Abstract

Aimed at the influences of various complicated factors for water inrush from a coal seam floor during coal seam mining, the prediction of the maximal water bursting discharge from a coal seam floor is regarded as a problem of pattern identification with nonlinear, high dimensions, and finite samples. Based on information fusion theory and regarding the prediction of maximal water bursting discharge from a coal seam floor as a process of multisource information fusion and state estimation, an evaluation system of the main controlling factors for predicting the maximal water bursting discharge from a coal seam floor was established. An evaluation model for forecasting the maximal water bursting discharge from a coal seam floor was also structured according to multiple nonlinear regression theory. Considering the major coal mines of Xinwen coalfield as the research background, six factors are selected as the basic discriminant factors, i.e., aquifer thickness, unit water inflow, water pressure, aquiclude thickness, fault influencing factor, and depth of a coal seam floor destroyed by rock pressure. Deng’s grey relational theory was used to analyze the correlation degrees between each main controlling factor and the maximal water bursting discharge from a coal seam floor. A structural equation model was adopted to reveal the internal connecting links among the key influencing factors and determine the weights of each main controlling factor for predicting the maximal water bursting discharge from a coal seam floor. An SPSS scatter plot and MATLAB functional programming were applied to fit the correlativity curves between each main controlling factor and the maximal water bursting discharge from a coal seam floor in the Xinwen Mining Area. The optimal unitary nonlinear regression models between the maximal water bursting discharge from the coal seam floor and each main control factor were established. A multiple nonlinear regression–modified model for predicting the maximal water bursting discharge from the coal seam floor was acquired using a multiple nonlinear regression analysis with the combined weights of each main control factor. Compared with the bivariant multiple regression equation and the measured data, the results showed that the average values of forecasting errors predicted by the multiple nonlinear regression–modified model and bivariant multiple regression equation are 10.53% and 16.76%, respectively, which indicates that the multiple nonlinear regression–modified model and the bivariant multiple regression equation have higher prediction accuracy and relatively smaller error ranges, with comparatively better application value in the prediction of maximal water bursting discharge from a coal seam floor.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call