叶娟,涂树杰,刘晓明,鄢鹏宇

• 1:海口市设计集团有限公司
• 2:湖南大学土木工程学院

摘要(Abstract)：

低雷诺数下岩石光滑裂隙渗流流量可用立方定律描述，而气孔构造岩石裂隙的渗透特性与之不同，需进一步研究。为此，首先开展了气孔构造裂隙渗透试验，获得了气孔构造单裂隙渗流流量与不同水力坡降、等效水力缝宽、气孔最大深度、气孔等效直径、气孔面积占比5个因素共382组试验数据；然后分别采用传统的回归分析和新出现的机器学习算法对试验数据进行分析，研究气孔构造岩石裂隙渗流量预测方法，通过回归分析，得到气孔构造裂隙渗流量预测公式；最后基于机器学习中的随机森林算法，建立了气孔构造岩石裂隙渗流流量预测模型，并分析了影响气孔构造岩石裂隙渗流量的各因素的重要性。结果表明：影响气孔构造岩石裂隙渗流流量的主要因素为水力坡降和等效水力缝宽，其他影响因素的重要性之和小于15%;回归所得流量预测公式形式简洁，抓住了主要影响因素，但其拟合优度不是很高(R~2=0.90),这是因为回归分析会忽略其中的次要影响因素；随机森林预测模型包含次要因素的影响，预测效果(R~2=0.97)显著优于回归预测公式，在预测复杂裂隙构造渗流量预测方面更有优势。

关键词(KeyWords)： 气孔构造玄武岩;裂隙渗流;流量预测公式;随机森林(RF)算法

Abstract:

Keywords:

基金项目(Foundation): 国家重点研发计划(2019YFC1904700)

作者(Author): 叶娟,涂树杰,刘晓明,鄢鹏宇

DOI: 10.13928/j.cnki.wrahe.2022.06.014

参考文献(References)：

• [1] LOMIZE G M.Flow in fractured rocks.[M] Moscow:Gosenergoizdat,1951.
• [2] 速宝玉，詹美礼，赵坚.光滑裂隙水流模型实验及其机理初探[J].水利学报，1994(5):19-24.SU Baoyu,ZHAN Meili,ZHAO Jian.Model experiment of water flow in smooth fissures and its mechanism[J].Journal of Hydraulic Engineering,1994(5):19-24.
• [3] TAN R,CHAI J,CAO C.Experimental investigation of the permeability measurement of radial flow through a single rough fracture under shearing action[J].Advances in Civil Engineering,2019 (7):1-13.
• [4] 刘日成，李博，蒋宇静，等.效水力隙宽和水力梯度对岩体裂隙网络非线性渗流特性的影响[J].岩土力学，2016,37(11):3165-3174.LIU Richeng,LI Bo,JIANG Yujing.The effect of equivalent hydraulic gap width and hydraulic gradient on the nonlinear seepage characteristics of rock mass fracture network[J].Rock and Soil Mechanics,2016,37(11):3165-3174.
• [5] 熊峰，孙昊，姜清辉.粗糙岩石裂隙低速非线性渗流模型及试验验证[J].岩土力学，2018,39(9):3294-3302.XIONG Feng,SUN Hao,JIANG Qinghui.Low-speed non-linear seepage model and experimental verification in rough rock fractures[J].Rock and Soil Mechanics,2018,39(9):3294-3302.
• [6] ZHANG X,CHAI J,QIN Y,et al.Experimental study on seepage and stress of single-fracture radiation flow[J].KSCE Journal of Civil Engineering,2019,233:1132-1140.
• [7] MATTER J M,KELEMEN P B.Permanent storage of carbon dioxide in geological reservoirs by mineral carbonation[J].Nature Geoscience,2009,2(12):837-841.
• [8] LAMUR A,KENDRICK J E,EGGERTSSON G H,et al.The permeability of fractured rocks in pressurised volcanic and geothermal systems[J].Scientific Reports,2017,71:1-9.
• [9] 刘晓明，杨本亮，申琦瑜.气孔构造岩石裂隙渗透特性研究[J].长江科学院院报，2021,38(4):81-87.LIU Xiaoming,YANG Benliang,SHEN Qiyu.Study on the permeability characteristics of rock fractures in stomata structure[J].Journal of Yangtze River Scientific Research Institute,2021,38(4):81-87.
• [10] BREIMAN L.Random forests[J].Machine Learning,2001,451:5-32.
• [11] 朱梦琦，朱合华，王昕.基于集成CART算法的TBM掘进参数与围岩等级预测[J].岩石力学与工程学报，2020,39(9):1860-1871.ZHU Mengqi,ZHU Hehua,WANG Xin.TBM tunnelling parameters and surrounding rock grade prediction based on integrated CART algorithm[J].Chinese Journal of Rock Mechanics and Engineering,2020,39(9):1860-1871.
• [12] 翁剑成，孙宇星，孔宁.基于多源数据的公交专用道效能评价方法与影响模型[J].中国公路学报，2022,35(4):267-276.WENG Jiancheng,SUN Yuxing,KONG Ning.Bus lane effectiveness evaluation method and impact model based on multi-source data[J].Journal of Highway and Transport,2022,35(4):267-276.
• [13] 林威伟，钟登华，胡炜.基于随机森林算法的土石坝压实质量动态评价研究[J].水利学报，2018,49(8):945-955.LIN Weiwei,ZHONG Denghua,HU Wei.Research on dynamic evaluation of compaction quality of earth-rock dams based on random forest algorithm[J].Journal of Hydraulic Engineering,2018,49(8):945-955.
• [14] TSANG Y W,TSANG C F,NERETNIEKS I,et al.Flow and tracer transport in fractured media:A variable aperture channel model and its properties[J].Water Resources Research,1988,24(12):2049-2060.
• [15] 王媛，速宝玉.单裂隙面渗流特性及等效水力隙宽[J].水科学进展，2002,13(1):61-68.WANG Yuan,SU Baoyu.Single fracture surface seepage characteristics and equivalent hydraulic gap width[J].Advances in Water Science,2002,13(1):61-68.
• [16] 程维虎.拟合优度检验的回归分析方法及其应用[J].北京工业大学学报，2000(2):79-84.CHENG Weihu.The regression analysis method of goodness of fit test and its application [J].Journal of Beijing University of Technology,2000(2)2:79-84.
• [17] YEO I W,DE FREITAS M H,ZIMMERMAN R W.Effect of shear displacement on the aperture and permeability of a rock fracture[J].International Journal of Rock Mechanics and Mining Sciences,1998,35(8):1051-1070.
• [18] ABELLáN J,MANTAS C J,CASTELLANO J G.A random forest approach using imprecise probabilities[J].Knowledge-Based Systems,2017,13(4):72-84.
• [19] 周志华.机器学习[M].北京：清华大学出版社，2017.ZHOU Zhihua.Machine learning [M].Beijing:Tsinghua University Press,2017.
• [20] 曹正凤.随机森林算法优化研究[D].北京：首都经济贸易大学，2014.CAO Zhengfeng.Research on Random Forest Algorithm Optimization [D].Beijing:Capital University of Economics and Business,2014.