Neural Network-Based Inverse Analysis for Defect Identification with Laser Ultrasonics

Abstract. This paper describes an application of the neural network-based inverse analysis method to the identification of a surface defect hidden in a solid, using laser ultrasonics. The inverse analysis method consists of three subprocesses. First, sample data of identification parameters versus dynamic responses of displacements at several monitoring points on the surface are calculated using the dynamic finite-element method. Second, the back-propagation neural network is trained using the sample data. Finally, the well-trained network is utilized for defect identification. Fundamental performance of the method is examined quantitatively and in detail, through both numerical simulations and laser ultrasonics experiments. Locations and depths of vertical defects are successfully estimated within 12.5% and 4.1% errors relative to the specimen thickness, respectively.

[1]  Satish S. Udpa,et al.  Time Delay Neural Networks for Classification of Ultrasonic NDT Signals , 1992 .

[2]  J. Achenbach,et al.  An Artificial Intelligence Technique to Characterize Surface-Breaking Cracks , 1995 .

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

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

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

[6]  Georgios E. Stavroulakis,et al.  Neural crack identification in steady state elastodynamics , 1998 .

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

[8]  Kyoji Homma,et al.  Acoustic Emission Source Location and Its Error Using a Neural Network Technique. , 1999 .

[9]  D. J. Roth,et al.  The use of the neural networks in the recognition of the austenitic steel types , 2000 .

[10]  C. M. Scala,et al.  Time‐ and frequency‐domain characteristics of laser‐generated ultrasonic surface waves , 1989 .

[11]  Genki Yagawa,et al.  A Parallel Finite-Element Analysis of Dynamic Problems Using an EWS Network , 1996 .

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

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

[14]  H. Yamawaki,et al.  Computer Simulation Of Laser-Generated Elastic Waves In Solid , 1992 .

[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]  M.H. Hassoun,et al.  Fundamentals of Artificial Neural Networks , 1996, Proceedings of the IEEE.

[18]  Inspection of Components Having Complex Geometries Using Laser-Based Ultrasound , 1992 .

[19]  J. Monchalin.  Optical Detection of Ultrasound , 1986, IEEE Transactions on Ultrasonics, Ferroelectrics and Frequency Control.

[20]  Genki Yagawa,et al.  An Application of Domain Decomposition Method to Dynamic FEM. , 1992 .

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

[24]  Jan Drewes Achenbach,et al.  Crack Sizing Using a Neural Network Classifier Trained with Data Obtained from Finite Element Models , 1995 .

[25]  Genki Yagawa,et al.  NEW REGULARIZATION BY TRANSFORMATION FOR NEURAL NETWORK BASED INVERSE ANALYSES AND ITS APPLICATION TO STRUCTURE IDENTIFICATION , 1996 .

[26]  G. Stavroulakis,et al.  Nondestructive elastostatic identification of unilateral cracks through BEM and neural networks , 1997 .

[27]  Genki Yagawa,et al.  Quantitative nondestructive evaluation with ultrasonic method using neural networks and computational mechanics , 1995 .

[28]  L. Drain,et al.  Laser Ultrasonics Techniques and Applications , 1990 .

[29]  Denis G. F. David,et al.  An Evaluation of Artificial Neural Networks Applied to Infrared Thermography Inspection of Composite Aerospace Structures , 1995 .

[30]  David A. Hutchins,et al.  Quantitative measurements of laser‐generated acoustic waveforms , 1982 .

[31]  Hidetoshi Nakano,et al.  Crack Measurements by Laser Ultrasonic at High Temperatures , 1993 .