A New Method for Damage Detection in Symmetric Beams Using Artificial Neural Network and Finite Element Method

Authors : F NAZARİ, S BAGHALİAN

Pages : 30-36

View : 19 | Download : 5

Publication Date : 2011-06-01

Article Type : Research Paper

Abstract :In this paper a new method for crack detection in symmetric beams is presented. Natural frequency is frequently used as a parameter to detect cracks in structures. In symmetric structures, it isn’t possible to identify the location and the depth of a crack using only the natural frequencies. This is due to the fact that the natural frequencies for any symmetric position of a crack with respect to symmetry plane of the structure are the same. In this research it is assumed that the structure is a rectangular beam which is fixed at both ends. Finite Element Method insert ignore into journalissuearticles values(FEM); was used to obtain natural frequencies of beam in different conditions of cracks. Then assumed the crack is located at the right side of the structure. Based on data were obtained from FEM, two distinct Artificial Neural Networks insert ignore into journalissuearticles values(ANNs); were trained for crack location and depth detection in some different conditions and then were tested. As it was assumed that the crack is at the right side of the beam, two symmetric positions could exist for a crack. Finally using an algorithm based on first vibrational mode shape of structure, locations and depths of cracks have been identified with good approximations
Keywords : Crack Detection, Symmetric Beam, Mode Shape, Natural Frequency, Artificial Neural Network