Gas Occurrence Characteristics And Weight Analysis Of Influencing Factors In Baoyushan Mine

In order to further study the gas occurrence law of Baoyushan Mine,according to the mine structure and gas occurrence conditions,the mine is divided into the east and west gas geological units with the Lugou anticline as the boundary.Qualitative analysis of gas occurrence rules in Baoyushan Mine using gas geological methods to determine the main controlling factors affecting gas occurrence.An improved particle swarm optimization(PSO)algorithm is used to optimize the BP neural network model,and the optimized model is used to quantify the weighting factors of gas influencing factors in different gas geological units,which provides important help for Baoyushan Mine safety production.The main conclusions are as follows:(1)Analyzed the evolution characteristics of regional geological structure,and revealed that the Lugou anticline bend-slip fold action during the Indosinian movement is the main factor causing coal body damage and uneven coal seam thickness distribution.(2)Dividing the mine into two east and west gas geological units with the mine near the No.21 exploration line(Lugou anticline).The gas distribution in different gas geological units is uneven.The gas content in the western gas geological unit is significantly higher than that in the eastern gas geological unit.(3)Revealed the gas occurrence characteristics of Baoyushan Mine,the gas content in the stress concentration area increased,and the gas content decreased locally due to the influence of surrounding rocks and internal circulating water bodies.Based on the actual geological conditions of the mine,the influences of faults,coal seam depth,coal seam thickness,androof-floor sand ratio on gas occurrence were analyzed,and the main controlling factor affecting the gas occurrence of the mine was the top-sand ratio.(4)Based on the qualitative analysis of the gas occurrence rules in Baoyushan Mine,use neural network to quantitatively express the weighting factors of gas occurrence.Based on the BP neural network,a gas content prediction model was established,and combined with the particle swarm optimization algorithm to improve the BP neural network,an AHPSO-BP neural network prediction model was constructed.Compared with the standard BP neural network prediction model,the improved model has the advantages of high prediction accuracy,fast convergence speed,and relatively stable operation results.The AHPSO-BP neural network model is used to quantitatively analyze the weight of influencing factors of gas occurrence in Baoyushan Minefield.The roof sand content is the main controlling factor affecting the gas occurrence in mines.The influence of coal thickness on gas occurrence in eastern and western gas geological units is different.Large,floor sand conten and fold complexity coefficient have little effect on gas occurrence.