Abstract：Rockburst is one of the main engineering geological hazards at deep high geostress zone and is influenced by many factors. The prediction of possibility and classification of rockburst are important issues in many underground engineering. Based on the principle of Mahalanobis¢ distance discriminant analysis(DDA)，a distance discriminant analysis model to predict the possibility and classification of rockburst is established. The main control factors of rockburst，such as values of in-situ stresses sq，uniaxial compressive strength sc and uniaxial tensile strength st of rock，elastic energy index of rock Wet，are chosen in the analysis. Three discrimination factors including sq /sc，sc/st and Wet are regarded as the discriminant factors of the DDA model. A series of underground rock projects in domestic and abroad are taken as the training and testing samples；and the ratio of mistake-distinguish is considerably low zero after the DDA model is trained. Rockbursts of Qinling Tunnel along Xi¢an—Ankang Railway and Dongguashan deep-buried hard rock mine are used to verify this model. The results show that the DDA model can be used to predict the possibility and classification of rockburst in deep underground engineering；and the prediction accuracy is acceptable.
