Abstract: Based on attribute mathematical theory, this paper establishes an attribute recognition model to predict the possibility and classification of rockburst. Firstly, the main factors of rockburst, such as the maximum tangential stress of the cavern wall , uniaxial compressive strength , uniaxial tensile strength , and the elastic energy index of rock , are taken into account in the analysis. Three factors, , and are defined as the criterion indices for rockburst prediction in the proposed model. Secondly, attribute measurement functions are constructed. Thirdly, the calculation methods are proposed to calculate the attribute measurement of single index and the synthetic attribute measurement of samples. A series of underground rock projects are assessed with the proposed model. It indicates that the synthetic assessment results agree well with the actual records, and are consistent with those of the fuzzy synthetic evaluation model and the matter-elements model. Therefore, the feasibility of the proposed model is validated. Moreover, the proposed model is used to predict rockbursts of a hydropower station and Qinling Tunnel, the results are consistent with those of the synthetic evaluation method such as artificial neural network and distance discriminant analysis method.