Neural crack identification in steady state elastodynamicsNeural crack identification in steady state elastodynamics Peer-Reviewed Journal Publication Δημοσίευση σε Περιοδικό με Κριτές 2015-10-111998enAn 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. http://creativecommons.org/licenses/by/4.0/Computer methods in applied mechanics and engineering 1-4165 129–146 Stavroulakis Georgios Σταυρουλακης Γεωργιος Antes, Horst, 1936- Elsevier Engineering