实参数与复参数混合域最小二乘平差方法

针对平差问题同时含有实数域参数和复数域参数的情形,提出了实参与复参混合的测量平差建模思路,并导出了相应的混合域最小二乘平差方法。该方法统一概括了实最小二乘和复最小二乘方法,其估计过程包括两步:基于零空间算子的实参数平差估计和复数平差模型的复参数估计。通过等价变换将实数域投影变换模型、直接线性变换模型分别重构为相应的混合域平差模型,有效降低法方程求逆维数,从而提高建模和平差计算效率。应用结果及分析验证了本文所提方法的正确性和有效性。     

On estimating gravity anomalies— A comparison of least squares collocation with conventional least squares techniques

The least squares collocation algorithm for estimating gravity anomalies from geodetic data is shown to be an application of the well known regression equations which provide the mean and covariance of a random vector (gravity anomalies) given a realization of a correlated random vector (geodetic data). It is also shown that the collocation solution for gravity anomalies is equivalent to the conventional least-squares-Stokes' function solution when the conventional solution utilizes properly weighted zero a priori estimates. The mathematical and physical assumptions underlying the least squares collocation estimator are described.     

地图数字化中基于点位坐标的统一平差模型

探讨了地图数字化过程中采用平差方法来建立坐标计算的统一模型。将测得的角度、边长等数据化为方向、距离观测值列立误差方程，通过调用统一的平差迭代计算程序来计算未知点坐标及精度。详细给出了基于平差的11种常用坐标计算方法，并通过实例进行了说明。     

基于中位参数初值的等价权抗差估计方法

等价权抗差估计法保留最小二乘估计处理正常观测值的优良特性,但其抗差性与初值关系极大,若用最小二乘估值作初值,必定会影响其抗差性.中位数法具有很好的抗差特性,但它只用部分观测数据计算参数估值,丢失大量有效信息.基于中位参数的抗差估计方法,在有限样本时,给出其崩溃污染率的估算方法.根据中位参数法和等价权抗差估计法的各自优点...     

Integral formulas for heterogeneous data in physical geodesy

The least squares estimator is derived for a random stochastic process implied by one or two heterogeneous random stochastic processes on a sphere. The solution can be regarded as least squares collocation in the continuous case. When the method is applied in physical geodesy the statistical expectation is usually substituted by the global average and the method will then give the minimum mean squares errors of the estimated quantities. The solutions can also be considered as generalizations of the classical integral formulas in physical geodesy for heterogeneous data information.     

An approach to response-based reliability analysis of quasi-linear Errors-in-Variables models

The paper presents an approach to internal reliability analysis of observation systems known as Errors-in-Variables (EIV) models with parameters estimated by the method of least squares. Such problems are routinely treated by total least squares adjustment, or orthogonal regression. To create a suitable environment for derivations in the analysis, a general nonlinear form of such EIV models is assumed, based on a traditional adjustment method of condition equations with unknowns, also known as the Gauss–Helmert model. However, in order to apply the method of reliability analysis based on the approach to response assessment in systems with correlated observations, presented in the earlier work of this author, it was necessary to confine the considerations to a quasi-linear form of the Gauss–Helmert model, representing quasi-linear EIV models. This made it possible to obtain a linear disturbance/response relationship needed in that approach. Several specific cases of quasi-linear EIV models are discussed. The derived formulas are consistent with those already functioning for standard least squares adjustment problems. The analysis shows that, as could be expected, the average level of response-based reliability for such EIV models under investigation is lower than that for the corresponding standard linear models. For EIV models with homoscedastic and uncorrelated observations, the relationship between the average reliability indices for the independent and the dependent variables is formulated for multiple regression and coordinate transformations. Numerical examples for these two applications are provided to illustrate this analysis.     

半参数回归与模型精化

就一般情况给出了半参数平差的算法，并结合一种特定的情况，讨论了正规化矩阵半正定时的计算方法，给出了相应的公式，最后构造了一个模拟的平差问题，对半参数法和最小二乘法的计算结果进行了比较，计算表明，半参数法能够发现并识别模型误差或观测值中的系统误差。     

最小二乘配置和普通Kriging法在GPS高程转换中的应用

最小二乘配置法和Kriging法进行高程转换时均兼顾考虑高程异常的系统部分和随机部分,为对比分析两种方法在GPS高程转化时的优劣性,根据最小二乘配置法的协方差函数（或kriging法的变异函数）的不同,采用五种方案对实测数据进行处理。结果分析证明了以距离作为协方差函数的最小二乘配置法在算法和推估结果可靠性要优于其他方案。     

Considered parameters in a least squares adjustment process

Least squares adjustment processes occasionally utilize constants with a known degree of uncertainty. If the covariance matrix of the adjusted parameters is estimated without considering those uncertainties the resulting estimate is invariably too optimistic. A method is proposed by which without altering the values of the adjusted parameters their a posteriori (after the adjustment) covariance matrix can be improved by the inclusion of the effect of uncertainties in the constants.     

