煤炭在我国能源结构中占据重要地位，高瓦斯煤矿和瓦斯突出煤矿的瓦斯治理是当前亟待解决的问题。煤层钻孔预抽瓦斯是防治工作面瓦斯超限的重要手段，但预抽过程中因缺乏有效的控制和调整依据，导致难以准确预测和评估抽采过程中的瓦斯参数和预抽效果，影响预抽效率，增加了瓦斯抽采不达标和采掘失衡的风险，给瓦斯治理工作带来了巨大挑战。本研究在数字孪生驱动下，建立了两模型，提出了两方法，即：煤层钻孔预抽瓦斯过程气固耦合模型、煤层钻孔预抽瓦斯过程参数预测模型；煤层钻孔预抽瓦斯过程参数反演方法、煤层瓦斯预抽钻孔抽采效果精细化评估方法。以黄陵二号煤矿215工作面胶带巷#325-#425本煤层预抽钻孔共计600 m煤层为工程背景依托开展应用研究，通过实体对象与孪生数据之间的交互与映射，从而深入地探讨了煤层钻孔预抽瓦斯过程的多个关键问题。本文的主要研究成果如下：

建立了含瓦斯煤的气固耦合模型，其涵盖了煤层瓦斯应力-应变场控制方程、“双孔介质”的孔隙裂隙控制方程、瓦斯运移的渗流扩散方程和预抽钻孔轴向负压衰减控制方程，该模型能够有效地模拟煤层瓦斯的渗流扩散过程。此外，建立了煤层钻孔预抽瓦斯物理模拟实验平台，将数值解分别与解析解、现场试验和实验测试的结果进行对比验证，对比结果均突显了模型的可靠性。为数字孪生框架中后续煤层钻孔预抽瓦斯过程中瓦斯运移的正演模拟奠定理论基础。

利用煤层钻孔预抽瓦斯过程气固耦合模型对黄陵二号煤矿215工作面煤层钻孔预抽瓦斯过程中瓦斯运移进行正演模拟，实现了煤层钻孔预抽瓦斯过程中复杂的物理现象的虚拟仿真，探讨了煤层钻孔预抽瓦斯过程中关键参数的时空运移规律，即瓦斯压力沿钻孔轴向的衰减远小于径向方向的衰减幅度，钻孔流量越大衰减越快。结合量纲分析与物理相似准则建立煤层瓦斯压力与煤层钻孔瓦斯流量之间的函数关系，为后续煤层钻孔预抽瓦斯过程中瓦斯参数反演计算奠定基础。

利用煤层钻孔预抽瓦斯过程中瓦斯运移的正演模拟计算结果，提出了煤层瓦斯预抽钻孔数据反演模型反演煤层瓦斯压力和含量的方法，形成了实体数据为数字孪生系统提供支撑，孪生数据映射物理实体的孪生交互，进一步揭示数字孪生驱动下瓦斯的赋存规律。以黄陵二号煤矿215工作面#325-#425共101个预抽钻孔，涵盖共计600 m的煤层段作为研究案例。通过反演煤层瓦斯压力和含量，分析煤层瓦斯的赋存规律，并划分不同瓦斯分布区域。结果表明：试验煤层段瓦斯压力平均值为0.259 MPa，瓦斯含量的平均值为3.146 m³/t，瓦斯富集区域主要集中在走向长度0-50 m和240-260 m处，且瓦斯分布呈现明显的左高右低趋势，最高瓦斯压力达0.488 MPa，最高瓦斯含量为5.570 m³/t。利用实时监测数据实现现实对象和数字孪生系统的相互映射，精细划分了不同瓦斯参数赋存规律的区域。

以实体对象监测数据为基础，提出了LSTM、Attention机制和Transformer的时序特征钻孔瓦斯流量预测模型，通过多层次深度学习模型组合，引入Dropout、层归一化以及时间序列自回归模型等优化策略，提高了预测精度。利用预测模型对瓦斯参数进行了7、15和30天的短中长期预测，结果表明，Transformer模型在短中长期的预测任务中表现出色，所有钻孔的预测R²值中位数高达0.98。将预测模型与反演模型结合，利用SURFER软件成功实现了煤层瓦斯压力和含量的动态预测的二维可视化展示，在数字孪生驱动下有效映射了煤层钻孔预抽瓦斯过程压力和含量的动态变化，为实体对象提供强有力的决策支持。

结合Transformer和Sequential模型，对煤层瓦斯预抽过程中单一钻孔达到阈值的时间进行了评估，实现了对抽采达标时间的精细化掌控。此外，利用层次分析法、模糊评价法和无监督学习（GMM、K-Means）相结合的方法组建了针对煤层瓦斯预抽钻孔抽采状态的半监督学习方法，自适应地学习评估指标与数据的依赖关系。通过聚类相似的抽采数据，并结合人工数据标定，实现了对单一钻孔当日抽采状态的评估，即钻孔预抽状态GMM的优良率为59.4%，K-Means的优良率为74.3%。评估模型立足于“单一钻孔”这一瓦斯预抽过程中的最小评估单位，综合考虑预抽钻孔的抽采条件和历史数据关联性，为煤层瓦斯预抽的高效性和调控决策提供了创新性解决方案。

Given the significant role of coal in China's energy structure, managing gas in high-gas and outburst-prone coal mines is a pressing issue. Borehole gas pre-extraction in coal seams is an important strategy for preventing gas exceedances at work faces. However, the lack of effective control and adjustment basis during the pre-extraction process makes it challenging to accurately predict and assess gas parameters and the effect of pre-extraction, affecting efficiency and increasing the risk of non-compliance and mining imbalance. This study, driven by digital twin technology, establishes two models and proposes two methods: the gas-solid coupling model for coal seam borehole pre-extraction and the parameter prediction model for the pre-extraction process; the parameter inversion method for the pre-extraction process and the refined evaluation method for the pre-extraction effect of coal seam gas boreholes. Using the #325-#425 boreholes in the belt tunnel of the No. 215 working face of Huangling No. 2 Coal Mine, covering a total of 600 meters of coal seam as the engineering background for applied research, this work delves into several key issues in the pre-extraction process of coal seam boreholes through the interaction and mapping between physical objects and twin data. The main results of this paper are as follows:

This paper establishes a gas-solid coupling model for coal with gas, covering the control equations of gas stress-strain field in coal seams, the control equations of porosity and fracture permeability under the "dual-porosity medium" theory, the seepage diffusion equation of gas migration, and the axial negative pressure attenuation control equation for pre-extraction boreholes. This model can effectively simulate the seepage and diffusion process of gas in coal seams. Moreover, a physical simulation platform for coal seam borehole pre-extraction is established, and the numerical solutions are compared with analytical solutions, field experiments, and test results, highlighting the reliability of the model. This lays the theoretical foundation for subsequent forward simulations of gas migration during the pre-extraction process of boreholes in the digital twin framework.

Using the gas-solid coupling model for coal seam borehole pre-extraction, forward simulations of gas migration in the No. 215 working face of Huangling No. 2 Coal Mine during the pre-extraction process were conducted, realizing the virtual simulation of complex physical phenomena in the pre-extraction process. The study discusses the spatiotemporal migration rules of key parameters during the pre-extraction process, indicating that gas pressure attenuation along the borehole axis is much less than the attenuation in the radial direction, and the larger the borehole flow, the faster the attenuation. A functional relationship between coal seam gas pressure and borehole gas flow is established based on dimension analysis and physical similarity criteria, laying the foundation for subsequent inversion calculations of gas parameters during the pre-extraction process.

