Discrimination Methods of Water Inrush from Mine Floor Based on PCA-Fisher
A method based on principal component analysis (PCA) and Fisher discrimination analysis is proposed targeting water inrush from mine floor. Based on the analysis of a large number of measured data from past projects, 13 factors affecting and controlling water inrush from floor are selected as the discrimination indexes. Firstly, the dimension of multi-index floor water inrush data is reduced by principal component analysis, and 4 principal component factors are extracted. Then the PCA-Fisher discrimination model of mine floor water inrush risk is established based on Fisher discrimination analysis theory, and its discrimination effect is verified by recurrent discrimination analysis and an example of its application is presented. The application results show that the results of the discrimination model are consistent with the actual situation, with an accuracy of 100%, which can provide a more effective method for discriminating the water inrush risk from mine floor.