Abstract：In order to accurately predict the coal-gas outburst, variable sets theory is used to build a two-stage variable preferred assessment model of coal-gas outburst.In the model, the critical values is used that affect the coal-gas outburst to form a boundary membership, and a reasonable model parameter is selected to ensure the evaluation of the vector results.The model adopts the combination weighting method based on Pareto principle, integrating entropy weight method and data envelopment analysis (DEA) method, it not only retains the objectivity, but also takes into the distinguish ability of research subjects.Then, according to the evaluation results of sample data, a quantitative grade is given for the outburst degree.To validate the reliability of the model and the quantitative grade, the actual data is selected to predict.The results show that the model can be applied to predict coal-gas outburst.

Keyword：coal-gas outburst;variable sets;entropy weight method;data envelopment analysis (DEA) ;