Using the results of forward simulation calculations of gas migration during the coal seam borehole pre-extraction process, a method for inverting coal seam gas pressure and content using the data inversion model for pre-extraction boreholes is proposed. This enables the support of physical data for the digital twin system and the twin interaction of data mapping to physical entities, further revealing the storage rules and dynamic evolution process of gas driven by digital twins. The study takes the #325-#425 boreholes, covering a total of 600 meters of coal seam section in the No. 215 working face of Huangling No. 2 Coal Mine, as the research case. By inverting the coal seam gas pressure and content, the distribution rules of gas pressure and content in the coal seam are analyzed, and different gas distribution areas are divided. The results show that the average gas pressure in the test coal seam section is 0.259 MPa, and the average gas content is 3.146 m³/t, with gas enrichment areas mainly concentrated around the axial lengths of 0-50 m and 240-260 m, showing a clear trend of higher on the left and lower on the right. The highest gas pressure reached 0.488 MPa, and the highest gas content was 5.570 m³/t. Real-time monitoring data are used to achieve mutual mapping between physical objects and digital twin systems, and different gas parameter storage areas are finely divided.

Based on monitoring data from physical objects, a time-series feature borehole gas flow prediction model employing LSTM, Attention mechanism, and Transformer is proposed. By combining multi-layer deep learning models and introducing optimization strategies such as Dropout, layer normalization, and time series autoregressive models, the prediction accuracy is enhanced. The prediction model is used for short, medium, and long-term forecasts of gas parameters for 7, 15 and 30 days. The results show that the Transformer model excels in short, medium, and long-term prediction tasks, with a median R² value of predictions for all boreholes reaching 0.98. By combining the prediction model with the inversion model, the dynamic prediction of coal seam gas pressure and content is successfully visualized in two dimensions using SURFER software. This effectively maps the dynamic changes in pressure and content during the coal seam borehole pre-extraction process driven by digital twins, providing strong decision support for physical objects.

Combining Transformer and sequential models, the assessment of the time for a single borehole to reach the threshold during the pre-extraction process is carried out, achieving refined control over the time to reach the standard. Moreover, a semi-supervised learning method for evaluating the pre-extraction state of coal seam boreholes is constructed using a combination of methods such as the Analytic Hierarchy Process, fuzzy evaluation method, and unsupervised learning (GMM, K-Means), adaptively learning the dependence relationship between evaluation indicators and data. By clustering similar extraction data and combining manual data calibration, the evaluation of the daily extraction state of a single borehole is realized, with an excellence rate of 59.4% for GMM and 74.3% for K-Means in the pre-extraction state. The evaluation model, based on "single borehole" as the smallest evaluation unit in the pre-extraction process, comprehensively considers the extraction conditions of pre-extraction boreholes and the relevance of historical data, providing an innovative solution for the efficiency and control decision-making of coal seam gas pre-extraction.

[ ] Zhao P, Zhuo R, Li S, et al. Greenhouse gas protection and control based upon the evolu-tion of overburden fractures under coal mining: A review of methods, influencing fac-tors, and techniques[J]. Energy, 2023: 129158.

[ ] Wang X, Zhou F, Ling Y, et al. Overview and outlook on utilization technologies of low-concentration coal mine methane[J]. Energy & Fuels, 2021, 35(19): 15398-15423.

[ ] Wu X, Li H, Wang B, et al. Review on improvements to the safety level of coal mines by applying intelligent coal mining[J]. Sustainability, 2022, 14(24): 16400.

[ ] Ulbig P, Hoburg D. Determination of the calorific value of natural gas by different meth-ods[J]. Thermochimica acta, 2002, 382(1-2): 27-35.

[ ] Khalil A E E, Arghode V K, Gupta A K, et al. Low calorific value fuelled distributed combustion with swirl for gas turbine applications[J]. Applied energy, 2012, 98: 69-78.

[ ] 张建国, 王满, 张国川, 等. 平顶山矿区深部动力灾害防治与资源绿色开采[J]. 煤炭科学技术, 2023, 51(1): 295-303.

[ ] Lee C C, Zhang J, Hou S. The impact of regional renewable energy development on envi-ronmental sustainability in China[J]. Resources Policy, 2023, 80: 103245.

[ ] Li M, Wang H, Wang D, et al. Risk assessment of gas explosion in coal mines based on fuzzy AHP and bayesian network[J]. Process Safety and Environmental Protection, 2020, 135: 207-218.

[ ] Lu Y Y, Zhang H D, Zhou Z, et al. Current status and effective suggestions for efficient exploitation of coalbed methane in China: a review [J]. Energy & Fuels, 2021, 35(11): 9102-9123.

[ ] He J, Leng C, Xu H, et al. Kinetic analysis of diffusion combustion of low calorific val-ue gas under the action of thermal dynamics[J]. Fuel, 2021, 287: 119435.

[ ] 肖家平, 杨科, 李志华, 等. 远距离煤层开采工作面布置方式卸压增透效应[J]. 中国安全科学学报, 2019, 29(3): 82.

[ ] 袁欣鹏, 梁冰, 孙维吉, 等. 煤层群覆岩裂隙带煤与瓦斯共采协同机制研究[J]. 中国矿业大学学报, 2020 (2): 289-295.

[ ] Yang F, Jiao Y, Zhang J, et al. Study on simultaneous extraction of coal and gas and clean utilization in high-gas outburst mines[C]//IOP Conference Series: Earth and Envi-ronmental Science. IOP Publishing, 2020, 510(2): 022013.

[ ] 程远平, 付建华, 俞启香. 中国煤矿瓦斯抽采技术的发展[J]. 采矿与安全工程学报, 2009, 2.

[ ] 翟成, 丛钰洲, 陈爱坤, 等. 中国煤矿瓦斯突出灾害治理的若干思考及展望[J]. 中国矿业大学学报, 2023, 52(06): 1146-1161.

[ ] 王兆丰, 孙小明, 陆庭侃, 等. 液态CO2相变致裂强化瓦斯预抽试验研究[J]. 河南理工大学学报: 自然科学版, 2015, 34(1): 1-5.

[ ] 王国法, 庞义辉, 李爽, 等. 基于煤矿时空多源信息感知的智能安控闭环体系[J]. 矿业安全与环保, 2022, 49(4): 1-11.

[ ] Li T, Wu B, Lei B. Study on the Optimization of a Gas Drainage Borehole Drainage Horizon Based on the Evolution Characteristics of Mining Fracture[J]. Energies, 2019, 12(23): 4499.

[ ] 申健, 李雪冰. 瓦斯抽采达标评价AHP-FCE模型及应用[J]. 辽宁工程技术大学学报: 自然科学版, 2015, 34(5): 578-583.

[ ] Wu C, Yuan C, Wen G, et al. A dynamic evaluation technique for assessing gas output from coal seams during commingling production within a coalbed methane well: a case study from the Qinshui Basin[J]. International Journal of Coal Science & Technology, 2020, 7: 122-132.

[ ] Liu P, Fan L, Li Q, et al. Power ultrasound assisted coalbed methane enhancement re-covery: Field application and performance evaluation in underground coal mine [J]. Fuel, 2022, 324: 124575.

[ ] Wen H, Yan L, Jin Y, et al. Coalbed methane concentration prediction and early-warning in fully mechanized mining face based on deep learning[J]. Energy, 2023, 264: 126208.

[ ] Lecun Y, Bengio Y, Hinton G. Deep learning[J]. nature, 2015,521(7553): 436-444.

[ ] 张吉林, 徐雪战, 邹云龙. 矿井瓦斯抽采达标在线评价技术研究[J]. 能源与环保, 2017, 39(5): 51-54.

[ ] Gelernter D. Mirror worlds: Or the day software puts the universe in a shoebox... How it will happen and what it will mean[M]. Oxford University Press, 1993.

