Identification of mine water sources using a multi-dimensional ion-causative nonlinear algorithmic model

Abstract

Based on the nonlinear algorithmic theory, the R-SVM water source discrimination model and prediction method were established by using the piper qualitatively to compare the differences between the ionic components and R-type factor approximation indicator input dimensions. Taking the mine water samples of Zhaogezhuang Coal Mine as an example, according to the chemical composition analysis of the water samples from different monitoring points, six indexes of Na+, Ca2+, Mg2+, Cl–, SO42– and HCO3– were selected as the discrimination factors. According to the water characteristics of each aquifer and the actual needs of discrimination, the water inrush sources in the mining area were divided into four categories: The goaf water is class I, Ordovician carbonate is class II, Sandstone fracture water from the 13 coal system is class III, and Sandstone fracture water from the 12 coal system is class IV. Taking 56 typical water inrush samples as training samples, 11 groups for prediction samples, establish the input index as typical ion content, output as water source type, using SPSS statistics and MATLAB to realize the R-SVM water source discriminant analysis model, automatically establishing the mapping relationship between the water quality indexes and the evaluation standards, which can achieve the purpose of rapid and accurate discrimination of the water sample data. The results showed that the accuracy of the R-SVM model classification was 90.90% in the verification of the water source discrimination example of Zhaogezhuang mine and the coupled model has high accuracy, good applicability and discriminant ability, and has certain guiding significance for the prevention and control of water damage and the related field work.