选取矿井涌水水源判别中常用的灰色关联分析和逐步判别分析作为基础模型,分析了两者的优缺点及单独使用中存在的问题,提出耦合判别思路,设计了GRA-SDA耦合式水源判别模型。利用某矿区实际样本数据,选取Na++K+、Ca2+、Mg2+、Cl-、SO42-、HCO3-共6组离子以及矿化度作为判别因子,对该模型进行实例验证。分析表明,该模型判别结果与实际情况吻合较好,与单独使用一种分析方法相比较,有效地提高了水源判别正确率。 The gray relational analysis and stepwise discriminant analysis, which are commonly used in the determination of mine gushing water, are selected as the basic model. The advantages and disadvantages of the two are analyzed and the problems existing in the single use are analyzed. The coupling discrimination is proposed and the GRA-SDA coupled water source discriminant model is designed. Using the actual sample data of a certain mining area, six groups of ions such as Na ++ K +, Ca2 +, Mg2 +, Cl-, SO42- and HCO3- were selected and the salinity was taken as the discriminant factor. The model was verified by an example. The analysis shows that the discriminant result of the model is in good agreement with the actual situation, and effectively improves the accuracy of water source discrimination compared with using only one analytical method.