Abstract: Based on the statistical theory theory, combining with the practice of project, a Fisher discriminant analysis model was established for classifying bolt support effects of mining gateway. Seven major bolt support effects factors such as strength of surrounding rock，roadway section，coefficient of mining influence，buried depth of roadway，integrities of rock，width of coal pillar，support intensity were regarded as the discriminant factors of the FDA model. A series of related data of bolt support effects in 18 deep roadways under dynamic pressure strips of Pingdingshan mining area were taken as the learning samples. The discriminant functions were also established. Four samples of bolt support effects of mining gateway were used to verify this model and the prediction results fully corresponded to actual situation．