Russian Journal of Nondestructive Testing

, Volume 41, Issue 12, pp 815–821 | Cite as

An improved genetic local search algorithm for defect reconstruction from MFL signals

  • W. Han
  • P. Que
Magnetic Methods
Received:

Abstract

This paper presents an improved genetic local algorithm by incorporating the simulated-annealing technique into the perturbation process of the genetic local search algorithm and proposes an improved-genetic-local-search-algorithm-based inverse algorithm for two-dimensional defect reconstruction from the magnetic-flux-leakage signals. In the algorithm, a radial-basis-function neural network is utilized as a forward model, and the improved genetic local search algorithm is used to solve the optimization problem in the inverse problem. Experiments are presented to compare the proposed inverse algorithm with both the canonical-genetic-algorithm-based inverse algorithm and the genetic-local-search-algorithm-based inverse algorithm. The results demonstrate that the proposed inverse algorithm is more accurate and robust to the noise.

Keywords

Neural Network Inverse Problem Structural Material Local Search Search Algorithm 
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.
This is a preview of subscription content, log in to check access.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Ramuhalli, P., Udpa, L., and Udpa, S.S., Electromagnetic NDC Signal Inversion by Function-Approximation Neural Networks, IEEE Trans. Magn., 2002, vol. 38, no. 6, pp. 3633–3642.CrossRefGoogle Scholar
  2. 2.
    Lim, J., Data Fusion for NDE Signal Characterization, Dissertation, Iowa State University, 2001.Google Scholar
  3. 3.
    Hwang, K., Mandayam, S., Udpa, S.S., Udpa, L., Lord, W., and Atzal, M., Characterization of Gas Pipeline Inspection Signals Using Wavelet Basis Function Neural Networks, NDT Int., 2000, vol. 33, no. 8, pp. 531–545.Google Scholar
  4. 4.
    Ramuhalli, P., Udpa, L., and Udpa, S.S., Neural Network-Based Inversion Algorithms in Magnetic Flux Leakage Nondestructive Evaluation, J. Appl. Phys., 2003, vol. 93, no. 103, pp. 8274–8276.Google Scholar
  5. 5.
    Li, Y., Udpa, L., and Udpa, S.S., Three-Dimensional Defect Reconstruction From Eddy-Current NDE Signals Using a Genetic Local Search Algorithm, IEEE Trans. Magn., 2004, vol. 40, no. 2, pp. 410–417.Google Scholar
  6. 6.
    Goldberg, D.E., Genetic Algorithms in Search, Optimization, and Machine Learning, Addison-Wesley, 1989.Google Scholar
  7. 7.
    Srinivas, M. and Patnaik, L. M., Genetic Algorithms: A Survey, Computer, 1994, vol. 27, no. 6, pp. 17–26.CrossRefGoogle Scholar
  8. 8.
    Wong, K.P. and Wong, Y.W., Genetic and Genetic-Simulated-Annealing Approaches to Economic Dispatch, IEE Proc., Generat., Transmit., Distribut., 1994, vol. 141, no. 5, pp. 507–513.Google Scholar
  9. 9.
    Sareni, B. and Krahenbuhl, L., Fitness Sharing and Niching Methods Revisited, IEEE Trans. Evolut. Comp., 1998, vol. 2, no. 3, pp. 97–106.Google Scholar
  10. 10.
    Haykin, S., Neural Networks: A Comprehensive Foundation, Englewood Cliffs, NJ: Prenticehall, 1994.Google Scholar
  11. 11.
    Chen, S., Cawan, C.F.N., and Grant, P.M., Orthogonal Least Squares Learning Algorithm for Radial Basis Function Networks, IEEE Trans. Neural Networks, 1991, vol. 2, no. 2, pp. 302–309.CrossRefGoogle Scholar

Copyright information

© MAIK “Nauka/Interperiodica” 2005

Authors and Affiliations

  • W. Han
    • 1
  • P. Que
    • 1
  1. 1.Department of Information Measurement Technology and InstrumentsShanghai Jiaotong UniversityShanghaiChina

Personalised recommendations