Journal of Nondestructive Evaluation

, Volume 17, Issue 4, pp 209–221 | Cite as

Approximate inverse mapping in ECT, based on aperture shifting and neural network regression

  • Radu C. Popa
  • Kenzo Miya


The inversion procedure presented in this paper is based on the statistical regression of the inverse map between the spaces of ECT scan data, and of crack parameters. The mapping is realized by a combination between a statistical data processing step, i.e., a principal component transformation of the scan data, and an incremental resolution neural network training. Starting from the necessities of improving the detrimental conditioning of the regression and of providing the inversion approach with enhanced potential for automation, a novel “shifting aperture” mapping concept and a data fusion technique are proposed. Supplementing the primary mapping algorithm with these latter processing steps allows one to avoid the usual anomalous-region focusing approach and improves the inversion capabilities by allowing adynamic reconstruction of the object's profile. Unconnected and multiply connected crack shapes are well estimated, that so far eluded most other inversion methods. For this primary validation of the completed algorithm, only synthetic B-scan data are used, which are collected by an optimized, high performance sensor on the interior of a metal tube.

Key Words

Eddy current testing inverse mapping aperture neural network principal components 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    S. Fukui, A. Kurokawa, and H. Komatsu, Progress of verification test program of eddy current inspection technology for steam generator tube of nuclear power plant in Japan, inStudies in Applied Electromagnetics and Mechanics, Vol.12, Takagi et al., eds. (IOS Press, 1997), pp. 1–8.Google Scholar
  2. 2.
    T. Takagi, M. Uesaka, and K. Miya, Electromagnetic NDE research activities in JSAEM, in Studies in Applied Electromagnetics and Mechanics, Vol.12, Takagi,et al., eds. (IOS Press, 1997), pp. 9–16.Google Scholar
  3. 3.
    S. Barkeshli, D. J. Radecki, and H. A. Sabbagh, On a linearized inverse scattering model for a three-dimensional flaw embedded in anisotropic advanced composite materials,IEEE Geosci. Rem. Sens. 30(1):71–80 (1992).CrossRefGoogle Scholar
  4. 4.
    H. A. Sabbagh and R. G. Lautzenheiser, Inverse problems in electromagnetic nondestructive evaluation, inReview of Progress in Quant, NDE, Vol.13, Thompson and Chimenti, eds. (Plenum Press, New York, 1994), pp. 911–918.Google Scholar
  5. 5.
    V. Monebhurrun, D. Lesselier, and B. Duchêne, Eddy current nondestructive evaluation of a 3D bounded defect in a metal tube using volume integral methods and nonlinerized inversion schemes, inStudies in Applied Electromagnetics and Mechanics, Vol.14, Albaneseet al., eds. (IOS Press, 1998), pp. 261–270.Google Scholar
  6. 6.
    J. R. Bowler, Inversion of eddy current data to reconstruct flaws by an optimization process,Int. J. Appl. Electromagn. Mech. 4: 277–284 (1994).Google Scholar
  7. 7.
    J. R. Bowler, Review of eddy current inversion with application to nondestructive evaluation,Int. J. Appl. Electromagn. Mech. 8: 3–16 (1997).Google Scholar
  8. 8.
    Z. Badicset al., Rapid flaw reconstruction scheme for three-dimensional inverse problems in eddy current NDE, inStudies in Applied Electromagnetics and Mechanics, Vol.12, Takagiet al., eds. (IOS Press, 1997), pp. 303–309.Google Scholar
  9. 9.
    Z. Chen, K. Miya, and M. Kurokawa, Reconstruction of crack shapes using a newly developed ECT probe, inStudies in Applied Electromagnetics and Mechanics, Vol.14, Albaneseet al., eds. (IOS Press, 1998), pp. 225–232.Google Scholar
  10. 10.
    NDT Abstract—Neural networks in nondestructive testing,NDT & E Intern. 30(5):321–334 (1997).Google Scholar
  11. 11.
    J. M. Mann, L. W. Schmerr, and J. C. Moulder, Neural network inversion of uniform-field eddy current data,Mater. Eval. 1:34–39 (1991).Google Scholar
  12. 12.
    L. Udpa and S. S. Udpa, Application of signal processing and pattern recognition techniques to inverse problems in NDE.Int. J. Appl. Electromagn. Mech. 8:99–117 (1997).Google Scholar
  13. 13.
    F. C. Morabito, An intelligent network for defect profile reconstruction in eddy current applications, inStudies in Applied Electromagnetics and Mechanics, Vol.13, Kose and Sievert, eds. (IOS Press, 1998), pp. 434–437.Google Scholar
  14. 14.
    D. W. Oldenburg and R. G. Ellis, Inversion of geophysical data using an approximate inverse mapping,Geophys. J. Int. 105:325–353 (1991).Google Scholar
  15. 15.
    W. Lord and L. Upda, Imaging of electromagnetic NDT problem, InReview of Progress in Quant, NDE, Vol.5A, Thompson and Chimenti, eds. (Plenum Press, New York, 1986), pp. 465–471.Google Scholar
  16. 16.
    R. Zorgatti, B. Duchêne, D. Lesselier, and F. Pons, Eddy current testing of anomalies in conductive materials, Part I: Qualitative imaging via diffraction tomography techniques,IEEE Trans. Magn. 27(6):4416–4437 (1991).CrossRefGoogle Scholar
  17. 17.
    R. C. Popa and K. Miya, A data processing and neural network approach for the inverse problem in ECT, inStudies in Applied Electromagnetics and Mechanics, Vol.14, Albaneseet al., eds. (IOS Press, 1998), pp. 297–304.Google Scholar
  18. 18.
    R. C. Popa, K. Miya, and M. Kurokawa, Optimized eddy current detection of small cracks in steam generator tubing.J. Nondestr. Eval. 16(3): 161–173 (1997).CrossRefGoogle Scholar
  19. 19.
    D. Prémel and A. Mohammad-Djafari, Eddy current tomography in cylindrical geometry,IEEE Trans. Magn. 31(3):2000–2003 (1995).CrossRefGoogle Scholar
  20. 20.
    K. H. Hedengren, D. E. Ritscher, and B. R. Groshong, Probe footprint estimation in eddy-current imaging, inReview of Progress in Quant. NDE, Vol.9, Thompson and Chimenti, eds. (Plenum Press, 1990), pp. 845–852.Google Scholar
  21. 21.
    I. T. Jolliffe,Principal Component Analysis (Springer Verlag, New York, 1986).Google Scholar
  22. 22.
    A. K. Jain,Fundamentals of Digital Image Processing (Engle-wood Cliffs, NJ, Prentice Hall, 1989).Google Scholar
  23. 23.
    R. C. Popa, Optimized Crack Detection and Inversion in Eddy Current Testing, PhD Thesis, Nuclear Eng. Res. Lab., University of Tokyo (1998).Google Scholar
  24. 24.
    C. L. P. Chen, A rapid supervised learning neural network for function interpolation and approximation,IEEE Trans. Neurol. Net. 7(6):1220–1230 (1996).CrossRefGoogle Scholar

Copyright information

© Plenum Publishing Corporation 1998

Authors and Affiliations

  • Radu C. Popa
    • 1
  • Kenzo Miya
    • 1
  1. 1.Nuclear Engineering Research LaboratoryThe University of TokyoIbarakiJapan

Personalised recommendations