A Two Stage Method to Identification Cracks in Beam Structures

Subject Areas : Analysis of Structure and Earthquake

siyamak ghadimi ¹ , seyyed sina kourehli ²

1 -
2 -

Received: 2017-12-11 Accepted : 2018-01-06 Published : 2018-01-08

Keywords: Optimization, Crack Detection, Two stage method, Extreme learning machine,

Abstract :

In this paper, a two stage crack detection method has been proposed. In the first stage, extreme learning machine used to identify crack using three fist modes frequencies and mode shapes as input data to train machine. In the second stage, the obtained results in the first stage, used as initial population in optimization procedure to detect crack locations and severities accurately. To demonstrate the potential of the proposed analysis over existing ones, a validation study has been done. To evaluate the performance of the presented method, a simply supported beam and a cantilever beam. The obtained results indicated that this method can provide a reliable tool to accurately identify cracks in beam structures