当误差含变量(EIV)模型的设计矩阵病态时,采用普通整体最小二乘(TLS)算法得不到稳定的数值解.为了减弱病态性,在整体最小二乘准则的基础上附加解的二次范数约束,组成拉格朗日目标函数,推导EIV模型的正则化整体最小二乘解(RTLS).然后将RTLS的求解转换为矩阵特征向量问题,设计一个迭代方案逼近RTLS解.通过L曲线法求得正则化因子来确定正常数,从而避免人为选择正常数的随意性.数值实例表明,提出的迭代正则化算法是有效可行的.
参考文献
| [1] | Schaffrin B.A note on constrained total least-squares estimation[J].Linear Algebra and its Applications,20061(1):245-258. |
| [2] | Schaffrin, B;Felus, YA.An algorithmic approach to the total least-squares problem with linear and quadratic constraints[J].Studia Geophysica et Geodaetica,20091(1):1-16. |
| [3] | Songlin Zhang;Xiaohua Tong;Kun Zhang.A solution to EIV model with inequality constraints and its geodetic applications[J].Journal of geodesy,20131(1):23-28. |
| [4] | 周拥军;邓才华.线性EIV模型的TLS估计及其典型应用[J].中国有色金属学报,2012(3):948-953. |
| [5] | 王乐洋.总体最小二乘解性质研究[J].大地测量与地球动力学,2012(05):48-52,57. |
| [6] | Burkhard Schaffrin;Kyle Snow.Total Least-Squares regularization of Tykhonov type and an ancient racetrack in Corinth[J].Linear Algebra and its Applications,20108(8):2061-2076. |
| [7] | Beck A;Ben-Tal A.On the solution of the Tikhonov regularization of the total least squares problem[J].SIAM Journal on Optimization: A Publication of the Society for Industrial and Applied Mathematics,20061(1):98-118. |
| [8] | 袁振超;沈云中;周泽波.病态总体最小二乘模型的正则化算法[J].大地测量与地球动力学,2009(2):131-134. |
| [9] | 王乐洋;许才军;鲁铁定.病态加权总体最小二乘平差的岭估计解法[J].武汉大学学报（信息科学版）,2010(11):1346-1350. |
| [10] | 王乐洋;于冬冬.病态总体最小二乘问题的虚拟观测解法[J].测绘学报,2014(6):575-581. |
| [11] | 葛旭明;伍吉仓.病态总体最小二乘问题的广义正则化[J].测绘学报,2012(3):372-377. |
| [12] | 葛旭明;伍吉仓.误差限的病态总体最小二乘解算[J].测绘学报,2013(2):196-202. |
上一张
下一张
上一张
下一张
计量
- 下载量()
- 访问量()
文章评分
- 您的评分：
-
10%
-
20%
-
30%
-
40%
-
50%