In this study, a promising pattern recognition based approach is introduced for structural damage identification using the measured dynamic data. The frequency response function (FRF) is preferably employed as the input of the proposed algorithm since it contains the most information of structural dynamic characteristics. The 2D principal component analysis (2D-PCA) is used to reduce the large size of FRFs data. The output data generated by the 2D-PCA are used to extract the damage indexes for each of the damage scenarios. A dataset of all probable damage indexes is provided; of which 30% are selected to form the train dataset and to be compared with the unknown damage index for an unidentified state of the structure. The sum of absolute errors (SAE) are calculated between the unknown damage index and the selected indexes from the dataset; of which the minimum refers to the most similar damage condition to the unknown one. The artificial neural networks (ANNs) are used to form a smooth function of the SAEs and the imperialist competitive algorithm (ICA) is utilized to minimize this function in order to find the location and severity of the damages of the unknown state of the structure. To validate the proposed method, the damage identification of a truss bridge structure and a two-story frame structure is conducted by considering all the single damage cases as well as multi damage scenarios. In addition, the robustness of the proposed method to measurement noise up to 20% is thoroughly investigated.

No abstract

A pattern recognition-based damage detection method using a brand-new damage index (DI) obtained from the frequency response function (FRF) data is proposed in this paper. One major issue of using the FRF data is the large size of input variables. The proposed method reduces the dimension of the initial FRF data and transforms it into new damage indices by applying a data reduction technique called the two-dimensional principal component analysis (2D-PCA). The proposed damage indices can be used as the unique patterns. After introducing the damage indices, a dataset of damage scenarios and related patterns is composed. Pattern recognition techniques such as the artificial neural networks and look-up-table (LUT) method are employed to find the most similar known DI to the unknown DI obtained for the damaged structure. As the result of this procedure, the actual damage location and severity can be determined. In this paper, the 2D-PCA and LUT method for damage detection is introduced for the first time. The damage identification of a truss bridge and a two-story frame structure is performed for verification of the proposed method, considering all single damage cases as well as many multiple damage scenarios. In addition, the robustness of the proposed algorithm to measurement noise was investigated by polluting the FRF data with 5%, 10%, 15% and 20% noises.