    • 1
  • Arthur Pelissier
    • 1
  • Alberto Sanfeliu
    • 2
  1. 1.Automatic Control DeptTechnical University of Catalonia UPCBarcelonaSpain
  2. 2.Institute of RoboticsIRI, UPCBarcelonaSpain

Personalised recommendations