Abstract: Based on the idea of the Bayes discriminant analysis method, the Bayes discriminant analysis model of the difficulty degree on coal seam water injection was established. Six indicators such as buried depth, cranny viability, porosity, wet rim angle, saturation moisture increment and firm coefficient of coal were used as discriminant factors in the model. The difficulty of the coal seam water injection is divided into three grades that were regarded as three normal population of the Bayes discriminant analysis. The Bayes discriminant model was set up through training of fifteen sets of in-situ data, each of the fifteen sets of samples was tested by using back substitution method according to the Bayes discriminant analysis, and then the model was used in practical engineering. The results show that misjudgment rate of the Bayes discriminant analysis model is low and the model can be better applied to practical engineering.