Damage identification of structures using second-order approximation of Neumann series expansion

In this paper, a novel approach proposed for structural damage detection from limited number of sensors using extreme learning machine (ELM). As the number of sensors used to measure modal data is normally limited and usually are less than the number of DOFs in the finite element model, the model reduction approach should be used to match with incomplete measured mode shapes. The second-order approximation of Neumann series expansion based model reduction approach has been used to condense mass and stiffness matrices. Frequencies and mode shapes of damaged structures and corresponding generated damage states used as input and output to train extreme learning machine, respectively. To evaluate the performance of proposed approach, three examples consists of a truss structure, irregular frame and shear frame have been studied. Results show the ability of the proposed approach in detecting and estimating different damage scenarios using limited numbers of installed sensors and noisy modal data.