A rapid structural damage detection method using integrated ANFIS and interval modeling technique

A new kind of rapid structural damage detection method is proposed based on structural dynamic vibration data, which can be used to fast assess structural fault for short-term monitoring. In this paper, to identify structural damage rapidly after its occurrence, we have employed adaptive neuro-fuzzy inference system (ANFIS) for nonparametric system identification and response prediction, which exploits the best approximation property of ANFIS. Interval modeling technique is then used to extract the feature data by processing ANFIS output data. ANFIS is found to provide a high degree of accuracy for the prediction of the structural response, and interval modeling technique to effectively extract damage characteristics. ANFIS and interval modeling technique, relatively new topics when applied to structure, can be integrated to facilitate rapid structural fault detection. The benchmark structure of IASC-ASCE Task Group is modeled in finite element method (FEM), and then utilized for demonstration of the proposed method, within which the structural damage is modeled as element removal. The simulation results indicate that the effect of the integrated method of ANFIS and interval modeling technique presented in rapid damage detection for short-term monitoring is quite plausible. (C) 2014 The Authors. Published by Elsevier B.V.