Skip to main content
SpringerLink
Log in

Classification of Steam Generator Tube Defects for Real-Time Applications Using Eddy Current Test Data and Self-Organizing Maps

  • Published:
Real-Time Systems Aims and scope Submit manuscript

Abstract

A new classification method, for isolating steam generator tube defects in nuclear power plants using Eddy Current Test (ECT) signals, has been developed. The method uses Self-Organizing maps (SOM) with different data signatures to identify and classify these defects. A multiple inference system is proposed which evaluates different extracted characteristic SOMs to infer the defect type. Wavelet zero-crossing representation, a linear predictive coding (LPC), and other basic signal representations, such as magnitude and phase, are used to construct characteristic vectors that combine one or more of these features. These vectors are evaluated for their ability to classify tube defects and the ones with the best performance are used in the multiple inference system. The effectiveness of the method is demonstrated by applications of the characteristic maps to ECT data from various cases of tube defects in pressurized water reactor plant steam generators. The developed algorithm enables real-time applications such as fast tube defects classification systems and visualization of ECT signal feature prototypes, which may improve the speed of time-critical decision making during power plant maintenance outages.

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

Similar content being viewed by others

References

  • Bouton, C., and Pagès, G. 1992. Self-organization and convergence of the one-dimensional Kohonen algorithm with non uniformly distributed stimuli. Laboratoire de Probabilitès. Universitè Paris VI, Paris.

    Google Scholar 

  • Brown, S. D. 1985. Template matching-an approach for the machine sorting of eddy current data. Materials Evaluation 43(12): 1553-1565.

    Google Scholar 

  • Chady, T., Enokizono, M., and Sikora, R. 2000. Neural network models of eddy current multi-frequency system for nondestructive testing. IEEE Transactions on Magnetics 36(4): 1724-1727.

    Google Scholar 

  • Chiueh, T. D., Tang, T. T., and Chen, L. G. 1994. Vector quantization using tree-structured self-organizing feature maps. IEEE Journals on Selected Areas in Communications 12(9): 1594-1599.

    Google Scholar 

  • Debeljak, Z., Strapac, M., and Medic-Saric, M. 2001. Application of self-organization maps for the classification of chromatographic systems and prediction of values of chromatographic quantities. Journal of Chromatography A 925: 31-40.

    Google Scholar 

  • Diercks, D. R., Bakhtiari, S., Chopra, O. K., Kasza, K. E., Kupperman, D. S., Majumdar, S., Park, J. Y., and Shack, W. J. 1997. Steam generator tube integrity program. Semiannual Report, NUREG/CR-6511, ANL-96/17, v. 1, USA.

  • Dodd, C. V. 1996. Data analysis for steam generator tubing samples. Report for US. Nuclear Regulatory Commission, NUREG/CR-6455, ORNL/TM-13206.

  • EPRI-Electric Power Research Institute. 1995. Steam generator eddy current data analysis performance demonstration. Review material, Palo Alto, USA.

  • Grossmann, A., and Morlet, J. 1984. Decomposition of Hardy functions into square integrable wavelets of constant shape. SIAM Journal of Mathematical Analysis 15(4): 723-736.

    Google Scholar 

  • Hooper, W. C., and Upadhyaya, B. R. 1998. An automated diagnostics system for eddy current data analysis of steam generator tubing. Annual Report of Nuclear Engineering Department of the University of Tennessee for the Electric Power Research Institute (EPRI).

  • Kang, S. J., Moon, J. C., Choi, D. H., Choi, S. S., and Woo, H. G. 1998. A distributed and intelligent system approach for the automatic inspection of steam-generator tubes in nuclear power plants. IEEE Transactions on Nuclear Science 45(3): 1713-1722.

    Google Scholar 

  • Kennedy, J., and Morasso, P. 1990. Application of self-organizing networks to signal processing. Lecture Notes on Computer Science 412: 225-232.

    Google Scholar 

  • Khandetsky, V., and Antonyuk, I. 2002. Signal processing in defect detection using back-propagation neural networks. NDT & E International 35(7): 483-488.

    Google Scholar 

  • Kohonen, T. 1982. Clustering, taxonomy, and topological maps of patterns. In Proceedings of the 6th International Conference on Pattern Recognition. Munich.

  • Kohonen, T., Mkisara, K., and Saramki, T. 1984. Phonotopic Maps-insightful representation of phonological features for speech recognition. In Proceedings of the 7th International Conference on Pattern Recognition. Los Alamitos.

  • Kohonen, T. 1988. The neural phonetic typewriter. Computer 21(3): 11-22.

    Google Scholar 

  • Kohonen, T. 2001. Self-Organizing Maps. Springer-Verlag.

  • Kurtz, R. J., Heasler, P. J., and Anderson, C. M. 1996. Performance demonstration tests for eddy current inspection of steam generator tubing. Pacific Northwest National Laboratory. Prepared for US Nuclear Regulatory Comission, NUREG/CR-6227, PNLL-9433, USA.

  • LCIS-Laboratory of Computer and Information Science. 2000. SOM Toolbox version 2. Finland (http://www.cis.hut.fi/projects/somtoolbox/).

  • Makhoul, J. 1975. Linear prediction: a tutorial review. Proceedings of IEEE 63(4): 561-580.

    Google Scholar 

  • Mallat, S. 1991. Zero-crossings of a wavelet transform. IEEE Transactions on Information Theory 37(4): 1019-1033.

    Google Scholar 

  • McMaster, R. C. 1959. Nondestructive Testing Handbook. Edited for the American Society for Nondestructive Testing, Ronald Press, New York.

