ICANN ’93 pp 799-804 | Cite as

Hybrid Digital Signal Processing and Neural Networks for Automated Diagnostics Using Eddy Current Inspection

  • Wu Yan
  • Belle R. Upadhyaya
Conference paper


The primary purpose of the current research is to develop an integrated approach by combining information compression methods and artificial neural networks for the monitoring of plant components using nondestructive examination (NDE) data. Specifically, data from eddy current inspection of heat exchanger tubing are utilized to develop this technology. The results of analysis show that for effective (low-error) artifact type classification and estimation of parameters, it is necessary to identify proper feature vectors using different data representation methods.


Mean Square Error Nondestructive Test Defect Type Defect Parameter Fourier Descriptor 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    W. E. Deeds and C. V. Dodd, “Eddy Current Inspection of Steam Generator Tubing,” Electromagnetic Methods of Nondestructive Testing, Vol. 3 of Nondestructive Testing Monographs and Tracts, W. Lord, Ed., Gordon and Breach, New York, 1985.Google Scholar
  2. 2.
    C. V. Dodd and W. E. Deeds, “In-Service Inspection of Steam-Generator Tubing Using Multiple-Frequency Eddy-Current Techniques,” Special Technical Publication, American Society for Testing and Material, Philadelphia, PA., 1981.Google Scholar
  3. 3.
    L. Udpa and S.S. Udpa, “Neural Networks for the Classification of Nondestructive Evaluation Signals,” IEE Proceedings-F, Vol. 138, No. 1, February 1991.Google Scholar
  4. 4.
    T. Pavlidis, “Algorithms for Shape Analysis of Contours and Waveforms,” IEEE Transaction on Pattern Analysis and Machine Intelligence, Vol. PAMI-2, No. 4, July 1980.Google Scholar
  5. 5.
    “Eddy Current Nondestructive Testing,” U.S. National Bureau of Standards Special Publication 589, 1981.Google Scholar
  6. 6.
    E. Persoon and K. S. Fu, “Shape Discrimination Using Fourier Descriptors,” IEEE Trans., SMC-7, pp. 170–179, March 1977.Google Scholar
  7. 7.
    G. H. Granlund, “Fourier Preprocessing for Hand Print Character Recognition,” IEEE Trans., C-21, pp. 195–201, February 1972.MathSciNetGoogle Scholar
  8. 8.
    “Neural Computing,” NeuralWorks Professional II/PLUS and neural Works Explorer Software, NeuralWare, Inc., 1991.Google Scholar
  9. 9.
    R. C. McMaster, P. McIntire, and M. L. Mester (Eds), “Nondestructive Testing Handbook,” Vol. 4 (Electromagnetic Testing), Am. Soc. for Nondestructive Testing, 1987.Google Scholar
  10. 10.
    B. R. Upadhyaya and E. Eryurek, “Application of Neural Networks for Sensor Validation and Plant Monitoring,” Nuclear Technology, Vol. 27, No. 2, pp. 170–176, 1992.Google Scholar
  11. 11.
    D. Rumelhart and J. McClelland, Paralled Distributed Processing. Vol. 2, Bradford Books/MIT Press, Cambridge, MA, 1986.Google Scholar
  12. 12.
    R. P. Lippmann, “An Introduction to Computing with Neural Nets,” IEEE ASSP Magazine, Vol. 4, No. 2, pp. 4–22, April 1987.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London Limited 1993

Authors and Affiliations

  • Wu Yan
    • 1
  • Belle R. Upadhyaya
    • 1
  1. 1.Department of Nuclear EngineeringThe University of TennesseeKnoxvilleUSA

Personalised recommendations