Abstract
A neural network system has been developed which can reconstruct images of defects within fibre reinforced polymer composite samples. This paper discusses the problems associated with the image reconstruction of the ultrasonic data using neural networks, together with various methods adopted to improve the performance of the neural network system, including a modification to the error backpropagation algorithm.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
KrautkrÄmer J, KrautkrÄmer H. Ultrasonic testing of Materials, 4th edition, Springer-Verlag, Berlin, 1990
Jones HW. Recent activity in ultrasonic tomography.Ultrasonics 1993; 31(5): 353–360
Halmshaw R. Non-destructive testing, Edward Arnold, London, 1987
Chapelon JY, Pradal T, Martin C, Maerfeld C, Cathignol D. New approaches for ultrasonic-attenuation imaging.Ultrasonic Imaging 1987; 9(1): 66–67
Censor Y. Finite series expansion reconstruction techniques.IEEE Proc. 1983; 71: 409–419
Gordon R, Bender R, Herman GT. Algebraic reconstruction techniques for three-dimensional electron microscopy and X-ray photography.J Theor Biol 1970; 29: 471–481
East RJR, Worthington MH, Goulty NR. Convolutional back-projection imaging of physical models with crosshole seismic data.Geophys Prosp 1988; 36: 139–148
Stark HH, Woods JW, Paul I, Hingorani R. Direct fourier reconstruction in computer tomography.IEEE Trans Acoustics, Speech, Signal Processing 1981; 29: 237–245
Devaney AJ. Geophysical diffraction tomography.IEEE Trans Geosci Rent Sens 1984; 22: 3–13
McNab A, Dunlop I. A review of artificial-intelligence applied to ultrasonic defect evaluation.Insight 1995; 37(1): 11–16
Shahani K, Udpa L, Udpa SS. Neural networks for classification of ultrasonic NDE signals.Proc 1st IEE ICANN, 1990, 407–412
Baker AR, Windsor CG. The classification of defects from ultrasonic data using neural networks: the hopfield method.NDT International 1989; 22(2): 97–105
Damarla TR, Karpur P, Bhagat PK. A self-learning neural net for ultrasonic signal analysis.Ultrasonics 1992; 30(5): 317–324
Steriti RJ, Fiddy MA. Regularized image-reconstruction using svd and a neural network method for matrix-inversion.IEEE Trans Signal Processing 1993; 41(10): 3074–3077
Srinivasan V, Han YK, Ong SH. Image-reconstruction by a Hopfield neural network.Image and Vision Computing 1993; 11(5): 278–282
Kearfott KJ, Hill SE. Simulated annealing image reconstruction method for a pinhole aperture single photon emission computed tomography (SPECT).IEEE Trans Medical Imaging 1990; 9(2): 128
Adler A, Guardo R. A neural network image reconstruction technique for electrical impedance tomography.IEEE Trans Medical Imaging 1994; 13(4): 594–600
Rumelhart DE, McClelland JL. Parallel distributed processing: explorations in the microstructure of cognition, MIT Press, Cambridge, MA, 1986
Zurada JM. Introduction to Artificial Neural Systems, West Publishing, 1992
Meyer RW. Handbook of Pultrusion Technology, Chapman & Hall, London, 1985
Eberhart RC, Dobbins RW. Neural Network PC Tools: A practical guide, Academic Press, London, 1990
Hinton GE. Connectionist learning procedures. Technical Report CMU-CS-87-115, Carnegie-Mellon University, Pittsburgh, 1987
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Pardoe, A.C., Hutchins, D.A., Mottram, J.T. et al. Neural networks applied to ultrasonic tomographic image reconstruction. Neural Comput & Applic 5, 106–123 (1997). https://doi.org/10.1007/BF01501175
Issue Date:
DOI: https://doi.org/10.1007/BF01501175