[ ] Grieves M. Digital twin: manufacturing excellence through virtual factory replication[J]. White paper, 2014, 1(2014): 1-7.

[ ] Främling K, Holmström J, Ala-Risku T, et al. Product agents for handling information about physical objects[J]. Report of Laboratory of information processing science series B, TKO-B, 2003, 153(03).

[ ] Grieves M. Back to the future: Product lifecycle management and the virtualization of product information[J]. Product Realization: A Comprehensive Approach, 2009: 1-13.

[ ] Grieves M W. Product lifecycle management: the new paradigm for enterprises[J]. In-ternational Journal of Product Development, 2005, 2(1-2): 71-84.

[ ] 邢震. 面向智能矿山的数字孪生技术研究进展[J/OL].工矿自动化:1-17.

[ ] 罗昌亮, 毛娅, 陈作炳, 等. 数字孪生与神经网络融合驱动的烧成系统故障预警研究[J/OL]. 机械科学与技术: 1-8.

[ ] Shafto M, Conroy M, Doyle R, et al. Draft modeling, simulation, information technolo-gy & processing roadmap[J]. Technology area, 2010, 11: 1-32.

[ ] Hochhalter J, Leser W P, Newman J A, et al. Coupling damage-sensing particles to the digitial twin concept[R]. 2014.

[ ] Rosen R, Von Wichert G, Lo G, et al. About the importance of autonomy and digital twins for the future of manufacturing[J]. Ifac-papersonline, 2015, 48(3): 567-572.

[ ] Schluse M, Rossmann J. From simulation to experimentable digital twins: Simulation-based development and operation of complex technical systems[C]//2016 IEEE interna-tional symposium on systems engineering (ISSE). IEEE, 2016: 1-6.

[ ] Söderberg R, Wärmefjord K, Carlson J S, et al. Toward a Digital Twin for real-time ge-ometry assurance in individualized production[J]. CIRP annals, 2017, 66(1): 137-140.

[ ] Xu Y, Sun Y, Liu X, et al. A digital-twin-assisted fault diagnosis using deep transfer learning[J]. Ieee Access, 2019, 7: 19990-19999.

[ ] Liu J, Zhou H, Liu X, et al. Dynamic evaluation method of machining process planning based on digital twin[J]. IEEE Access, 2019, 7: 19312-19323.

[ ] 张霖. 关于数字孪生的冷思考及其背后的建模和仿真技术[J]. 系统仿真学报, 2020, 32(4): 744.

[ ] 刘大同, 郭凯, 王本宽, 等. 数字孪生技术综述与展望[J]. 仪器仪表学报, 2018, 39(11): 1-10.

[ ] 陶飞, 刘蔚然, 刘检华, 等. 数字孪生及其应用探索[J].计算机集成制造系统, 2018, 24(01): 1-18.

[ ] Xu Y, Sun Y, Liu X, et al. A digital-twin-assisted fault diagnosis using deep transfer learning[J]. Ieee Access, 2019, 7: 19990-19999.

[ ] 李浩, 陶飞, 王昊琪, 等. 基于数字孪生的复杂产品设计制造一体化开发框架与关键技术[J]. 计算机集成制造系统, 2019, 25(06): 1320-1336.

[ ] 丁华, 杨亮亮, 杨兆建, 等. 数字孪生与深度学习融合驱动的采煤机健康状态预测[J].中国机械工程, 2020, 31(07): 815-823.

[ ] 肖粲俊, 刘红梅, 石发强, 等.基于数字孪生的煤矿智能管控平台架构研究与实现[J]. 矿业安全与环保, 2023, 50(05): 43-49.

[ ] 张超, 张旭辉, 毛清华, 等. 煤矿智能掘进机器人数字孪生系统研究及应用[J]. 西安科技大学学报, 2020, 40(5): 813-822.

[ ] 蔡兴旺, 裴耀强, 杨继华, 等. 煤矿掘进机系统数字孪生技术研究[J/OL]. 系统仿真学报: 1-13.

[ ] Yu R, Yang X, Cheng K. Deep learning and IoT enabled digital twin framework for monitoring open-pit coal mines[J]. Frontiers in Energy Research, 2023, 11: 1265111.

[ ] Miao B, Ge S, Guo Y. Construction of digital twin system for intelligent mining in coal mines[J]. J. Mining Sci. Technol, 2022, 7(2): 143-153.

[ ] Cheng Y, Liu Q, Ren T, et al. Flow Theory of Gas in Coal Seams[J]. Coal Mechanics, 2021: 377-414.

[ ] Zeng Z, Grigg R. A criterion for non-Darcy flow in porous media[J]. Transport in porous media, 2006, 63: 57-69.

[ ] FENG G, LIU Q, SHI G, et al. An unsteady seepage flow model considering kickoff pressure gradient for low-permeability gas reservoirs[J]. Petroleum Exploration and De-velopment, 2008, 35(4): 457-461.

[ ] Lu M, Connell L D. A model for the flow of gas mixtures in adsorption dominated dual porosity reservoirs incorporating multi-component matrix diffusion: Part I. Theoretical development[J]. Journal of Petroleum Science and Engineering, 2007, 59(1-2): 17-26.

[ ] Noack K. Control of gas emissions in underground coal mines[J]. International Journal of Coal Geology, 1998, 35(1-4): 57-82.

[ ] Millington R J. Gas diffusion in porous media[J]. Science, 1959, 130(3367): 100-102.

[ ] Pan Z, Connell L D, Camilleri M, et al. Effects of matrix moisture on gas diffusion and flow in coal[J]. Fuel, 2010, 89(11): 3207-3217.

[ ] Xia T, Zhou F, Liu J, et al. Evaluation of the pre-drained coal seam gas quality[J]. Fuel, 2014, 130: 296-305.

[ ] Liu J, Chen Z, Elsworth D, et al. Interactions of multiple processes during CBM extrac-tion: a critical review[J]. International Journal of Coal Geology, 2011, 87(3-4): 175-189.

[ ] Biot M A. General theory of three dimensional consolidation[J]. Journal of Applied Physics, 1941, 12: 155-164.

[ ] Terzaghi K. Origin and functions of soil mechanics[J]. Transactions of the American Society of Civil Engineers, 1953, 118(2): 666-696.

[ ] Ertekin T, King G R, Schwerer F C. Dynamic gas slippage: a unique dual-mechanism approach to the flow of gas in tight formations[J]. SPE formation evaluation, 1986, 1(01): 43-52.

[ ] Zhou A, Li J, Gong W, et al. Theoretical and numerical study on the contribution of multi-hole arrangement to coalbed methane extraction[J]. Energy, 2023, 284: 128598.

[ ] Gray I. Reservoir engineering in coal seams: part 1—the physical process of gas storage and movement in coal seams[J]. SPE Reservoir Engineering, 1987, 2(01): 28-34.

[ ] Zhao Y, Hu Y, Zhao B, et al. Nonlinear coupled mathematical model for solid defor-mation and gas seepage in fractured media[J]. Transport in Porous Media, 2004, 55(2): 119-136.

[ ] Zhu W C, Liu J, Sheng J C, et al. Analysis of coupled gas flow and deformation process with desorption and Klinkenberg effects in coal seams[J]. International Journal of Rock Mechanics and Mining Sciences, 2007, 44(7): 971-980.

[ ] Connell L D. Coupled flow and geomechanical processes during gas production from coal seams[J]. International Journal of Coal Geology, 2009, 79(1-2): 18-28.

[ ] Valliappan S, Wohua Z. Numerical modelling of methane gas migration in dry coal seams[J]. International Journal for Numerical and Analytical Methods in Geomechanics, 1996, 20(8): 571-593.

