为了准确确定工程区各地层渗透系数,基于相关向量机(RVM)与布谷鸟算法(CS)建立反演分析模型,对研究区域内各地层的渗透系数进行反演分析。首先,基于均匀设计法构造渗透系数组合,利用有限元计算测点水位值并生成RVM学习样本;随后,通过训练RVM构建渗透系数与水头之间的映射关系,使其能够代替有限元方法快速地完成渗流计算;最后,根据工程区钻孔的实测水位值,利用CS算法搜索确定区域内各地层的渗透系数。将建立的渗流反演模型应用于某大型抽水蓄能电站工程区的初始渗流场中,结果表明:所建立的渗流反演模型能够考虑多地层渗透系数和钻孔水头间的非线性,RVM能代替有限元模型,可快速、精确地确定渗透系数;此渗流反演模型在大型抽水蓄能电站工程区反演结果合理,精度满足工程要求。
Abstract
An inversion analysis model integrating relevance vector machine (RVM) and cuckoo search (CS) is established to accurately determine the permeability coefficients of strata in engineering area. Firstly, the uniform design method is employed to construct combinations of permeability coefficients, and the finite element method is used to calculate the water head values and generate RVM learning samples. In subsequence, the mapping relation between permeability coefficient and water head is constructed by RVM training which replaces the finite element method in calculating seepage. According to the measured water head values of drilling holes in the project area, the CS algorithm is adopted to search and determine the permeability coefficient of stratum. The seepage inversion model is applied to the inversion of initial seepage field of a large pumped storage power station project. Results demonstrate that the proposed model reflects the nonlinear relation between water head in borehole and permeability coefficient of multiple strata. RVM could replace the finite element method to determine quickly and accurately the permeability coefficient. The inversion results for the large pumped storage power station are reasonable and the accuracy of the proposed model meets engineering requirements.
关键词
渗透系数 /
反演分析 /
相关向量机 /
布谷鸟算法 /
均匀设计法
Key words
permeability coefficient /
inversion analysis /
relevance vector machine /
cuckoo search /
uniform design method
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 陈益峰,周创兵,李典庆,等.大型水电工程渗流分析的若干关键问题研究[J].岩土工程学报,2010,28(9): 1448-1454.
[2] 王洪波,张庆松,刘人太,等.渗透系数反演的CHNN模型方法[J].raybet体育在线
院报,2001,18(3):25-28.
[3] 郭海庆,吴中如,张乾飞.基于压水试验的地层渗流场反分析[J].岩土力学,2018,39(3):985-992.
[4] 刘先珊,周创兵,张立君.基于模拟退火的Gauss-Newton算法的神经网络在渗流反分析中的应用[J].岩土力学,2005,26(3):404-408,414.
[5] 何 翔,李守巨,刘迎曦,等.基于遗传神经网络的坝基岩体渗透系数识别[J].岩石力学与工程学报,2004,23(5):751-751.
[6] 李 萍.改进的Hopfield神经网络在配送车辆调度中的应用研究[D].阜新:辽宁工程技术大学,2008.
[7] 王复明,苗 丽,郭雪莽.基于流固耦合的大坝渗流特性反演方法研究[J].水力发电学报,2008(2):60-64.
[8] 陈海洋,滕彦国,王金生.基于GA-SVR的渗透系数参数反演方法[J].水文地质工程地质,2011,38(2):14-18.
[9] 倪沙沙,迟世春.基于粒子群支持向量机的高心墙堆石坝渗透系数反演[J].岩土工程学报,2017,39(4):727-734.
[10]杨 杰,马春辉,向 衍,等.基于相关向量机与随机有限元的筑坝材料参数不确定性反分析[J].中国科学:技术科学,2018,48(10):87-95.
[11]TIPPING M E. Sparse Bayesian Learning and the Relevance Vector Machine[J]. Journal of Machine Learning Research, 2001, 1: 211-244.
[12]MACKAY D J C. Mackay Bayesian Interpolation[J]. Neural Computation, 1992, 4(3): 415-447.
[13]郑志成,徐卫亚,徐 飞,等.基于混合核函数PSO-LSSVM的边坡变形预测[J].岩土力学,2012,33(5):1421-1426.
[14]YANG X S,DEB S.Cuckoo Search Via Levy Flight[C]//Proceedings of World Congress on Nature and Biologically Inspired Computing.USA:IEEE Publications,2009:210-214.
[15]YANG X S, DEB S. Engineering Optimisation by Cuckoo Search[J]. International Journal of Mathematical Modeling and Numerical Optimisation, 2010, 1(4): 330-343.
[16]兰少峰,刘 升.布谷鸟搜索算法研究综述[J].计算机工程与设计,2015(4):1063-1067.
[17]周 斌,刘斯宏,姜忠见,等.洪屏抽水蓄能电站渗控效果数值模拟与评价[J].水力发电学报,2015,34(5):131-139.
[18]张 巍, 肖 明.地下工程渗流断层数值模拟的隐式复合材料单元法研究[J].岩土工程学报,2005,27(10):1203-1206.
[19]方开泰.均匀设计与均匀设计表[M].北京:科学出版社,1994:69-97.
[20]梅松华,盛 谦,冯夏庭.均匀设计在岩土工程中的应用[J].岩石力学与工程学报,2004,23(16):2694-2694.
[21]XU Z G, LIU Y, HUANG J, et al. Performance Assessment of the Complex Seepage-Control System at the Lu Dila Hydropower Station in China[J]. International Journal of Geomechanics, 2019, 19(3): 05019001.
[22]孙超伟,柴军瑞,许增光,等.金川水电站地下厂房裂隙围岩渗控效应数值模拟与评价[J].岩土工程学报,2016,38(5):786-797.
[23]蒋海云,徐剑飞,刘斯宏,等.句容抽水蓄能电站渗控效果数值模拟与评价[J].三峡大学学报(自然科学版),2016,38(4):17-22.
[24]许增光,曹 成,李康宏,等.某抽水蓄能电站上水库局部防渗渗控分析[J].应用力学学报,2018,35(2):417-422.
基金
陕西省水利科技计划项目(2018SLKJ-5)
PDF(1524 KB)
