基于改进M5'-主成分模型树的高心墙堆石坝沉降变形预测  

Forecasting of the settlement deformation for high core rock-fill dam based on the improved M5'-PCR model tree

作　　者：王飞[1] 张宗亮[1] 王佳俊[1] 佟大威[1] 任炳昱[1] WANG Fei;ZHANG Zongliang;WANG Jiajun;TONG Dawei;REN Bingyu(State Key Laboratory of Hydraulic Engineering Simulation and Safety,Tianjin University,Tianjin 300072,China)

机构地区：[1]天津大学水利工程仿真与安全国家重点实验室,天津300072

出　　处：《河海大学学报（自然科学版）》2018年第4期353-359,共7页Journal of Hohai University(Natural Sciences)

基　　金：国家自然科学基金创新群体基金(51621092);国家自然科学基金(51339003);国家重点基础研究发展计划(973计划)(2013CB035906)

摘　　要：针对高心墙堆石坝沉降变形过程动态非线性特点,建立基于改进M5'-主成分模型树的高心墙堆石坝沉降变形分析模型,在采用相关性分析甄选沉降变形影响因素和采用主成分分析将高维影响因素空间进行降维的基础上,利用该全局分段非线性模型对高心墙堆石坝沉降过程进行分析。通过与沉降量实测值对比,验证了改进M5'-主成分模型树的有效性。通过绝对差值和均方根误差2个指标对比分析改进M5'-主成分模型树与M5'模型树、多元线性回归模型、主成分回归分析模型的预测结果,表明改进M5'-主成分模型树预测沉降量具有更高的精度。Considering the nonlinear and dynamic characteristics of settlement deformation,a global piecewise nonlinear analysis model of settlement deformation is proposed based on the modified M5'-principal component(M5'-PCR)model tree,to analyze the settlement process by selecting the influence factors with correlation analysis and reducing the dimension of high dimensional influence factors with principal component analysis method.The the improved M5'-PCR model tree is verified by comparing with the measured settlement.By comparing the prediction results of improved M5'-PCR model tree,M5'model tree,multiple linear regression,and principal component regression analysis model through the absolute difference and the root mean square error,the results show that improved M5'-PCR model tree has a higher precision in settlement prediction and provides a new approach for the analysis of dam settlement deformation.

关 键 词：心墙堆石坝 沉降预测 M5'模型树 相关性分析 主成分回归分析 

分 类 号：TV641.41[水利工程—水利水电工程]