[ ] Choi E S, Cheema T, Islam M R. A new dual-porosity/dual-permeability model with non-Darcian flow through fractures[J]. Journal of Petroleum Science and Engineering, 1997, 17(3–4): 331–344.

[ ] Cicek O. Compositional and non-isothermal simulation of CO2 sequestration in natural-ly fractured reservoirs/coalbeds: development and verification of the model[C]. The SPE Annual Technical Conference and Exhibition, Denver, Colorado, U.S.A., 2003.

[ ] 刘清泉, 程远平, 李伟, 等.深部低透气性首采层煤与瓦斯气固耦合模型[J]. 岩石力学与工程学报, 2015, 34(S1): 2749-2758.

[ ] 赵阳升, 秦惠增, 白其峥. 煤层瓦斯流动的固－气耦合数学模型及数值解法的研究[J].固体力学学报, 1994(01): 49-57.

[ ] 赵阳升. 煤体—瓦斯耦合数学模型及数值解法[J]. 岩石力学与工程学报, 1994(03): 229-239.

[ ] 孙培德, 万华根. 煤层气越流固-气耦合模型及可视化模拟研究[J]. 岩石力学与工程学报, 2004, (07): 1179-1185.

[ ] 杨新乐, 任常在, 张永利, 等. 低渗透煤层气注热开采热-流-固耦合数学模型及数值模拟[J]. 煤炭学报, 2013, 38(06): 1044-1049.

[ ] Chen D, Pan Z, Liu J, et al. Modeling and simulation of moisture effect on gas storage and transport in coal seams[J]. Energy & Fuels, 2012, 26(3): 1695-1706.

[ ] Harpalani S, Chen G. Estimation of changes in fracture porosity of coal with gas emis-sion[J]. Fuel, 1995, 74(10): 1491-1498.

[ ] Shi J, Chang Y, Wu S, et al. Development of material balance equations for coalbed me-thane reservoirs considering dewatering process, gas solubility, pore compressibility and matrix shrinkage[J]. International Journal of Coal Geology, 2018, 195: 200-216.

[ ] Thararoop P. Development of a multi-mechanistic, dual-porosity, dual-permeability nu-merical flow model for coalbed methane reservoirs accounting for coal shrinkage and swelling effects[D]. The Pennsylvania State University, 2010.

[ ] Thararoop P, Karpyn Z T, Ertekin T. Development of a material balance equation for coalbed methane reservoirs accounting for the presence of water in the coal matrix and coal shrinkage and swelling[J]. Journal of Unconventional Oil and Gas Resources, 2015, 9: 153-162.

[ ] Connell L D, Lu M, Pan Z. An analytical coal permeability model for tri-axial strain and stress conditions[J]. International Journal of Coal Geology, 2010, 84(2): 103-114.

[ ] 马飞英, 王永清, 王林, 等. 考虑水分含量的煤岩渗透率动态变化特征[J]. 天然气地球科学, 2014, 25(09): 1477-1482.

[ ] Wang K, Zang J, Wang G, et al. Anisotropic permeability evolution of coal with effec-tive stress variation and gas sorption: model development and analysis[J]. International Journal of Coal Geology, 2014, 130: 53-65.

[ ] Karacan C Ö, Ruiz F A, Cotè M, et al. Coal mine methane: a review of capture and uti-lization practices with benefits to mining safety and to greenhouse gas reduction[J]. In-ternational journal of coal geology, 2011, 86(2-3): 121-156.

[ ]刘军. 预抽钻孔负压沿孔长变化特性及对瓦斯抽采效果影响研究[D]. 焦作: 河南理工大学, 2014.

[ ] Yan L, Wen H, Jin Y, et al. Fluid–Solid Coupling Characteristics of Methane-Containing Coal during Borehole Extraction of Coalbed: Numerical Modeling and Experimental Research[J]. ACS omega, 2023.

[ ] Zhang Q, Wang E, Li Z, et al. Control of directional long borehole on gas drainage and optimal design: Case study[J]. Journal of Natural Gas Science and Engineering, 2022, 107: 104766.

[ ] 张超林, 王恩元, 许江, 等. 煤层瓦斯压力对瓦斯抽采效果的影响[J]. 采矿与安全工程学报, 2022, 39(03): 634-642.

[ ] Richter M, Kleinrahm R. Influence of adsorption and desorption on accurate density measurements of gas mixtures[J]. The Journal of Chemical Thermodynamics, 2014, 74: 58-66.

[ ] 林海飞, 龙航, 李树刚, 等. 煤体瓦斯吸附解吸与压裂渗流全过程真三轴试验系统研发与应用[J]. 岩石力学与工程学报, 2022, 41(S2): 3294-3305.

[ ] 王和平. 采用气压法原理的WS-1型瓦斯计标准装置的研制[J]. 计量技术, 1995(11): 37-39.

[ ] Bertard C, Bruyet B, Gunther J. Determination of desorbable gas concentration of coal (direct method)[C]//International Journal of Rock Mechanics and Mining Sciences & Geomechanics Abstracts. Pergamon, 1970, 7(1): 43-65.

[ ] Creedy D P. Methods for the evaluation of seam gas content from measurements on coal samples[J]. Mining Science and Technology, 1986, 3(2): 141-160.

[ ] Szlązak N, Obracaj D, Korzec M. Estimation of gas loss in methodology for determin-ing methane content of coal seams[J]. Energies, 2021, 14(4): 982.

[ ] 余陶, 卢平, 孙金华, 等. 基于钻孔瓦斯流量和压力测定有效抽采半径[J]. 采矿与安全工程学报, 2012, 29(04): 596-600.

[ ] 冯玉凤, 董虎子. 基于不同含水率煤的瓦斯解吸特性推算煤层瓦斯压力方法研究[J].煤矿安全, 2023, 54(09): 8-14.

[ ] 褚鹏, 尚德磊, 李建华, 等. 原位保压取心气体组分对煤层瓦斯压力测算的影响[J]. 煤田地质与勘探, 2023, 51(08): 79-87.

[ ] Wang L, Cheng L, Cheng Y, et al. A new method for accurate and rapid measurement of underground coal seam gas content[J]. Journal of Natural Gas Science and Engineering, 2015, 26: 1388-1398.

[ ] Butland C I, Moore T A. Secondary biogenic coal seam gas reservoirs in New Zealand: a preliminary assessment of gas contents[J]. International Journal of Coal Geology, 2008, 76(1-2): 151-165.

[ ] Diamond W P, Schatzel S J. Measuring the gas content of coal: A review[J]. Internation-al Journal of Coal Geology, 1998, 35(1-4): 311-331.

[ ] 孙昌宁. 基于煤样常态瓦斯存留量的煤层瓦斯压力及含量测值技术研究[D]. 徐州:中国矿业大学, 2021.

[ ] 赵发军, 刘彦伟, 郝富昌, 等. 常压法测定煤层瓦斯含量的误差分析[J]. 中国安全生产科学技术, 2018, 14(03): 102-108.

[ ] Liu Y, Du Y, Li Z, et al. A rapid and accurate direct measurement method of under-ground coal seam gas content based on dynamic diffusion theory[J]. International Jour-nal of Mining Science and Technology, 2020, 30(6): 799-810.

[ ] Hou X, Liu S, Zhu Y, et al. Evaluation of gas contents for a multi-seam deep coalbed methane reservoir and their geological controls: In situ direct method versus indirect method[J]. Fuel, 2020, 265: 116917.

[ ] Wang Y, Kang J, Zhou F, et al. Evaluation of lost gas in the borehole drilling stage: Im-plication for the direct method of coalbed methane content determination[J]. Journal of Natural Gas Science and Engineering, 2022, 105: 104711.

