Crack identification in beams

In present paper a new procedure for crack identification in circular cross section beams is presented. One of the most popular parameters that are used to detect cracks in structures is natural frequency. The process of crack identification in the suggested procedure consists of four steps. In first step, a circular cross section beam with two disks was modeled using finite element method. For applying FEM, ANSYS commercial Software was used. Then natural frequencies of the structure for different locations and depths of cracks were obtained by modal analysis. The modal analysis results were verified by data of one of available references. It was concluded that the FEM analysis has been done accurately. In second step, two multi-layer neural networks were created. In third step, genetic algorithm was used to train the neural network. For applying genetic algorithm MATLAB commercial software was used. Inputs of neural networks were natural frequencies and outputs were locations and depths of cracks. The all of data were applied to neural networks in normalized form. In forth step, natural frequencies of circular cross section beam with distinct crack conditions as inputs applied to trained neural networks and corresponding locations and depths of cracks were calculated. The trained neural networks predicted crack location better than crack depth. Obtained results showed that cracks characteristics were computed with good approximations. It was concluded that the presented method can be used for identification of crack in circular cross section beams.