Damage identification in steel frames using dual-criteria vibration-based damage detection method and artificial neural network

Vibration-based damage identification methods have proven to be effective in identifying damage in various structures by employing modal parameters. This paper presents and develops a two-stage multi-criteria damage detection method based on modified damage indices (DIs), specifically modal flexibility and modal strain energy -based damage indices, and artificial neural network (ANN) to locate and quantify damage in steel frames. Only information from the first three bending modes was used to calculate the DIs. The location of damages is detected using DIs in the first stage, and two separate artificial neural networks are trained based on the DIs as input parameters in the second stage. The feasibility and performance of the proposed method were assessed by applying different single and multiple damage scenarios to a 3D finite element model of a simply supported steel beam and a steel frame of an industrial shed. The results demonstrate the efficiency and competency of the proposed non-destructive method for damage detection in such steel frames.