[ ] Song J, Su X, Wang Q, et al. A new method for calculating gas content of coal reser-voirs with consideration of a micro-pore overpressure environment[J]. Natural Gas In-dustry B, 2017, 4(3): 182-188.

[ ] 赵洪瑞. 煤层瓦斯赋存参数快速自动测量装置[J]. 煤矿安全, 2016, 47(03): 87-89+93.

[ ] 周福宝, 康建宏, 王有湃, 等. 煤层瓦斯含量井下一站式自动化精准测定方法[J]. 煤炭学报, 2022, 47(08): 2873-2882.

[ ] Moore T A. Coalbed methane: A review[J]. International Journal of Coal Geology, 2012, 101: 36-81.

[ ] Altowilib A, AlSaihati A, Alhamood H, et al. Reserves estimation for coalbed methane reservoirs: A review[J]. Sustainability, 2020, 12(24): 10621.

[ ] Lama R D, Bodziony J. Management of outburst in underground coal mines[J]. Inter-national Journal of Coal Geology, 1998, 35(1-4): 83-115.

[ ] Cao Y, He D, Glick D C. Coal and gas outbursts in footwalls of reverse faults[J]. Inter-national Journal of Coal Geology, 2001, 48(1-2): 47-63.

[ ] Cui X, Bustin R M, Chikatamarla L. Adsorption‐induced coal swelling and stress: Im-plications for methane production and acid gas sequestration into coal seams[J]. Journal of Geophysical Research: Solid Earth, 2007, 112(B10).

[ ] Zhao Y, Hu Y, Zhao B, et al. Nonlinear coupled mathematical model for solid defor-mation and gas seepage in fractured media[J]. Transport in Porous Media, 2004, 55: 119-136.

[ ] Zhu W C, Liu J, Sheng J C, et al. Analysis of coupled gas flow and deformation pro-cess with desorption and Klinkenberg effects in coal seams[J]. International Journal of Rock Mechanics and Mining Sciences, 2007, 44(7): 971-980.

[ ] Valliappan S, Wohua Z. Numerical modelling of methane gas migration in dry coal seams[J]. International Journal for Numerical and Analytical Methods in Geomechanics, 1996, 20(8): 571-593.

[ ] Karimpouli S, Tahmasebi P, Ramandi H L. A review of experimental and numerical modeling of digital coalbed methane: Imaging, segmentation, fracture modeling and permeability prediction[J]. International Journal of Coal Geology, 2020, 228: 103552.

[ ] Hu X, Yang S, Zhou X, et al. A quantification prediction model of coalbed methane content and its application in Pannan coalfield, Southwest China[J]. Journal of Natural Gas Science and Engineering, 2014, 21: 900-906.

[ ] Wang G, Ren T, Qi Q, et al. Prediction of coalbed methane (CBM) production consid-ering bidisperse diffusion: model development, experimental test, and numerical simu-lation[J]. Energy & Fuels, 2017, 31(6): 5785-5797.

[ ] Gentzis T, Bolen D. The use of numerical simulation in predicting coalbed methane producibility from the Gates coals, Alberta Inner Foothills, Canada: Comparison with Mannville coal CBM production in the Alberta Syncline[J]. International Journal of Coal Geology, 2008, 74(3-4): 215-236.

[ ] Tang M, Zheng P, Zheng C, et al. Numerical analysis and prediction of coal mine me-thane drainage based on gas–solid coupling model[J]. Tehnički vjesnik, 2019, 26(3): 752-761.

[ ] 张军, 孙炳兴, 梁运培, 等. 工作面瓦斯涌出量预测数值模拟方法应用[J]. 煤矿安全, 2007(03): 15-17.

[ ] 姜延航, 周露函, 韩明旭. 一面四巷瓦斯抽采对采空区遗煤自燃影响数值模拟研究[J/OL]. 煤炭科学技术: 1-10.

[ ] 王新丰, 刘文港, 王龙, 等. 静态致裂作用下低渗厚煤层瓦斯增透数值模拟研究[J]. 煤田地质与勘探, 2023, 51(11): 1-12.

[ ] 贾进章, 张天阔, 王东明, 等. 注二氧化碳促抽煤层瓦斯数值模拟及现场试验[J]. 安全与环境工程, 2023, 30(01): 78-86.

[ ] 王登科, 唐家豪, 魏建平, 等. 煤层瓦斯多机制流固耦合模型与瓦斯抽采数值模拟分析[J]. 煤炭学报, 2023, 48(02): 763-775.

[ ] 刘彦青, 李国富, 张宏杰, 等. 回采期间下邻近层向工作面涌出瓦斯数值模拟分析[J].采矿与安全工程学报, 2022, 39(04): 827-836+846.

[ ] 高建良, 陈太东, 王文祺, 等. 掘进工作面瓦斯爆炸风门冲击载荷的数值模拟[J]. 安全与环境学报, 2022, 22(02): 688-694.

[ ] Zhao Y, Zhao L, Wang Z, et al. Numerical simulation of multi-seam coalbed methane production using a gray lattice Boltzmann method[J]. Journal of Petroleum Science and Engineering, 2019, 175: 587-594.

[ ] Xu H, Qin Y, Wu F, et al. Numerical modeling of gas extraction from coal seam com-bined with a dual-porosity model: Finite difference solution and multi-factor analysis[J]. Fuel, 2022, 313: 122687.

[ ] Erfani S M , Rajasegarar S , Karunasekera S , et al. High-dimensional and large-scale anomaly detection using a linear one-class SVM with deep learning.[J]. Pattern Recog-nition, 2016, 58(C):121-134.

[ ] Torfi A, Shirvani R A, Keneshloo Y, et al. Natural language processing advancements by deep learning: A survey[J]. arXiv preprint arXiv:2003.01200, 2020.

[ ] Deng L, Yu D. Deep learning: methods and applications[J]. Foundations and Trends® in Signal Processing, 2014, 7(3-4): 197-387.

[ ] Wang J , Zhang J , Wang X . Bilateral LSTM: A Two-Dimensional Long Short-Term Memory Model With Multiply Memory Units for Short-Term Cycle Time Forecasting in Re-entrant Manufacturing Systems[J]. IEEE Transactions on Industrial Informatics, 2018, 14(2):748-758.

[ ] Li Y C, Zhou R G, Xu R Q, et al. A quantum deep convolutional neural network for image recognition[J]. Quantum Science and Technology, 2020, 5(4): 044003.

[ ] Sun Y, Chen Y, Wang X, et al. Deep learning face representation by joint identification-verification[C]//Advances in neural information processing systems. 2014: 1988-1996.

[ ] 郭丽丽, 丁世飞. 深度学习研究进展[J]. 计算机科学, 2015, 42(05): 28-33.

[ ] Michelsanti D, Tan Z H, Zhang S X, et al. An overview of deep-learning-based audio-visual speech enhancement and separation[J]. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2021, 29: 1368-1396.

[ ] Wang N, Yeung D Y. Learning a deep compact image representation for visual track-ing[C]//Advances in neural information processing systems. 2013: 809-817.

[ ] Liu Z, Luo P, Wang X, et al. Deep learning face attributes in the wild[C]//Proceedings of the IEEE International Conference on Computer Vision. 2015: 3730-3738.

[ ] Uziela K, Menéndez Hurtado D, Shu N, et al. ProQ3D: improved model quality as-sessments using deep learning[J]. Bioinformatics, 2017, 33(10): 1578-1580.

[ ] 施式亮. 矿井安全非线性动力学评价模型及应用研究[D]. 长沙: 中南大学, 2000.

[ ] 施式亮, 伍爱友. GM(1,1)模型与线性回归组合方法在矿井瓦斯涌出量预测中的应用[J]. 煤炭学报, 2008(04): 415-418.

