引入模型误差的非线性回归模型  

The Nonlinear Regression Model Introduced by Model Error

作　　者：邢诚[1] 王建强[1] 贾志强[2] 

机构地区：[1]武汉大学测绘学院,湖北武汉430079 [2]天津市勘察院,天津300191

出　　处：《海洋测绘》2009年第3期1-3,共3页Hydrographic Surveying and Charting

摘　　要：在第一类非线性回归模型中,经常出现病态问题,它严重影响计算结果的精度。提出了一种引入模型误差求解部分参数的方法,这种方法可以改变病态性质,提高对部分参数的求解精度。通过算例来检验这种方法的可行性并探讨它的使用范围。Ill-conditioned problems widely exist in the first class nonlinear regression model and seriously affect the accuracy of results. In order to change pathological problems, a new method is presented by solving some of the parameters with the introduction to the function model error. The solution enhances the accuracy of parameters, and the feasibility of this method is tested by using an example.

关 键 词：测量平差 病态问题 非线性回归 法方程 

分 类 号：P207[天文地球—测绘科学与技术]