Abstract
A probabilistic neural network is used here to classify flaws in weldments from their ultrasonic scattering signatures. It is shown that such a network is both simple to construct and fast to train. Probabilistic nets are also shown to be able to exhibit the high performance of other neural networks, such as feed forward nets trained via back-propagation, while possessing important advantages of speed, explicitness of their architecture, and physical meaning of their outputs. Probabilistic nets are also demonstrated to have performance equal to common statistical approaches, such as theK-nearest neighbor method, while retaining their unique advantages.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Handbook on the Ultrasonic Examination of Welds (The Welding Institute, Abington Hall, Cambridge, England, 1977).
The Evaluation of Ultrasonic Signals (The International Institute of Welding, Cambridge, England, 1987).
S. F. Burch, Objective characterization of welding defects using physical based pattern recognition techniques. inReview of Progress in Quantitative Nondestructive Evaluation, Vol. 7B, D. O. Thompson and D. E. Chimenti, eds. Plenum Press, New York, 1988, pp. 1495–1502.
J. L. Rose, Elements of a feature-based ultrasonic inspection system.Mater. Eval. 42(2):210–218 (1984).
J. L. Rose, Y. H. Jeong, and C. T. Cooper, A methodology for reflector classification analysis in complex geometric welded structures,Mater. Eval. 42(1):98–106 (1984).
J. L. Rose, J. Nestleroth, L. Niklas, O. Ganglbauer, J. Ausserwoeger, and F. Wallner, Flaw classification in welded plates employing a multidimensional feature-based decision process.Mater. Eval. 42(4):433–438, 443 (1984).
M. F. Whalen and A. N. Mucciardi. Inversion of physically recorded ultrasonic waveforms using adaptive learning network models trained on theoretical data. inProc. ARPA/AFML Review of Progress in Quantitative NDE, D.O. Thompson, ed. (Air Force Materials Laboratory Technical Report AFML-TR-78-205, 1979), pp. 341–367.
S. M. Nugen, L. W. Schmerr, K. M. Christensen, and B. K. Lovewell, Design and implementation of an expert system for flaw classification,Microcomp. Appl. 9:1–8 (1990).
L. W. Schmerr, K. E. Christensen, S. M. Nugen, L.-S. Koo, and C.-P. Chiou, Ultrasonic flaw classification — An expert system approach. inReview of Progress in Quantitative Nondestructive Evaluation, Vol. 8A, D. O. Thompson and D. E. Chimenti, eds. (Plenum Press, New York, 1989), pp. 657–664.
S. J. Song and L. W. Schmerr, Ultrasonic flaw classification in weldments using neural networks, inReview of Progress in Quantitative Nondestructive Evaluation, Vol. 10A, D. O. Thompson and D. E. Chimenti, eds. (Plenum Press, New York, 1990), pp. 697–704.
L. M. Brown and R. DeNale, Classification of ultrasonic defect signatures using an artificial neural network, inReview of Progress in Quantitative Nondestructive Evaluation, Vol. 10A, D. O. Thompson and D. E. Chimenti, eds. (Plenum Press, New York, 1990), pp. 705–712.
D. Berry, L. Udpa, and S. S. Udpa, Classifications of ultrasonic signals via neural networks, inReview of Progress in Quantitative Nondestructive Evaluation, Vol. 10A, D. O. Thompson and D. E. Chimenti, eds. (Plenum Press, New York, 1990), pp. 697–704.
R. P. Lippmann, An introduction to computing with neural nets,IEEE ASSP Mag. 4–22 (April 1987).
Y. H. Pao,Adaptive Pattern Recognition and Neural Networks. (Addison-Wesley Publishing Co., Reading, MA, 1989).
D. E. Rumelhart, G. E. Hinton, and R. J. Williams, Learning internal representations by error propagation. inParallel Distributed Processing, Vol. 1, D. E. Rumelhart, J. L. McClelland, and the PDP Research Group, eds. (MIT Press, Cambridge, MA, 1986), pp. 318–362.
D. F. Specht, Probabilistic neural networks for classification, mapping, or associative memory,Proc. IEEE Int. Conf. Neur. Net. 1:525–532 (1988).
D. F. Specht, Probabilistic neural networks,Neur. Net. 3:109–118 (1990).
D. F. Specht, Probabilistic neural networks and polynomial adaline as complementary techniques for classification.IEEE Trans. Neur. Net 1:111–121 (1990).
D. F. Specht and P. D. Shapiro, Generalization accuracy of probabilistic neural networks compared with back-propagation networks,Proc. Int. Joint Conf. Neur. Net. 1:887–892 (1991).
T. P. Washburne, M. M. Okamura, D. F. Specht, and W. A. Fisher, The Lockheed probabilistic neural network processor,Proc. Int. Joint Conf. Neur. Net. 1:513–518 (1991).
R. O. Duda and P. E. Hart,Pattern Classification and Scene Analysis (Wiley-Interscience Publication Co., 1973).
D. F. Specht, Enhancements to probabilistic neural networks,Proc. Int. Joint Conf. Neur. Net. 1:761–768 (1992).
K. Fukunaga,Statistical Pattern Recognition, 2nd. Ed. (Academic Press, New York, 1990).
R. Schalkoff,Pattern Recognition (John Wiley and Sons, New York, 1992).
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Song, S.J., Schmerr, L.W. Ultrasonic flaw classification in weldments using probabilistic neural networks. J Nondestruct Eval 11, 69–77 (1992). https://doi.org/10.1007/BF00568290
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF00568290