[ ] 马磊, 陆卫东, 魏国营. 基于GASA-BP神经网络的煤层瓦斯含量预测方法研究[J]. 中国安全生产科学技术, 2022, 18(08): 59-65.

[ ]何利文, 施式亮, 宋译, 等. 基于支持向量机(SVM)的回采工作面瓦斯涌出混沌预测方法研究[J]. 中国安全科学学报, 2009, 19(09): 42-46+180.

[ ]伍爱友, 田云丽, 宋译, 等. 灰色系统理论在矿井瓦斯涌出量预测中的应用[J]. 煤炭学报, 2005(05): 47-50.

[ ] 付华, 谢森, 徐耀松, 等. 基于MPSO-WLS-SVM的矿井瓦斯涌出量预测模型研究[J].中国安全科学学报, 2013, 23(05): 56-61.

[ ] 付华, 姜伟, 单欣欣. 基于耦合算法的煤矿瓦斯涌出量预测模型研究[J]. 煤炭学报, 2012, 37(04): 654-658.

[ ] 付华. 煤矿瓦斯灾害特征提取与信息融合技术研究[D]. 阜新: 辽宁工程技术大学, 2006.

[ ] Akdaş S B, Fişne A. A data-driven approach for the prediction of coal seam gas content using machine learning techniques[J]. Applied Energy, 2023, 347: 121499.

[ ] Sujatha R, Chatterjee J M, Jhanjhi N Z, et al. Performance of deep learning vs machine learning in plant leaf disease detection[J]. Microprocessors and Microsystems, 2021, 80: 103615.

[ ] Wang P, Fan E, Wang P. Comparative analysis of image classification algorithms based on traditional machine learning and deep learning[J]. Pattern Recognition Letters, 2021, 141: 61-67.

[ ] Janiesch C, Zschech P, Heinrich K. Machine learning and deep learning[J]. Electronic Markets, 2021, 31(3): 685-695.

[ ] Dargan S, Kumar M, Ayyagari M R, et al. A survey of deep learning and its applica-tions: a new paradigm to machine learning[J]. Archives of Computational Methods in Engineering, 2020, 27: 1071-1092.

[ ] Castiglioni I, Rundo L, Codari M, et al. AI applications to medical images: From ma-chine learning to deep learning[J]. Physica Medica, 2021, 83: 9-24.

[ ] Ordóñez, Javier F , Roggen, et al. Sensors, Vol. 16, Pages 115: Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition[J]. Sensors, 2016, 16(1).

[ ] Lenz I,Lee H,Saxena A . Deep learning for detecting robotic grasps [J]. The Interna-tional Journal of Robotics Research,2015,34(4-5):705-724.

[ ] 许满贵. 煤矿重大危险源评价研究[J]. 矿业安全与环保, 2005(05): 80-81+84.

[ ] 梁晓珍, 王依, 侯玮. 矿井瓦斯涌出量动态预测数值模拟方法[J]. 煤炭技术, 2012, 31(05): 69-70.

[ ]田云丽, 周利华. 基于BP神经网络的煤与瓦斯突出预测方法的研究[J]. 系统工程理论与实践, 2005(12): 102-106.

[ ] 肖红飞, 田云丽, 周利华. 基于MATLAB 工具箱的开采煤层自燃危险性预测[J]. 中国安全科学学报, 2005(10): 7-10+24.

[ ] 邱春荣. 基于PSO-SVR的瓦斯浓度预测方法研究[D]. 中国矿业大学, 2017.

[ ] Du S, Wang M, Yang J, et al. An enhanced prediction framework for coalbed methane production incorporating deep learning and transfer learning[J]. Energy, 2023, 282: 128877.

[ ] Guo Z, Zhao J, You Z, et al. Prediction of coalbed methane production based on deep learning[J]. Energy, 2021, 230: 120847.

[ ] WORDEN K,STASZEWSKI WJ,HENSMAN J J. Natural computing for mechanical systems research:A tutorial overview[J]. Mechanical Systems and Signal Pro-cessing,2011,25(1):4-111.

[ ] Read J ,Perez-Cruz F. Deep Learning for Multi-label Classification[J]. Machine Learn-ing,2014,85(3):333-359.

[ ] Soutner D , Müller, Luděk. Application of LSTM neural networks in language model-ling[J]. Lecture Notes in Computer Science, 2013, 8082:105-112.

[ ] Li H,Ota K,Dong M .Learning IoT in Edge: Deep Learning for the Internet of Things with Edge Computing[J]. IEEE Network, 2018,32(1):96-101.

[ ] 毛勇华, 桂小林, 李前, 等. 深度学习应用技术研究[J]. 计算机应用研究, 2016, 33(11): 3201-3205.

[ ] Peng F, Peng S, Du W, et al. Coalbed methane content prediction using deep belief network[J]. Interpretation, 2020, 8(2): T309-T321.

[ ] 付华, 任仁, 王雨虹, 等. 基于CSO-RVM的瓦斯涌出量预测模型研究[J]. 传感技术学报, 2015, 28(10): 1508-1512.

[ ] Zhao Z, Chen Y, Zhang Y, et al. A deep learning model for predicting the production of coalbed methane considering time, space, and geological features[J]. Computers & Ge-osciences, 2023, 173: 105312.

[ ] 李冬, 彭苏萍, 杜文凤, 等. 煤层瓦斯突出危险区综合预测方法[J]. 煤炭学报, 2018, 43(02): 466-472.

[ ] Wen H, Yan L, Jin Y, et al. Coalbed methane concentration prediction and early-warning in fully mechanized mining face based on deep learning[J]. Energy, 2023, 264: 126208.

[ ] Zhong R, Johnson R, Chen Z, et al. Coal identification using neural networks with real-time coalbed methane drilling data[J]. The APPEA Journal, 2019, 59(1): 319-327.

[ ] 杨丽, 刘晖, 毛善君, 等. 基于多元分布滞后模型的瓦斯浓度动态预测[J]. 中国矿业大学学报, 2016, 45(03): 455-461.

[ ] Karimpouli S, Tahmasebi P, Ramandi H L. A review of experimental and numerical modeling of digital coalbed methane: Imaging, segmentation, fracture modeling and permeability prediction[J]. International Journal of Coal Geology, 2020, 228: 103552.

[ ] 马磊, 陆卫东, 魏国营. 基于GASA-BP神经网络的煤层瓦斯含量预测方法研究[J]. 中国安全生产科学技术, 2022, 18(08): 59-65.

[ ] Zuber M D, Boyer C M. Coalbed-methane evaluation techniques-The current state of the art[J]. Journal of petroleum technology, 2002, 54(02): 66-68.

[ ] Pophare A M, Mendhe V A, Varade A. Evaluation of coal bed methane potential of coal seams of Sawang Colliery, Jharkhand, India[J]. Journal of Earth System Science, 2008, 117: 121-132.

[ ] Wang L, Cheng Y, Wang L, et al. Safety line method for the prediction of deep coal-seam gas pressure and its application in coal mines[J]. Safety science, 2012, 50(3): 523-529.

[ ] Chen X, Li L, Yuan Y, et al. Effect and mechanism of geological structures on coal seam gas occurrence in Changping minefield[J]. Energy Science & Engineering, 2020, 8(1): 104-115.

[ ] Turton D J. Lawyers in Australia's coal seam gas debate: A study of participation in recorded community forums[J]. The Extractive Industries and Society, 2015, 2(4): 802-812.

[ ] 任培良, 刘彦伟, 韩红凯, 等. 冲煤率对煤层卸压增透及瓦斯抽采的影响规律研究[J].煤炭科学技术, 2022, 50(10): 102-109.

