A TWO STAGE METHOD FOR STRUCTURAL DAMAGE IDENTIFICATION USING AN ADAPTIVE NEURO-FUZZY INFERENCE SYSTEM AND PARTICLE SWARM OPTIMIZATION

An efficient methodology is proposed to detect the multiple damages in structural systems. The methodology consists of two main stages. In the first stage, an exhaustive search is performed using the adaptive neuro-fuzzy inference system (ANFIS) to quickly identify the most potentially damaged elements (MPDE). In the second stage, a particle swarm optimization (PSO) is presented to accurately determine the actual damage extents using the first stage results. In order to assess the performance of the proposed methodology for structural damage detection, two illustrative test examples are considered. The numerical results demonstrate the computational efficiency of the proposed methodology when comparing with those of the methods found in the literature.