摘要
颗粒级配、孔隙比是决定粗粒土渗透系数的关键因素。收集并整理得到93组粗粒土全级配(d_(10)~d_(100))、孔隙比数据,采用遗传算法(genetic algorithm,GA)优化的BP(back propagation)神经网络分析和预测粗粒土渗透系数,通过平均影响值法和试验验证,评价各级配粒径对渗透系数的影响大小,探讨孔隙比对粗粒土渗透系数的影响。结果表明:d_(50)为界限粒径,在其他粒径不变,若增大d_(50)及以下粒径,渗透系数就增大,而增大d_(50)以上粒径,渗透系数减小; d_(50)及以下粒径的"细颗粒"对渗透系数的影响大于d_(50)以上粒径的"粗颗粒";按相对权重,d_(20)、d_(80)、d_(40)属于高敏感度粒径,d_(10)、d_(50)、d_(100)、d_(70)为中敏感度粒径,d_(30)、d_(90)、d_(60)为低敏感度粒径。孔隙比对渗透系数的影响大于任一特征粒径,渗透系数与孔隙比呈正相关关系;相同颗粒级配的粗粒土,随孔隙比变化可使渗透系数产生数量级跨越。采用GA-BP神经网络方法,由全级配和孔隙比能较好地预测粗粒土渗透系数。
Grain grade and void ratio are the crucial factors affecting the coefficient of permeability for coarsegrained soil.In this paper,93 sample data of full grain grades(d10~d100)and void ratio are collected to analyze and predict the coefficient of permeability by applying the BP neural network optimized by genetic algorithm.By means of the mean impact value(MIV)method and verification test,the influential extents of each grain size and void ratio on the coefficient of permeability are evaluated and discussed.The results reveal that d50 is the critical particle size of coarse-grained soil,indicating that if the others grain sizes keep constant,the coefficient of permeability will increase with the increasing grain size below d50 and decreasing grain sizes over d50.The influential extent of the fine particles smaller than d50 is much more than these coarse particles bigger than d50.According to the relative influential weights,d20,d80,d40 belong to the high-sensitivity grain sizes,d10,d50,d100,and d70 are medium-sensitivity grain sizes,and d30,d90,and d60 are low-sensitivity grain sizes.Moreover,the effect of void ratio on the coefficient of permeability is greater than that of each grain size,and the coefficient of permeability is positively correlated with the void ratio.As for the coarse-grained soils with the same grain size,the variation in void ratio will result in the change in the coefficient of permeability by order of magnitude.It is concluded that the coefficient of permeability of coarse-grained soil can be well predicted by applying the GA-BP Neural Network taking full grain grades and void ratio into account.
作者
丁瑜
饶云康
倪强
许文年
刘大翔
张恒
DING Yu;RAO Yunkang;NI Qiang;XU Wennian;LIU Daxiang;ZHANG Heng(Key Laboratory of Geological Hazards on Three Gorges Reservoir Area(China Three Gorges University),Ministry of Education,Yichang,Hubei 443002,China;Key Laboratory of Disaster Prevention and Mitigation,Hubei Province,China Three Gorges University,Yichang,Hubei 443002,China;Collaborative Innovation Center for Geo-hazards and Eco-Environment in Three Gorges Area,Hubei Province,Yichang,Hubei 443002,China;Jiaxing Planning&Research Institute Co.,Ltd,Jiaxing,Zhejiang 314050,China)
出处
《水文地质工程地质》
CAS
CSCD
北大核心
2019年第3期108-116,共9页
Hydrogeology & Engineering Geology
基金
国家重点研发计划资助(2017YFC0504902-05)
国家自然科学基金项目资助(51678348
51708333)
湖北省自然科学基金重点实验室项目资助(2016CFA085)
关键词
粗粒土
渗透系数
孔隙比
颗粒级配
GA-BP神经网络
coarse-grained soil
coefficient of permeability
void ratio
gradation
GA-BP neural network