[ ] 李泉新, 许超, 刘建林, 等. 煤矿井下全域化瓦斯抽采定向钻进关键技术与工程实践[J]. 煤炭学报, 2022, 47(08): 3108-3116.

[ ] 谷旺鑫, 鲁义, 施式亮, 等. 基于瓦斯抽采效果的钻孔塑性区范围优化及应用[J]. 中国安全生产科学技术, 2021, 17(01): 25-30.

[ ] 王亮, 廖晓雪, 褚鹏, 等. 瓦斯抽采穿层钻孔钻扩造穴卸压增透机理研究[J]. 煤炭科学技术, 2021, 49(05): 75-82.

[ ] 刘东, 刘文. 水力冲孔压裂卸压增透抽采瓦斯技术研究[J]. 煤炭科学技术, 2019, 47(03): 136-141.

[ ] 龚晓燕, 陈有乐, 刘壮壮, 等. 综掘面风速瓦斯粉尘最优分布的风流智能调控优化评价模型[J]. 中国安全生产科学技术, 2023, 19(05): 65-72.

[ ] 赖文哲, 邵良杉. 基于博弈论偏序集的煤矿瓦斯爆炸风险评价模型研究[J]. 运筹与管理, 2023, 32(09): 136-142.

[ ] 张书金, 李绍泉, 李树清, 等. 基于层次分析法的煤矿瓦斯抽采技术成熟度评价[J]. 煤矿安全, 2013, 44(09): 169-172.

[ ] 肖鹏, 丁毅, 李树刚. 基于未确知测度的矿井瓦斯防治管理体系评价[J]. 中国安全科学学报, 2017, 27(01): 98-103.

[ ] Zhu J, Zhao Y, Hu Q, et al. Coalbed methane production model based on random for-ests optimized by a genetic algorithm[J]. ACS omega, 2022, 7(15): 13083-13094.

[ ] Feng Q, Zhang J, Zhang X, et al. Optimizing well placement in a coalbed methane res-ervoir using the particle swarm optimization algorithm[J]. International Journal of Coal Geology, 2012, 104: 34-45.

[ ] Wu C, Yuan C, Wen G, et al. A dynamic evaluation technique for assessing gas output from coal seams during commingling production within a coalbed methane well: a case study from the Qinshui Basin[J]. International Journal of Coal Science & Technology, 2020, 7: 122-132.

[ ] Coalbed methane: scientific, environmental and economic evaluation[M]. Springer Science & Business Media, 2013.

[ ] Carman E P, Caldwell D L. Research and Technologic Work on Coal and Related In-vestigations: 1954[M]. US Department of the Interior, Bureau of Mines, 1956.

[ ] Xia T, Zhou F, Liu J, et al. Evaluation of the pre-drained coal seam gas quality[J]. Fuel, 2014, 130: 296-305.

[ ] Jin K, Cheng Y, Wang W, et al. Evaluation of the remote lower protective seam mining for coal mine gas control: a typical case study from the Zhuxianzhuang Coal Mine, Huaibei Coalfield, China[J]. Journal of Natural Gas Science and Engineering, 2016, 33: 44-55.

[ ] Xue Y, Gao F, Gao Y, et al. Quantitative evaluation of stress-relief and permeability-increasing effects of overlying coal seams for coal mine methane drainage in Wulan coal mine[J]. Journal of Natural Gas Science and Engineering, 2016, 32: 122-137.

[ ] Ni X, Tan X, Yang S, et al. Evaluation of coal reservoir coalbed methane production potential in considering different coal structures in a coal seam section: a case study of the Shizhuang North Block in the Qinshui Basin[J]. Environmental Earth Sciences, 2021, 80: 1-10.

[ ] 李国富, 李贵红, 刘刚. 晋城矿区典型区煤层气地面抽采效果分析[J]. 煤炭学报, 2014, 39(09): 1932-1937.

[ ] 罗新荣, 俞启香. 矿井瓦斯预测与评价[J]. 中国安全科学学报, 1994, 4(3): 45-52.

[ ] 邓敢博, 邹云龙. 瓦斯抽采达标在线评价系统建设及应用[J]. 煤炭技术, 2016, 35(05): 201-202.

[ ] 梁冰, 秦冰, 孙福玉, 等. 煤与瓦斯共采评价指标体系及评价模型的应用[J]. 煤炭学报, 2015, 40(04): 728-735.

[ ] 邓海洲. 矿井安全生产模糊综合评判系统的研究[D]. 徐州: 中国矿业大学, 2008.

[ ] 张书金, 李绍泉, 李树清, 等. 基于层次分析法的煤矿瓦斯抽采技术成熟度评价[J]. 煤矿安全, 2013, 44(09): 169-172.

[ ] 陈国红, 孟贤正, 黄旭超, 等. 模糊综合评判确定煤与瓦斯突出预测敏感指标[J]. 煤矿安全, 2010, 41(08): 27-29.

[ ] 王彦波, 谢贤平, 李锦峰, 等. 基于 FAHP 的煤矿瓦斯治理综合评价研究[J]. 中国安全生产科学技术, 2012, 8(11): 101-106.

[ ] 李树刚, 程皓, 潘红宇, 等. 崔家沟煤矿采空区瓦斯抽采效果评价模型[J]. 西安科技大学学报, 2020, 40(01): 11-17+87.

[ ] 李云. 层次分析法在顺层钻孔抽采效果评价中的应用[J]. 矿业安全与环保, 2015, 42(06): 57-61.

[ ] 闫乐林, 徐精彩, 许满贵, 等. 未确知数学在煤矿安全预评价中的应用[J]. 矿业安全与环保, 2004(02): 24-26+1.

[ ] 许满贵. 煤矿动态综合安全评价模式及应用研究[D]. 西安: 西安科技大学, 2006.

[ ] 念其锋, 施式亮, 李润求, 等. 基于 PNN 的煤矿安全生产风险综合预警研究[J]. 中国安全生产科学技术, 2013, 9(10): 71-77.

[ ] Zhu C, Miao X, Liu Z. Mechanical analysis on deformation of surrounding rock with road-in packing of gob-side entry retaining in fully-mechanized sub-level caving face[J]. Journal of Coal Science and Engineering (China), 2008, 14(1): 24-28.

[ ] 朱川曲. 基于神经网络的综采工作面人-机-环境系统的可靠性研究[J]. 煤炭学报, 2000(03): 268-272.

[ ] 朱川曲. 采煤工作面瓦斯涌出量预测的神经网络模型 [J]. 中国安全科学学报, 1999(02): 45-48.

[ ] Guo J, Zhang Z, Guo G, et al. Evaluation of Coalbed Methane Content by Using Ker-nel Extreme Learning Machine and Geophysical Logging Data[J]. Geofluids, 2022, 2022.

[ ] 顾伟红, 赵雪. 基于GRA-SSA-Elman的隧道施工瓦斯安全性预测评价[J]. 自然灾害学报, 2023, 32(06): 230-239.

[ ] 史洪恺, 祁云, 张国恩, 等. 组合赋权-灰色聚类的煤与瓦斯突出危险评价[J]. 中国安全科学学报, 2023, 33(S1): 52-57.

[ ] 刘俊娥, 曾凡雷, 郭章林. 基于RS-SVM模型的煤与瓦斯突出多因素风险评价[J]. 中国安全科学学报, 2011, 21(07): 21-26.

[ ] Song H, Du S, Yang J, et al. Evaluation of hydraulic fracturing effect on coalbed me-thane reservoir based on deep learning method considering physical constraints[J]. Journal of Petroleum Science and Engineering, 2022, 212: 110360.

