基于LHS-ISSA-SVR的心墙堆石坝渗流参数反演方法及应用  

Inversion Method of Seepage Parameters of Core Rockfill Dam Based on LHS-ISSA-SVR and Its Application

作　　者：李永超 沈振中[1,2] 熊汉野 李皓璇 张宏伟 LI Yong-chao;SHEN Zhen-zhong;XIONG Han-ye;LI Hao-xuan;ZHANG Hong-wei(College of Water Conservancy and Hydropower Engineering,Hohai University,Nanjing 210098,China;State Key Laboratory of Hydrology-Water Resources and Hydraulic Engineering,Hohai University,Nanjing 210098,China)

机构地区：[1]河海大学水利水电学院,江苏南京210098 [2]河海大学水文水资源与水利工程科学国家重点实验室,江苏南京210098

出　　处：《水电能源科学》2024年第7期109-113,共5页Water Resources and Power

基　　金：国家自然科学基金项目(52179130);江苏高校优势学科建设工程资助项目(水利工程)(YS11001)。

摘　　要：高效合理地确定大坝的渗流参数是科学分析大坝渗流性态的关键。针对心墙堆石坝复杂多渗流参数反演问题,提出了一种基于LHS-ISSA-SVR组合代理模型的心墙堆石坝渗流参数反演新方法。基于饱和—非饱和渗流理论,建立了心墙堆石坝渗流有限元模型,采用拉丁超立方抽样(LHS)获取均匀性更优的渗透系数组合样本集,并代入有限元模型模拟监测点水头,通过支持向量回归机(SVR)准确建立监测点水头与材料渗流参数的映射关系。融合佳点集、莱维飞行与柯西反向学习策略改进麻雀搜索算法(SSA),基于改进的麻雀搜索算法实现了SVR模型参数的优化调整和渗流参数的智能反演。工程实例应用表明,各监测点渗压水头反演值与实测值相对误差均在2.5%内,心墙堆石坝渗流场位势分布规律合理,渗流参数反演结果准确可靠。该方法为准确反演长期服役的心墙堆石坝渗流参数提供了新途径。Efficiently and reasonably determining the seepage parameters of dams is the key basis for scientifically analyzing the seepage behaviors of dams.In order to address the complex multiple seepage parameters inversion problem of core rockfill dams,this paper proposed a novel method for seepage parameters inversion in core rockfill dams based on the LHS-ISSA-SVR fusion surrogate model.Based on the saturated-unsaturated seepage theory,a finite element seepage model of a core rockfill dam was established.The Latin Hypercube Sampling method was used to obtain the permeability coefficients combination samples with better homogeneity,which is substituted into the finite element model to simulate the water head at the monitoring points.The mapping relationship between the water head and permeability coefficients was accurately constructed by Support Vector Regression(SVR).The Sparrow Search Algorithm(SSA)was effectively improved by fusing the Good Point Set,Levy Flight and Cauchy Inverse Learning Strategies.Both the optimization of SVR model parameters and the intelligent inversion of seepage parameters were carried out based on the improved sparrow search algorithm.The application of engineering examples shows that the relative error between the inversion value and the measured value of water head at each monitoring point is within 2.5%,and the potential distribution law of seepage field in the core rockfill dam is reasonable,indicating the accuracy and reliability of the inversion results for seepage parameters.This method provides a new way to accurately invert seepage parameters of core rockfill dams in long-term service.

关 键 词：心墙堆石坝 渗流参数 反演分析 改进麻雀搜索算法 支持向量回归机 

分 类 号：TV223.4[水利工程—水工结构工程]