Damage Identification of Cracked Plates Using Neural Networks

Damage identification is a branch of structural health monitoring methodologies. In this paper a method for damage identification in plates employing neural networks is presented. In order to evaluate the proposed method, a plate is modeled by a finite element program and then changes in the responses are analyzed using MATLAB neural networks toolbox. Also Radial Basis Function networks and back propagation networks have been studied in terms of speed and accuracy. Numerical results demonstrate the efficiency of the proposed method for correct damage identification in plates

Keywords:

damage detection , mode shape , cracked plate , neural networks