Three-Dimensional Visualization Of Coal Seam Structure And Coal Quality Prediction Research In Fully Mechanized Working Face

Coal is the main energy source for our country’s development.With the application of computer technologies and artificial intelligence algorithms in various fields,intelligent coal mining with the combination of computer remote monitoring and manual intervention has become the core of enterprise coal mining.Due to the sampling data obtained before mining the working face is limited,the interpolation method usually be used to predict the coal seam structure inside the working face.In addition,in the mining process,it is necessary to predict the coal quality index of the total amount of coal mined in the next stage and guide the next washing and coal blending scheme according to the predicted coal quality index.However,in the mining process,the coal yield prediction is inaccurate due to the large amount of calculation and the error of manual operation,which affects the prediction result of coal quality index of the working face.To solve the above problems,based on theoretical foundation of kriging interpolation algorithm and differential evolution(DE)algorithm,the paper studies the building process of 3d model of working face and realizes real-time prediction of coal quality indicators of working face.The main research contents are as follows:(1)In order to solve the problem of parameter determination in engineering applications,this paper studies the meta-heuristic algorithms.The differential evolution algorithm is widely used due to its advantages of less parameters and easy understanding.Aiming at the DE algorithm easily falling into the local optimal solution resulting in the algorithm stagnation,an improved guided differential evolution algorithm(IAGDE)is proposed.The IAGDE algorithm adopts a new mutation strategy,a parameters adaptive tunning scheme and a population reduction strategy to optimize the differential evolution algorithm,and experiments are carried out on the CEC2013 data set.The experimental results show that compared with other optimization algorithms such as SHADE,the IAGDE algorithm has higher solution accuracy,faster convergence speed and better stability.(2)Due to the limited and sparse geological data obtained in the working face before mining,an interpolation algorithm is used to interpolate the elevation of the coal seam structure inside the working face.This paper analyzes the advantages and disadvantages of several interpolation algorithms,and selects the Kriging interpolation method,which is widely used in geostatistics,as the theoretical basis.Aiming at the over-fitting or under-fitting caused by the problem of parameter determination during the fitting process of the variogram model by kriging interpolation,employing the IAGDE algorithm to solve the parameters in the Kriging variogram fitting model and proposing the IAGDE-Kriging interpolation method to interpolate the elevation of the inner roof and floor of the working face and the coal gangue layer.Based on the roadway floor elevation data of the arranged working face,the method is verified by cross-experiment and compared with other interpolation algorithms such as PSO-Kriging.The results show that the interpolation error of the IAGDE-Kriging algorithm is smaller and the fitting effect is better.(3)Using multivariate data fusion technology to analyze and organize the excavated data,roadway information,small columnar data,drilling data,etc.that obtained during the layout of the working face.Then using the IAGDE-Kriging method to interpolate and rich working face internal elevation data according to the basic data.The three-dimensional model of the working face is realized by using the regular grid method and digital elevation modeling in the threedimensional spatial data model.According to the established three-dimensional model of the working face,within a certain range of advancement,calculating the volume of coal gangue mined.Combining the coal quality prediction formulas of the rough coal,raw coal and commercial coal of the working face to establish an interactive interface and to realize real-time coal quality prediction process.