[ ] Zhong R, Johnson Jr R L, Chen Z. Using machine learning methods to identify coal pay zones from drilling and logging-while-drilling (LWD) data[J]. SPE Journal, 2020, 25(03): 1241-1258.

[ ] Forster C, Smith L. Groundwater flow systems in mountainous terrain: 1. Numerical modeling technique[J]. Water Resources Research, 1988, 24(7): 999-1010.

[ ] Zhou-xiang D. Mechanical fundamentals of seepage force concept and its generaliza-tion[J]. Chinese Journal of Geotechnical Engineering, 2017, 39(11): 2088-2101.

[ ] 陶云奇. 含瓦斯煤THM耦合模型及煤与瓦斯突出模拟研究[D]. 重庆: 重庆大学, 2009.

[ ] Liu J, Elsworth D. Evaluation of pore water pressure fluctuation around an advancing long wall panel[J]. Advances In Water Resources, 1999, 22 (6): 633-644.

[ ] Liu J, Chen Z, Elsworth D, Qu H, Chen D. Interactions of multiple processes during CBM extraction: A critical review[J]. International Journal of Coal Geology, 2011, 87: 175-189.

[ ] 夏同强. 瓦斯与煤自燃多场耦合致灾机理研究[D]. 徐州: 中国矿业大学, 2015.

[ ] 张学博, 王文元, 沈帅帅. 钻孔变形失稳条件下抽采负压及流量分布规律试验研究[J].煤炭科学技术, 2020, 48(10): 45-51.

[ ] 徐超, 王建文, 杜昌昂, 等. 瓦斯抽采长钻孔负压沿孔长衰减机制及影响因素模拟研究[J]. 采矿与安全工程学报, 2021, 38(02): 419-428.

[ ] 汪皓. 突出煤层定向钻进随钻瓦斯参数动态反演及消突效果评价研究[D]. 徐州: 中国矿业大学, 2020.

[ ] Zhou L, Zhou X, Fan C, et al. Coal permeability evolution triggered by variable injec-tion parameters during gas mixture enhanced methane recovery[J]. Energy, 2022, 252: 124065.

[ ]孙培德. 煤层瓦斯动力学的基本模型[J]. 西安矿业学院学报, 1989(02): 7-13.

[ ] 闫斌移. 突出煤层瓦斯抽放及消突效果考察[J]. 煤矿安全, 2010 (10): 18-19.

[ ] Bowers B, Schatzman L. Dimensional analysis[M]//Developing grounded theory. Routle-dge, 2016: 86-126.

[ ] 闫鹏, 方秦, 张锦华, 等. 不同典型形状落石冲击砂垫层试验与量纲分析[J]. 爆炸与冲击, 2021, 41(7): 073303-1-073303-16.

[ ] 周世宁, 林柏泉. 煤层瓦斯赋存与流动理论[M]. 北京: 煤炭工业出版社, 1999: 58-65.

[ ] 田静萱, 夏僮, 杨振宇, 等. 基于纳米压痕试验的塑性本构参数反演方法研究[J]. 固体力学学报, 2023, 44(5): 606-621.

[ ] 张新建, 王硕, 张双全, 等. 大采高长工作面三级瓦斯抽采模式研究[J]. 煤炭科学技术, 2013, 41(6): 62-64.

[ ] 赵嵘, 齐黎明. 井下直接法测定煤层瓦斯压力研究现状及分析[J]. 煤炭技术, 2017, 36(3): 202-203.

[ ] LeCun Y, Bengio Y, Hinton G. Deep learning[J]. nature, 2015, 521(7553): 436-444.

[ ] Rosenblatt F. The perceptron: a probabilistic model for information storage and organ-ization in the brain[J]. Psychological review, 1958, 65(6): 386.

[ ] Gurney K. An introduction to neural networks[M]. CRC press, 2018.

[ ] Li Z, Liu F, Yang W, et al. A survey of convolutional neural networks: analysis, appli-cations, and prospects[J]. IEEE transactions on neural networks and learning systems, 2021, 33(12): 6999-7019.

[ ] Salehinejad H, Sankar S, Barfett J, et al. Recent advances in recurrent neural net-works[J]. arXiv preprint arXiv:1801.01078, 2017.

[ ] Banerjee C, Mukherjee T, Pasiliao Jr E. An empirical study on generalizations of the ReLU activation function[C]//Proceedings of the 2019 ACM Southeast Conference. 2019: 164-167.

[ ] Li X, Hu Z, Huang X. Combine ReLU with tanh[C]//2020 IEEE 4th Information Tech-no-logy, Networking, Electronic and Automation Control Conference (ITNEC). IEEE, 2020, 1: 51-55.

[ ] Lillicrap T P, Santoro A, Marris L, et al. Backpropagation and the brain[J]. Nature Re-views Neuroscience, 2020, 21(6): 335-346.

[ ] Sherstinsky A. Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network[J]. Physica D: Nonlinear Phenomena, 2020, 404: 132306.

[ ] Li S, Li W, Cook C, et al. Independently recurrent neural network (indrnn): Building a longer and deeper rnn[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 5457-5466.

[ ] Yu Y, Si X, Hu C, et al. A review of recurrent neural networks: LSTM cells and network architectures[J]. Neural computation, 2019, 31(7): 1235-1270.

[ ] Hochreiter S, Schmidhuber J. Long short-term memory[J]. Neural computation, 1997, 9(8): 1735-1780.

[ ] Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[J]. Advances in neural information processing systems, 2017, 30.

[ ] Subakan C, Ravanelli M, Cornell S, et al. Attention is all you need in speech separation [C]//ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Sig-nal Processing (ICASSP). IEEE, 2021: 21-25.

[ ] He K, Zhang X, Ren S, et al. Deep residual learning for image recogni-tion[C]//Proceed-ings of the IEEE conference on computer vision and pattern recogni-tion. 2016: 770-778.

[ ] Gal Y, Ghahramani Z. Dropout as a bayesian approximation: Representing model un-cert-ainty in deep learning[C]//international conference on machine learning. PMLR, 2016: 1050-1059.

[ ] Chung Y A, Hsu W N, Tang H, et al. An unsupervised autoregressive model for speech representation learning[J]. arXiv preprint arXiv:1904.03240, 2019.

[ ] Bos R, De Waele S, Broersen P M T. Autoregressive spectral estimation by application of the Burg algorithm to irregularly sampled data[J]. IEEE Transactions on Instrumenta-tion and Measurement, 2002, 51(6): 1289-1294.

[ ] Cavanaugh J E, Neath A A. The Akaike information criterion: Background, derivation, properties, application, interpretation, and refinements[J]. Wiley Interdisciplinary Re-views: Computational Statistics, 2019, 11(3): e1460.

[ ] Pan Q, Zhang L, Dai G, et al. Two denoising methods by wavelet transform[J]. IEEE transactions on signal processing, 1999, 47(12): 3401-3406.

[ ] 孙东玲, 梁运培, 黄旭超, 等. 新疆大倾角多煤组煤矿区煤层气开发利用进展与前景[J]. 煤炭科学技术, 2023, 51(S1): 162-172.

[ ] 马莉, 石新莉, 李树刚, 等. 基于MPC的瓦斯抽采智能调控模型研究[J]. Coal Sci-ence & Technology (0253-2336), 2022, 50(8).

[ ] Dar T, Rai N, Bhat A. Delineation of potential groundwater recharge zones using ana-lytical hierarchy process (AHP)[J]. Geology, Ecology, and Landscapes, 2021, 5(4): 292-307.

[ ] Yu Y, Zeng J, Zhong L, Gao M, Wen J, Wu Y. Multi-views contrastive learning for dense text retrieval[J]. Knowledge-Based Systems, 2023, 274: 110624.