Advertisement

Hole Identification System in Conducting Plates by using Wavelet Networks

  • Giovanni Simone
  • Francesco Carlo Morabito
Conference paper
Part of the Perspectives in Neural Computing book series (PERSPECT.NEURAL)

Abstract

In this paper, we propose a wavelet network (WN) approach to the identification of holes in conducting plates, in the context of a Non Destructive Evaluation (NDE) signal processing system, based on the eddy currents inspection. The system aims to locate holes in the specimen under inspection by using a two-stage approach, namely, a WN followed by a least squares post-processing block. The WN stage estimates the distances between the hole and the sensor probes; the least squares stage identifies the hole on the basis of the distances computed by the previous neural block. The efficacy of the proposed approach is tested on artificial data and compared with different approaches based on feedforward multilayer perception (MLP) and on radial basis function neural network. The robustness of the system has been tested: the effects of the white noise and of the lift-off noise at different signal-to-noise ratios have been inspected.

Keywords

Global Position System Radial Basis Function Neural Network Wavelet Neural Network Neural Architecture Wavelet Network 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    J.Blitz, “Electrical and Magnetic Methods of Non-destructive Testing”, Chapman & Hall, Second Edition, 1997;CrossRefGoogle Scholar
  2. [2]
    F.C.Morabito, A.Gasparics, “A Wavelet Neural Network Processor of Eddy Current NDE Data”, Electromagnetic Nondestructive Evaluation (III), Lesselier and Razek Eds., IOS Press, 1999, pp. 108–116;Google Scholar
  3. [3]
    L.Udpa, S.S.Udpa, “Application of Signal Processing and Pattern Recognition Techniques to Inverse Problems in NDE”, International Journal of Applied Electromagnetics and Mechnaics, Vol.8, 1997, pp.99–117;Google Scholar
  4. [4]
    S.Haykin, “Neural Networks, A Comprehensive Foundation”, Macmillan, New York, 1994;MATHGoogle Scholar
  5. [5]
    C.Bishop, “Pattern Recognition and Neural Networks”, Oxford University Press, 1995;Google Scholar
  6. [6]
    F.C.Morabito, M.Campolo, “A Task Decomposition Neural Network Approach to Non-Destructive Testing Problems”, Proc. of World Congress on Neural Networks, 1994, Vol.1, pp.566–571;Google Scholar
  7. [7]
    B.W.Parkinson, F.Van Graas, P.K.Eng, et al., “Global Positioning System: Theory and Applications”, American Institute of Aeronautics and Astronautics, Vol.1 and 2, 1994;Google Scholar
  8. [8]
    M.P.Green, “Extended Kalman Filter for Integrating Tracking Data from Ground-Based Radar and Airborne Global Positioning System”, Master Thesis, M.I.T., 1998;Google Scholar
  9. Q.Zhang, “Using Wavelet Networks in Non-parametric Estimation”, IEEE Trans, on Neural Networks,Vol.8, No.2, March 1997, pp.227–236;CrossRefGoogle Scholar
  10. [10]
    L.M.Reyneri, “Unification of Neural and Wavelet Networks and Fuzzy Systems”, IEEE Trans, on Neural Networks, Vol.10, No.4, July 1999, pp.801–814.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London Limited 2002

Authors and Affiliations

  • Giovanni Simone
    • 1
  • Francesco Carlo Morabito
    • 1
  1. 1.Facoltà di Ingegneria Via GraziellaUniversità „Mediterranea“ di Reggio CalabriaReggio CalabriaItaly

Personalised recommendations