LAUSR

ABSTRACT In this paper, a novel approach has been proposed to detect crack in beam structures under moving mass using extreme learning machine and the least square support vector machine. For this purpose, acceleration responses of beam under moving mass were used as input to train machines. This data are acquired by the analysis of cracked structure applying the finite element method. To demonstrate the potential of the proposed vibration analysis over existing ones, a validation study has been done. To evaluate the performance of the presented method, a simply supported beam and a three-span continuous beam with and without noise in acceleration responses were considered. Also, the effect of the discrepancy in stiffness between the finite element model and the actual tested dynamic system has been investigated. The obtained results indicated that this method can provide a reliable tool to accurately identify cracks in beam structures under moving mass.