In order to increase the precision of structural identification, a two stage method based on data fusion and simplex genetic algorithm is proposed. Firstly, flexibility curvature matrix and generalized residual force vector difference are considered as two kinds of information sources, and the D S evidence theory is utilized to integrate the two information sources and preliminarily detect structural damage locations. Then, simplex genetic algorithm is used to identify structural damage extents．Considering the premature convergence of basic GA, a method combined genetic algorithm with simplex algorithm is utilized as the improved strategy. It is shown that the two stage method can precisely identify structural damage locations and extent under the condition of 2% random noise. The proposed method improves the efficiency and accuracy of pipeline damage identification.