Abstract:A GA optimized least square estimation algorithm using an adaptive tracking technique was presented for structural damage identification. In the proposed approach, a genetic optimizing algorithm was adopted to optimize a variable adaptive factor matrix in which each adaptive factor is associated with the variation of a particular parameter, and the adaptive factor matrix can be determined based on current measured data.For illystrating advantages the presented method was applied to on-line identification of the changes of system parameters for linear and nonlinear hysteretic structures. Simulation results demonstrate that the proposed method is capable of tracking the time-varying system parameters and detecting the structural damages, including the damage location and severity. Besides, experimental study was presented to verify the capability of the proposed method by taking a small-scale 3-story building model as an example. Experimental results demonstrate that the proposed approach is capable of tracking the variation of structural parameters, leading to the detection of structural damages.