大坝变形变系数回归建模  

Modeling Dam Deformation Using Varying Coefficient Regression

作　　者：卢骏[1,2,3] 戴吾蛟[1,2] 章浙涛 

机构地区：[1]中南大学测绘与国土信息工程系,湖南长沙410083 [2]湖南省精密工程测量与形变灾害监测重点实验室,湖南长沙410083 [3]湖南地科资源利用工程设计有限公司,湖南长沙410007

出　　处：《武汉大学学报（信息科学版）》2015年第1期139-142,共4页Geomatics and Information Science of Wuhan University

基　　金：国家自然科学基金资助项目(41074004);国家973计划资助项目(2013CB733303)~~

摘　　要：在变形分析建模中常采用回归分析建模,但普通的回归模型是一种静态的模型,当变形体结构或物理性质发生变化时,普通线性回归所建立的静态模型将不再适用。变系数回归模型是一种动态模型,有着更强的灵活性和适应性,因此,将变系数回归引入大坝变形分析建模中,采用局部线性估计的方法进行系数拟合。仿真和大坝变形建模实验表明,变系数回归得到的大坝变形模型优于普通的线性回归模型,预测精度更高。Regression analysis is often used in deformation analysis modeling, however, it is a static model. When the structure or physical properties of the monitoring object change, the static model will no longer be applicable. However, a varying coefficient regression model is a dynamic model and has greater flexibility and adaptability. So varying coefficient regression is introduced into dam deformation analysis. Local linear estimation is used to fit the varying coefficients. Both a simulation experiment and a real dam deformation monitoring data experiment show that a dam deformation model using varying coefficient regression is better than that using ordinary linear regression; and more precise when predicting deformation.

关 键 词：变系数回归模型 局部线性估计 回归分析 变形建模 

分 类 号：P258[天文地球—测绘科学与技术] TU196[建筑科学—建筑理论]