Neural crack identification in steady state elastodynamics

An inverse crack identification problem with harmonic excitation in linear elastodynamics is treated here by means of back-propagation neural network methods and boundary element techniques. The problem concerns the determination of the existence and the characteristics of a hidden crack within an elastic structure by means of measurements of the structural response on the accessible boundary for given external time-periodic loadings. The direct problem is solved by a boundary element formulation in the frequency domain which leads to a system of linear equations with frequency-dependent matrices. Thus, for a given frequency, certain similarities with linear elastostatics exist. Feed-forward multilayer neural networks trained by back-propagation are used to learn the (inverse) input-output relation of the structural system. Then, the inverse problem is solved by a simple application of the neural network recalling (production) ability.

[1]  Jaewook Rhim,et al.  A neural network approach for damage detection and identification of structures , 1995 .

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

[3]  P. D. Panagiotopoulos,et al.  The Boundary Integral Approach to Static and Dynamic Contact Problems: Equality and Inequality Methods , 1992 .

[4]  Masataka Tanaka,et al.  Identification of Defects by the Elastodynamic Boundary Element Method Using Noisy Additional Information , 1991 .

[5]  J. Domínguez.  Boundary elements in dynamics , 1993 .

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

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

[8]  Y. Ben-Haim.  Robust reliability in the mechanical sciences , 1996 .

[9]  A. Mitra,et al.  Solution of Inverse Problems by Using the Boundary Element Method , 1992 .

[10]  Masoud Sanayei,et al.  Parameter Estimation of Structures from Static Strain Measurements. I: Formulation , 1996 .

[11]  L. M. Bezerra,et al.  A boundary element formulation for the inverse elastostatics problem (iesp) of flaw detection , 1993 .

[12]  Andrew D. Dimarogonas,et al.  VIBRATION OF CRACKED SHAFTS IN BENDING , 1983 .

[13]  Genki Yagawa,et al.  Neural networks in computational mechanics , 1996 .

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

[15]  Norbert Hoffmann,et al.  Simulation Neuronaler Netze , 1991 .

[16]  Rudolf Kruse,et al.  Neuronale Netze und Fuzzy-Systeme , 1994 .

[17]  Derek B. Ingham,et al.  Boundary Integral Formulations for Inverse Analysis , 1997 .

[18]  Zvi Hashin,et al.  The Elastic Moduli of Heterogeneous Materials , 1962 .

[19]  Heinz Antes,et al.  Anwendungen der Methode der Randelemente in der Elastodynamik und der Fluiddynamik , 1988 .

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

[21]  A. B. Abda,et al.  The reciprocity gap: a general concept for flaws identification problems , 1993 .

[22]  M. H. Aliabadi,et al.  Three Dimensional Flaw Identification UsingSensitivity Analysis , 1970 .

[23]  Yakov Ben-Haim,et al.  Crack detection in beams by rankordering of eigenfrequency shifts , 1994 .

[24]  K. Hjelmstad,et al.  Parameter Estimation of Structures from Static Response. I. Computational Aspects , 1994 .

[25]  Poyu Tsou,et al.  Structural damage detection and identification using neural networks , 1993 .

[26]  Johann Gasteiger,et al.  Neural Networks for Chemists: An Introduction , 1993 .

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

[28]  M. Nakamura,et al.  Estimation of Unknown Boundary Values by Inverse Analysis with Elastodynamic Boundary Element Method , 1993 .

[29]  R. Kress,et al.  Inverse Acoustic and Electromagnetic Scattering Theory , 1992 .

[30]  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 .

[31]  J. Z. Zhu,et al.  The finite element method , 1977 .

[32]  Hans Günther Natke,et al.  Einführung in Theorie und Praxis der Zeitreihen- und Modalanalyse , 1983 .

[33]  Prabhat Hajela,et al.  APPLICATIONS OF ARTIFICIAL NEURAL NETS IN STRUCTURAL MECHANICS , 1992 .

[34]  D. Beskos,et al.  Boundary Element Methods in Elastodynamics , 1988 .

[35]  Dar Yun Chiang,et al.  Modal Parameter Identification Using Simulated Evolution , 1997 .

[36]  Zhen-Xiang Gong,et al.  Review of:“Computational Methods for Free and Moving Boundary Problems in Heat Transfer and Fluid Flow”Editor: L.C. Wrobel and C.A. Brebbia Computational Mechanics Publications Southampton Boston Elsevier Applied Science London New York , 1994 .

[37]  Pc Pandey,et al.  Performance of the generalized delta rule in structural damage detection , 1995 .

[38]  Naoshi Nishimura,et al.  A boundary integral equation method for an inverse problem related to crack detection , 1991 .

[39]  Nicholas Zabaras,et al.  Investigation of regularization parameters and error estimating in inverse elasticity problems , 1994 .

[40]  Darrell W. Pepper,et al.  Boundary element technology , 1991 .

[41]  Nobuyoshi Tosaka,et al.  Unknown defect identification in elastic field by boundary element method with filtering procedure , 1995 .

[42]  Prabhat Hajela,et al.  Recent developments in damage detection based on system identification methods , 1990 .