As the stability of surrounding rock of coal roadway is affected by many factors, which makes the classification result hard to be consistent with the field practice. To solve the above problems, this paper proposes a method for the classification of stability of rock which is present in roadway of coal using the artificial intelligence algorithm. In this paper, the influencing factors of stability of rock which is present in roadway are analyzed, and seven influential factors are selected as classification indexes. To solve the problem of slow convergence speed and easy to fall into the local minimum of the back propagation artificial neural network (BP-ANN), an improved BP-ANN algorithm based on additional momentum and Levenberg-Marquardt optimization is proposed based on the analysis of the existing improved methods, which improves the convergence speed and avoids the local minimum effectively. Based on the learning model available, classification system based on fuzzy rule have been implemented and yielded better behavior in the situation of uncertain data sets. Finally, the stability classification model of surrounding rocks of coal roadway using BP-ANN was established in MATLAB environment, and the model was applied to 13 data samples of coal roadway for testing, with the identification rate of 92.3%. The experimental results verify that the method proposed based on fuzzy rule classification system in this paper has a high accuracy of type identification and is applicable to the stability classification of surrounding rock in the coal roadway.

No abstract

With the raw coal from a typical low-permeability coal seam in the coalfield of South Junger Basin in Xinjiang as the research object, this paper examined six kinds of coal samples with different permeabilities using a scanning electron microscope and a low-temperature nitrogen adsorption test that employed a JSM-6460LV high-resolution scanning electron microscope and an ASAP2020 automatic specific surface area micropore analyzer to measure all characteristic micropore structural parameters. According to fractal geometry theory, four fractal dimension calculation models of coal and rock were established, after which the pore structure characteristic parameters were used to calculate the fractal dimensions of the different coal seams. The results show that (1) the low-permeability coal seam in the coalfield of South Junger Basin in Xinjiang belongs to mesoporous medium, with a certain number of large pores and no micropores. The varying adsorption capacities of the different coal seams were positively correlated with pore volume, surface area, and the mesoporous surface area proportions, from which it was concluded that mesopores were the main contributors to pore adsorption in low-permeability coal seams. (2) The raw coal pore fractal dimension had a negative linear relationship to average pore size, a positive linear relationship with total pore volume, total surface area, and adsorption capacity, and a positive correlation with the mesoporous surface area proportion; that is, the higher the fractal dimension, the larger the pore volume and surface area of the raw coal. (3) The permeability of the low-permeability coal seam had a phase correlation with the micropore development degree; that is, the permeability had a phase negative correlation with the pore distribution fractal dimension, and there was a positive correlation between permeability and porosity. These results are of theoretical significance for the clean exploitation of low-permeability coal seam resources.