摘要
以重庆松藻煤矿瓦斯抽采钻孔为依托,现场监测数据为依据,采用敏感分析和有限元模拟相结合的研究方法,建立BP神经网络模型对膨胀泥岩钻孔力学参数进行反演分析。结果表明:影响膨胀泥岩钻孔变形的主要力学参数敏感度依次为饱和含水率、线性膨胀系数、泊松比、弹性模量和地应力;该反演方法提高了反演参数的有效性和可靠性;得到的力学参数符合实际情况,可为煤矿膨胀泥岩钻孔的缩径变形预测和优化设计提供理论支撑。
Taking gas extraction borehole of Chongqing Songzao coal mine and its work field data as the basis, backward analysis of mechanical parameters for coalmine expansive mudstone boreholes was conducted by the method of combining sensitivity analysis and numerical simulation and BP neural network model. The results show that the influence degree of the main parameters for deformation of expansive mudstone boreholes is in the order of saturated water content, linear expansion coefficient,Poisson ratio, elastic modulus and in-situ stress. The method improves the validity and reliability of the inversion parameters, and the obtained mechanical parameters conform to the actual situation, which can provide theoretical support for the prediction and optimization design of shrinkage deformation of the coal mine swelling mudstone boreholes.
引文
[1]谢和平,周宏伟,薛东杰,等.我国煤与瓦斯共采:理论、技术与工程[J].煤炭学报,2014,39(8):1 391-1 397.
[2]LU Y, LIU Y, LI X,et al. A new method of drilling long boreholes in low permeability coal by improving its permeabilit y[J]. International Journal of Coal Geology, 2010, 84(2):94-102.
[3]张巍,尚彦军,曲永新,等.泥质膨胀泥岩崩解物粒径分布与膨胀性关系试验研究[J].岩土力学,2013,34(1):66-72,79.
[4]周建春,魏琴,刘光栋.采用BP神经网络反演隧道围岩力学参数[J].岩石力学与工程学报,2002,23(6):941-945.
[5]张志华,周传波,夏志强,等.地铁隧道土体参数敏感性分析与正交反演[J].中南大学学报:自然科学版,2013,44(6):2 488-2 493.
[6]吕志涛,吴庚林,靳晓光,等.隧道膨胀性围岩蠕变特性分析及参数反演[J].地下空间与工程学报,2016,12(6):1 504-1 510.
[7]王开禾,罗先启,沈辉,等.围岩力学参数反演的GSA-BP神经网络模型及应用[J].岩土力学,2016,37(S1):631-638.
[8]王者超,李术才,吕晓庆,等.地下水封石油洞库施工期围岩完整性参数敏感性分析[J].岩土力学,2011,32(S2):488-495.