Advertisement

Smart Feature Extraction from Acoustic Camera Multi-sensor Measurements

  • Petia Koprinkova-Hristova
  • Volodymyr Kudriashov
  • Kiril Alexiev
  • Iurii Chyrka
  • Vladislav Ivanov
  • Petko Nedyalkov
Chapter
Part of the Studies in Computational Intelligence book series (SCI, volume 648)

Abstract

The paper applies recently developed smart approach for feature extraction from multi-dimensional data sets using Echo state networks (ESN) to the focalized spectra obtained from the acoustic camera multi-sensor measurements. The aim of the study is development of distance diagnostic system for prediction of wearing out of bearings. The procedure for initial features selection and features extraction from the focalized spectra was developed. Then the k-means clustering algorithm and Support vector machine (SVM) classifiers were applied to differentiate the tested bearings into two classes with respect to their condition (“Good” or “Bad”). The results using different dimensions of the extracted features space were compared.

Keywords

Smart signal processing Multi-sensor system Feature extraction Classification Echo state network IP tuning K-means clustering Support vector machine 

Notes

Acknowledgments

This work was partly supported by the project AComIn, grant 316087, funded by the FP7 Capacity Program (Research Potential of Convergence Regions).

References

  1. 1.
    Assent, I.: Clustering high dimensional data. Wiley Interdisc. Rev. Data Min. Knowl. Discovery 2(4), 340–350 (2012)CrossRefGoogle Scholar
  2. 2.
    Bozhkov, L., Koprinkova-Hristova, P., Georgieva, P.: Learning to Decode Human Emotions with Echo State Networks, Neural Networks, In Press, Corrected Proof. doi: 10.1016/j.neunet.2015.07.005. Accessed 7 Sept 2015
  3. .
    Buscarello, R.: Practical Solutions to Machinery and Maintenance Vibration Problems. http://www.update-intl.com/VibrationBook8g.htm (2002)
  4. 4.
    Bunte, K., Lee, J.A.: Unsupervised dimensionality reduction: the challenges of big data visualization. In: ESANN 2015 proceedings, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. Bruges (Belgium), 22–24 April 2015, i6doc.com publ. ISBN 978-287587014-8. http://www.i6doc.com/en/
  5. 5.
    Cai, T., Shen, X. (eds.): High-Dimensional Data Analysis, Frontiers of Statistics, vol. 2. World Scientific Publishing, Singapore (2010)Google Scholar
  6. 6.
    Christensen, J.J., Hald, J.: Beamforming. Brüel Kjær Tech. Rev. 1, 1–48 (2004)Google Scholar
  7. 7.
    Dempsey, P.J., Kreider, G., Fichter, T.: Tapered Roller Bearing Damage Detection Using Decision Fusion Analysis, NASA/TM—2006-214380, NASA (2006)Google Scholar
  8. 8.
    Graney, B.P., Starry, K.: Rolling element bearing analysis. Mater. Eval. 70(1), 78–85 (The American Society for Nondestructive Testing Inc.) (2011)Google Scholar
  9. 9.
    Hald, J.: Patch near-field acoustical holography using a new statistically optimal method. Brüel Kjær Tech. Rev. 1, 40–50 (2005)Google Scholar
  10. 10.
    Halme J., Andersson, P.: Rolling contact fatigue and wear fundamentals for rolling bearing diagnostics—state of the art. In: JET656 Proceedings IMechE, Part J: Journal Engineering Tribology, vol. 224 (2009)Google Scholar
  11. 11.
    James, C.R., Berry, J.E.: Description of PEAKVUE® and illustration of its wide array of applications in fault detection and problem severity assessment. In: Emerson Process Management Reliability Conference (2001)Google Scholar
  12. 12.
    Koprinkova-Hristova, P.: Multi-dimensional data clustering and visualization via Echo state networks. In: Kountchev, R., Nakamatsu, K. (eds.) Intelligent Systems Reference Library, New Approaches in Intelligent Control and Image Analysis: Techniques, Methodologies and Applications. Springer (2016)Google Scholar
  13. 13.
    Koprinkova-Hristova, P., Tontchev, N.: Echo state networks for multi-dimensional data clustering. Lecture Notes in Computer Science (including subseries Lecture Notes in Arti-ficial Intelligence and Lecture Notes in Bioinformatics), vol. 7552 (PART 1), pp. 571–578 (2012)Google Scholar
  14. 14.
    Lukosevicius, M., Jaeger, H.: Reservoir computing approaches to recurrent neural network training. Comput. Sci. Rev. 3, 127–149 (2009)CrossRefzbMATHGoogle Scholar
  15. 15.
    Michael J.R., Kacpryznski, G.J., Orsagh, R.F.: Advanced Vibration Analysis to Support Prognosis of Rotating Machinery Components. Impact Technologies, New YorkGoogle Scholar
  16. 16.
    Sarkissian, A.: Method of superposition applied to patch near-field acoustic holography. J. Acoust. Soc. Am. 118(2), 671–678 (2005)Google Scholar
  17. 17.
    Schrauwen, B., Wandermann, M., Verstraeten, D., Steil, J.J., Stroobandt, D.: Improving reservoirs using intrinsic plasticity. Neurocomputing 71, 1159–1171 (2008)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  • Petia Koprinkova-Hristova
    • 1
  • Volodymyr Kudriashov
    • 1
  • Kiril Alexiev
    • 1
  • Iurii Chyrka
    • 1
  • Vladislav Ivanov
    • 2
  • Petko Nedyalkov
    • 2
  1. 1.Institute of Information and Communication TechnologiesBulgarian Academy of SciencesSofiaBulgaria
  2. 2.Technical University of SofiaSofiaBulgaria

Personalised recommendations