Smart Structures and Systems

Techno-Press (테크노프레스)
권호 표지
DOI QR코드

DOI QR Code

Early warning of hazard for pipelines by acoustic recognition using principal component analysis and one-class support vector machines

  • Wan, Chunfeng (International Institute for Urban Systems Engineering, School of Civil Engineering, Southeast University) ;
  • Mita, Akira (System Design Department, Keio University)
  • Received : 2009.07.29
  • Accepted : 2009.10.06
  • Published : 2010.05.25
⟨ Previous Next ⟩

Abstract

This paper proposes a method for early warning of hazard for pipelines. Many pipelines transport dangerous contents so that any damage incurred might lead to catastrophic consequences. However, most of these damages are usually a result of surrounding third-party activities, mainly the constructions. In order to prevent accidents and disasters, detection of potential hazards from third-party activities is indispensable. This paper focuses on recognizing the running of construction machines because they indicate the activity of the constructions. Acoustic information is applied for the recognition and a novel pipeline monitoring approach is proposed. Principal Component Analysis (PCA) is applied. The obtained Eigenvalues are regarded as the special signature and thus used for building feature vectors. One-class Support Vector Machine (SVM) is used for the classifier. The denoising ability of PCA can make it robust to noise interference, while the powerful classifying ability of SVM can provide good recognition results. Some related issues such as standardization are also studied and discussed. On-site experiments are conducted and results prove the effectiveness of the proposed early warning method. Thus the possible hazards can be prevented and the integrity of pipelines can be ensured.

Keywords

References

  1. Cattell, R.B. (1966), "The Scree test for the number of factors", Multivar. Behav. Res., 1(2), 245-276. https://doi.org/10.1207/s15327906mbr0102_10
  2. Eiber, R.J., Jones, D.J. and Kramer, G.S. (1987), "Outside force causes most natural gas pipeline failures", Oil Gas J., 85(11), 52-57.
  3. Gaunard, P., Mubikangiey, C.G., Couvreur, C. and Fontaine, V. (1998), "Automatic classification of environmental noise events by hidden Markov model", Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, Seattle, WA , USA, May.
  4. Goldhor, R.S. (1993), "Recognition of environment sounds", Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, Minneapolis, MN, USA, April.
  5. Hausamann, D., Zirnig, W. and Schreier, G. (2003), "Monitoring of gas transmission pipelines-A customer driven civil UAV application", Proceedings of the ODAS Conference, Toulouse, France, June.
  6. Huebler, J.E. (2004), Detection of unauthorized construction equipment in pipeline right-of-ways, Technical Report of Gas Technology Institute.
  7. Jackson, J.E. (1991), A user's Guide to Principal Components, John Wiley & Sons, Inc.
  8. Jain, A.K., Duin, R.P.W. and Mao, J. (2000), "Statistical pattern recognition: a review", IEEE Trans. Pattern Anal. Mach. Intell., 22(1), 4-37. https://doi.org/10.1109/34.824819
  9. Jolliffe, I.T. (1986), Principal Component Analysis, Springer-Verlag New York Inc.
  10. Kaiser, H.F. (1960), "The application of electronic computers to factor analysis", Educ. Psychol. Meas., 20, 141-151. https://doi.org/10.1177/001316446002000116
  11. Krishna, A.G. and Sreenivas, T.V. (2004), "Music instrument recognition: from isolated notes to solo phrases", Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, Montreal, Quebec, Canada, May.
  12. Lu, L., Li, S.Z. and Zhang, H.J. (2001), "Content-based audio segmentation using support vector machines", Proceedings of the IEEE International Conference on Multimedia and Expo, Tokyo, Japan.
  13. Lu, L., Li, S.Z. and Zhang, H.J. (2003), "Content-based audio classification and segmentation by using support vector machines", Multimedia Syst., 8(6), 482-492. https://doi.org/10.1007/s00530-002-0065-0
  14. Ma, L., Milner, B. and Smith, D. (2006), "Acoustic environment classification", ACM TSLP, 3(2), 1-22.
  15. Peltonen, V., Tuomi, J., Klapuri, A., Huopaniemi, J. and Sorsa, T. (2002), "Computational auditory scene recognition", Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, Orlando, Florida, USA, May.
  16. Toyoda, Y., Huang, J., Ding, S. and Liu, Y. (2004), "Environmental sound recognition by multilayered neural networks", Proceedings of the 4th International Conference on Computer and Information Technology, Wuhan, China, September.
  17. Unnthorsson, R., Runarsson, T.P. and Jonsson, M.T. (2003), "Model selection in one class nu-SVMs using RBF kernels", Proceedings of the 16th Conference on Condition Monitoring and Diagnostic, April.
  18. Vapnik, V. (1979), Estimation of Dependences Based on Empirical Data (in Russian), Nauka, Moscow, Russia (English translation: Springer Verlag, New York, 1982).
  19. Vapnik, V. (1995), The Nature of Statistical Learning Theory, Springer-Verlag, New York.
  20. Wan, C., Mita, A. and Kume, T. (2008), "An automatic pipeline monitoring system using sound information", Struct. Contr. Health Monit., published online., Available at http://www3.interscience.wiley.com/journal/121552603/abstract.
  21. Wan, C. and Mita, A. (2008), "Recognition of potential danger to buried pipelines based on sounds", Struct. Contr. Health Monit., published online., Available at http://www3.interscience.wiley.com/journal/121575104/abstract.
  22. Wan, C. and Mita, A. (2009), "Pipeline monitoring using acoustic PCA recognition with Mel scale", Smart Mater. Struct., 18(5).
  23. Principal Component Analysis (PCA), Lecture slides at Computer Science Department of University of Nevada, Available at http://www.cse.unr.edu/~bebis/MathMethods/PCA/lecture.pdf.
  24. Principal Component Analysis, notes from Indiana University, Available at http://rguha.net/writing/notes/stats/ node7.html.
  25. Principal Components and Factor Analysis, electronic statistics textbook, StatSoft, Inc., Available at http:// www.statsoft.com/textbook/stfacan.html.

Cited by

  1. Support vector machine for prediction of the compressive strength of no-slump concrete vol.11, pp.4, 2013, https://doi.org/10.12989/cac.2013.11.4.337
  2. Applying robust variant of Principal Component Analysis as a damage detector in the presence of outliers vol.50-51, 2015, https://doi.org/10.1016/j.ymssp.2014.05.032