Crack Parameter Characterization by a Neural Network

  • M. Takadoya
  • J. D. Achenbach
  • Q. C. Guo
  • M. Kitahara

Abstract

A neural network with binary outputs is presented to determine the angle and the depth of a surface-breaking crack from ultrasonic backscattering data. The estimation procedure is divided into two steps:
  1. 1.

    The angle of the crack is estimated in the range from 10 to 70 degrees with a precision of 5 degrees. To improve the accuracy of estimation, information on the integral of the backscattered signal is utilized.

     
  2. 2.

    2. When the angle of the crack has been estimated, the depth of the crack is determined with a precision of 0.5mm in the range from 2.0mm to 4.0mm. This determination is achieved by employing sets of neural networks corresponding to various angles of the crack.

     

Keywords

Deconvolution 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Ch. Zhang and J.D. Achenbach, Ultrasonics, 26, 132 (1988).CrossRefGoogle Scholar
  2. 2.
    M. Takadoya, Y. Yabe, M. Kitahara, J.D. Achenbach, Q.C. Guo, and M.L. Peterson, in Review of Progress in Quantitative NDE, Vol.l4A, edited by D.O. Thompson and D.E. Chimenti (Plenum Press, New York, 1995), p.771.Google Scholar
  3. 3.
    M. Takadoya, Y. Yabe, J.D. Achenbach, Q.C. Guo, M.L. Peterson, and M. Kitahara, in Review of Progress in Quantitative NDE, Vol.13А, edited by D.O. Thompson and D.E. Chimenti (Plenum Press, New York, 1994), p.887.Google Scholar
  4. 4.
    M. Takadoya, M. Notake, M. Kitahara, J.D. Achenbach, Q.C. Guo and M.L. Peterson, in Review of Progress in Quantitative NDE, Vol.12A, edited by D.O. Thompson and D.E. Chimenti (Plenum Press, New York, 1993), p.803.Google Scholar

Copyright information

© Plenum Press, New York 1996

Authors and Affiliations

  • M. Takadoya
    • 1
  • J. D. Achenbach
    • 2
  • Q. C. Guo
    • 2
  • M. Kitahara
    • 3
  1. 1.Advanced Science Dept.Mitsubishi Research InstituteTokyoJapan
  2. 2.Center for Quality Engineering and Failure PreventionNorthwestern UniversityEvanstonUSA
  3. 3.Faculty of Marine Science and TechnologyTokai UniversityShizuokaJapan

Personalised recommendations