Quantitative nondestructive evaluation with ultrasonic method using neural networks and computational mechanics

This paper describes an inverse analysis method using hierarchical neural networks and computational mechanics, and its application to the quantitative nondestructive evaluation with the ultrasonic method. The present method consists of three subprocesses. First, by parametrically changing the location and size of a defect hidden in solid, elastic wave propagation in the solid is calculated with the dynamic finite element method. Second, the back-propagation neural network is trained using the calculated relationships between the defect parameters and the dynamic responses of solid surface. Finally, the trained network is utilized to determine appropriate defect parameters from some measured dynamic responses of solid surface. The accuracy and efficiency of the present method are discussed in detail through the identification of size and location of a defect hidden in solid.

[1]  T. Raju Damarla,et al.  A self-learning neural net for ultrasonic signal analysis , 1992 .

[2]  G. A. Georgiou,et al.  Quantitative studies in ultrasonic wave-defect interaction , 1987 .

[3]  L. W. Schmerr,et al.  Ultrasonic flaw classification in weldments using neural networks : Review of Progress in Quantitative Nondestructive Evaluation, La Jolla, California (United States), 15–20 Jul. 1990. Vol. 10A, pp. 697–704. Edited by D.O. Thompson, and D.E. Chimenti. Plenum Press (1991). ISBN 0-306-43903-4 , 1992 .

[4]  D Zipser,et al.  Learning the hidden structure of speech. , 1988, The Journal of the Acoustical Society of America.

[5]  Andrzej Cichocki,et al.  Neural networks for optimization and signal processing , 1993 .

[6]  Jon Juel Thomsen,et al.  Quality control of composite materials by neural network analysis of ultrasonic power spectra , 1991 .

[7]  Ken-ichi Funahashi,et al.  On the approximate realization of continuous mappings by neural networks , 1989, Neural Networks.

[8]  Hiroaki Kitano,et al.  Designing Neural Networks Using Genetic Algorithms with Graph Generation System , 1990, Complex Syst..

[9]  Genki Yagawa,et al.  Identification of Crack Shape Hidden in Solid by Means of Neural Network and Computational Mechanics , 1993 .

[10]  P. Peretto.  An introduction to the modeling of neural networks , 1992 .

[11]  R. J. Blake,et al.  Rayleigh wave scattering from surface features: wedges and down-steps , 1990 .

[12]  W. Lord,et al.  A finite-element study of ultrasonic wave propagation and scattering in an aluminum block , 1988 .

[13]  K. Harumi,et al.  Computer simulation of ultrasonics in a solid , 1986 .

[14]  C. G. Windsor,et al.  The classification of defects from ultrasonic data using neural networks: The Hopfield method , 1989 .

[15]  Jocelyn Sietsma,et al.  Creating artificial neural networks that generalize , 1991, Neural Networks.

[16]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[17]  L. Bond,et al.  Interaction of Rayleigh waves with a rib attached to a plate , 1991 .

[18]  Genki Yagawa,et al.  Inverse Analyses by Means of Hierarchical Neural Network and Computational Mechanics with Application to 3D Crack Identification. , 1993 .

[19]  Yoshio Hirose,et al.  Backpropagation algorithm which varies the number of hidden units , 1989, International 1989 Joint Conference on Neural Networks.

[20]  恭二 本間,et al.  ニューラルネットワークを利用したAE原波形解析 (第一報) : 2層のネットワークによる擬似AE波の計算 , 1991 .

[21]  James H. Garrett,et al.  Use of neural networks in detection of structural damage , 1992 .

[22]  Lester W. Schmerr,et al.  Neural network inversion of uniform-field eddy current data , 1991 .

[23]  R. B. Thompson.  Quantitative Ultrasonic Nondestructive Evaluation Methods , 1983 .

[24]  Lalita Udpa,et al.  Eddy current defect characterization using neural networks , 1990 .

[25]  Igor Grabec,et al.  Application of an intelligent signal processing system to acoustic emission analysis , 1989 .

[26]  Genki Yagawa,et al.  Finite element simulation of ultrasonic wave propagation in pipe and pressure vessel walls , 1990 .

[27]  Shiro Kubo,et al.  Classification of Inverse Problems Arising in Field Problems and Their Treatments , 1993 .

[28]  W. Lord,et al.  A Finite Element Formulation for Ultrasonic NDT Modeling , 1985 .

[29]  Hesham El-Rewini,et al.  Introduction to Parallel Computing , 1992 .

[30]  Masahiko Hirao,et al.  Scattering of Rayleigh surface waves by edge cracks: Numerical simulation and experiment , 1982 .

[31]  Genki Yagawa,et al.  A parallel finite element method with a supercomputer network , 1993 .