Abstract: Based on the coupled free vibration records of bridge deck sectional model testing, a flutter derivatives identification method based on the artificial bee colony (ABC) algorithm is proposed. The objective function is constructed as the ensemble residual quadratic sum of the vertical and torsional vibration time histories in the sense of least squares. The ABC algorithm is used to search the optimal parameters so that the value of the objective function is minimized. Compared with other iteration methods, the ABC algorithm can facilitate the identification process with no need for initial values. In order to investigate the effectiveness of the ABC algorithm in the flutter derivatives identification, an ideal thin-plate model simulation and a real bridge sectional model testing are carried out. The results show that the ABC algorithm for the flutter derivatives identification of bridge decks is robust and reliable.