Fisher discriminant analysis model and its application for prediction of classification of rockburst in deep-buried long tunnel

Abstract

A Fisher discriminant analysis (FDA) model for the prediction of classification of rockburst in deep-buried long tunnel was established based on the Fisher discriminant theory and the actual characteristics of the project. First, the major factors of rockburst, such as the maximum tangential stress of the cavern wall σ _θ, uniaxial compressive strength σ _c, uniaxial tensile strength σ _t, and the elastic energy index of rock W _et, were taken into account in the analysis. Three factors, Stress coefficient σ _θ/σ _c, rock brittleness coefficient σ _c/σ _t, and elastic energy index W _et, were defined as the criterion indices for rockburst prediction in the proposed model. After training and testing of 12 sets of measured data, the discriminant functions of FDA were solved, and the ratio of misdiscrimination is zero. Moreover, the proposed model was used to predict rockbursts of Qinling tunnel along Xi’an-Ankang railway. The results show that three forecast results are identical with the actual situation. Therefore, the prediction accuracy of the FDA model is acceptable.