Multiple crack identification in Euler beams using extreme learning machine

In this paper, a novel method proposed for multiple crack identification in Euler beams using extreme learning machine (ELM). For this purpose, the extreme learning machine used the modal strain energy and natural frequencies of cracked beam as input and crack states in beam elements as output. To illustrate the performance of the presented method in crack detection, Euler beam with different support conditions consist of cantilever, simply supported and fixed simply supported with single or several cracks in beam elements has been investigated. In other work, a validation study has been done using a simply supported beam. Also, noise effect on the measured modal data has been investigated. The obtained results show the capability of the proposed method for crack detection using ELM.