    Google Scholar 

  • Petri, M. C., Wei, T. Y. C., Kupperman, D. S., Reifman, J., and Morman, J. A. 2000. Eddy current signal deconvolution technique for the improvement of steam generator tubing burst pressure predictions. Journal of Nondestructive Evaluation 19(4): 149-164.

    Google Scholar 

  • Rabiner, L. R., and Schafer, R. W. 1978. Digital Processing of Speech Signals. Prentice-Hall, New Jersey.

    Google Scholar 

  • Rajesh, S. N., Udpa, L., and Udpa, S. S. 1993. Numerical model based approach for estimating probability of detection in NDE applications. IEEE Transactions on Magnetics 29(2): 1857-1860.

    Google Scholar 

  • Rao, B. P. C., Raj, B., Jayakumar, T., and Kalyanasundaram, P. 2002. Using artificial neural network to quantify discontinuities in eddy current testing. Materials Evaluation 60(1): 84-88.

    Google Scholar 

  • Sadjadi, M. R. A., Yao, D., Huang, Q., and Dobeck, G. J. 2000. Underwater target classification using wavelet packets and neural networks. IEEE Transactions on Neural Networks 11(3): 784-794.

    Google Scholar 

  • Shindo, Y., Yoshie, S., and Marimoto, M. 1985. Quantitative system for evaluating eddy current testing of heat exchanger tubing. Materials Evaluation 43(10): 1299.

    Google Scholar 

  • Shyamsunder, M. T., Rajagopalan, C., Ray, K. K., and Raj, B. 1995. A comparative study of conventional and artificial neural network classifiers for eddy-current signal classification. Insight 37(1): 26-30.

    Google Scholar 

  • Shyamsunder, M. T., Rajagopalan, C., Raj, B., Dewangar, S. K., Rao, B. P. C., and Ray, K. K. 2000. Pattern recognition approaches for the detection and characterization of discontinuities by eddy current testing. Materials Evaluation 58(1): 93-101.

    Google Scholar 

  • Simone, G., and Morabito, F. C. 2001. RBFNN-based hole identification system in conducting plates. IEEE Transactions on Neural Networks 12(6): 1445-1454.

    Google Scholar 

  • Stolte, J., Udpa, L., and Lord, W. 1982. Multifrequency eddy current testing of steam generator tubes using optimal affine transformation. In Review of Progress in Quantitative Nondestructive Evaluation. New York: Plenum Press.

    Google Scholar 

  • The Mathworks, 2000. Inc. Matlab version 5.3. USA.

  • Udpa, L., and Udpa, S. S. 1990. Eddy current defect characterization using neural networks. Materials Evaluation 48(3): 342-347.

    Google Scholar 

  • Udpa, S. S., and Lord, W. 1984. A Fourier descriptor classification scheme for differential probe signals. Materials Evaluation 42(9): 1136-1141

    Google Scholar 

  • Upadhyaya, B. R., Yan, W., and Berkan, R. C. 1993. Hybrid digital signal processing and neural networks for automated diagnostics using NDE method. Annual Report of Nuclear Engineering Department of the University of Tennessee for the US Nuclear Regulatory Commission Office of Nuclear Regulatory Research, USA.

  • Upadhyaya, B. R., Erbay, A. S., Hzi, G., and Sung, K. Y. 1999. Eddy current test data analysis for steam generator tubing diagnosis using artificial intelligence methods. Annual Report of Nuclear Engineering Department of the University of Tennessee for the Electric Power Research Institute (EPRI), USA.

  • Wade, M. A. 1993. Numerical study of linear predictive coding for the compression of gray scale images. M.Sc. Thesis, University of Tennessee, Knoxville.

    Google Scholar 

  • Yan, W., and Upadhyaya, B. R. 1996. Development of an automated diagnostics system for eddy current analysis using applied artificial intelligence techniques. Annual Report of Nuclear Engineering Department of the University of Tennessee for the Electric Power Research Institute (EPRI), USA.

  • Young, N. 1988. An Introduction to Hilbert Space. New York: Cambridge University Press.

    Google Scholar 

  • Zaoui, F., Marchand, C., and Razek, A. 1997. Localization and shape classification of defects using the finite element method and the neural networks. In Proceedings of the 3rd International Workshop on E'NDE. Reggio Calabria, Italy, September.

Download references

Author information

Authors and Affiliations

  1. Nuclear Engineering Center, Nuclear and Energetic Research Institute (IPEN) and Mechanical Engineering Department, University of São Paulo, São Paulo, Brazil

    Roberto N. de Mesquita

  2. Nuclear Engineering Center, Nuclear and Energetic Research Institute (IPEN), São Paulo, Brazil

    Daniel K. S. Ting

  3. Mechanical Engineering Department, University of São Paulo, São Paulo, Brazil

    Eduardo L. L. Cabral

  4. Nuclear Engineering Department, The University of Tennessee, Knoxville, USA

    Belle R. Upadhyaya

Authors
  1. Roberto N. de Mesquita
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Daniel K. S. Ting
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Eduardo L. L. Cabral
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Belle R. Upadhyaya
    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

de Mesquita, R.N., Ting, D.K.S., Cabral, E.L.L. et al. Classification of Steam Generator Tube Defects for Real-Time Applications Using Eddy Current Test Data and Self-Organizing Maps. Real-Time Systems 27, 49–70 (2004). https://doi.org/10.1023/B:TIME.0000019126.26053.23

Download citation

  • Issue Date:

  • DOI: https://doi.org/10.1023/B:TIME.0000019126.26053.23

Search

Navigation