Application of distance discriminant analysis method to headstream recognition of water-bursting source

Abstract

Based on the principle of Mahalanobis distance discriminant analysis (DDA), a distance discriminant analysis model of headstream recognition is established, including six indexes reflecting the mine water-bursting; Na + + K + , Cl -1 , Ca 2+ , Mg 2+ , HCO - 3 , SSO 4 2- Linear discriminant functions are obtained through training the initial data for headstream recognition of mine water-bursting of 35 groups in Jiaozuo mining area. After the DDA model is trained, the ration of mistake distinguish is considerably low zero. In order to verify the effectiveness and feasibility of the model, the cases of other aquifer of groundwater in Jiaozuo mining area are analyzed using the proposed method, and the obtained results are also compared with the results of quantification theory model, support vector machines model and practical conditions. The results show that the results predicted by DDA model are both in good agreement with the practical conditions and the results obtained from quantification theory model and support vector machines model. The method offers a new way in headstream recognition of mine water-bursting.