半参数测量平差模型与系统误差处理

考虑半参数测量模型L=Bx+S+Δ,x$Rd为未知回归参数,S为未知Borel函数。本文首先利用自然样条函数法,找到符合条件的非参数自然插值样条函数。其次利用偏残差法并综合最小二乘法,导出了这种平差方法的解算公式。最后,用一个算例说明了此方法的优越性。     

广义平差的概括模型

提出了广义平差的概括模型———附有条件的最小二乘配置模型。该概括模型不仅包括滤波和推估模型 ,扩充了原有的最小二乘配置模型 ,而且经典平差模型都是它的特例。     

Generalyzed variance-covariance propagation law formulae and application to explicit least-squares adjustments

Standard formulae overlook the contribution of a number of terms in the derivation of variance-covariance matrices for parameters in nonlinear least squares adjustment. In a large class of nonlinear mathematical models, these terms can contribute to an important error in the estimation of parameter variances. Improved formulae are derived. A numerical example is given and the use of our improved formula in the case of least-squares adjustment in the explicit case (L=F(X)) is fully documented.     

Improvement of parameter accuracy by choice and quality of observation

In a least squares adjustment (a minimum variance solution) using the technique of variation of coordinates (observation equations), a key result is the co-variance (dispersion) matrix of parameters. Assuming that standard errors of observations are used in the formation of the normal equations, rather than relative weights, this dispersion matrix gives the estimates of standard errors for the parameters solved for in the adjustment. A method will be presented which allows the designer of the observing plan to alter this dispersion matrix, which may not meet user requirements, so that it will meet user requirements and, from its inverse, solve mathematically for the selection and quality (accuracy) of the observations required to form this altered dispersion matrix of parameters.     

Deterministic and stochastic parameters in inertial survey adjustment

In the adjustment of inertial position surveys the additional parameters describing the systematic errors of individual traverses can be considered as deterministic or stochastic. The paper deals with various aspects of the deterministic or stochastic approach by way of a standard functional model. If purely deterministic parameters are set up, the solvability of the least squares problem depends on redundant observations like coordinate discrepancies of forward and backward runs or coordinate differences at cross-over points of traverse networks. Inequalities are presented to handle the configuration problem for any net and for several ways of introducing parameter sets. Also condition equations being geometrically explainable are developed solving the datum problem in free adjustment applications. Based on the Ebersberger Forst campaigns with a large amount of Ferranti, Honeywell and Litton data, numerical investigations into the stochastic properties of the additional parameters and the observations follow. It turns out that additional parameters for Honeywell and Litton data can be considered as stochastic parameters while for Ferranti data significant azimuth and time dependent effects can be found. The investigations of true errors show that in case of the deterministic adjustment approach a diagonal covariance matrix can be introduced and in case of stochastic additional parameters a first order Gauss-Markov process serves as a good approximation for the stochastic behaviour of the observations.     

地图扫描矢量化误差的最小二乘配置法处理研究

屏幕扫描数字化是地图数字化的常用方法。在数字化过程中,由于地图本身的变形、扫描仪分辨率等系统误差会影响数字化的结果。仿射变换是实现栅格数据向矢量化数据转换的常用方法之一,研究表明基于最小二乘的仿射变换只可以消除整体变形,而不能消除局部变形。为此作者提出采用最小二乘配置。采用最小二乘配置可以在计算转换参数的同时估计局部系统变形信号,可以消除或减弱以上误差的影响,改善数字化精度。实例分析表明,是提高扫描数字化的有效方法。     

A comparison of Stokes' numerical integration and collocation,and a new combination technique

Summary Basically two different evaluation methods are available to compute geoid heights from residual gravity anomalies in the inner zone: numerical integration and least squares collocation.If collocation is not applied to a global gravity data set, as is usually the case in practice, its result will not be equal to the numerical integration result. However, the cross covariance function between geoid heights and gravity anomalies can be adapted such that the geoid contribution is computed only from a small gravity area up to a certain distance _o from the computation point. Using this modification, identical results are obtained as from numerical integration.Applying this modification makes the results less dependent on the covariance function used. The difference between numerical integration and collocation is mainly caused by the implicitly extrapolated residual gravity anomaly values, outside the original data area. This extrapolated signal depends very much on the covariance function used, while the interpolated values within the original data area depend much less on it.As a sort of by-product, this modified collocation formula also leads to a new combination technique of numerical integration and collocation, in which the optimizing practical properties of both methods are fully exploited.Numerical examples are added as illustration.     

分离系统差的地面网与卫星网之间转换的数学模型及其解算方法

本文分析了地面网所含系统差之后,指出只需要两个参数就可描述地面网的定向系统差。若分别考虑地面水平网的尺度参数K_L和高程网的尺度参数K_H,则地面网与卫星网间转换的数学模型中参数的个数为10个。若假定K_L=K_H,则参数需要9个。导出了含有9个和10个未知参数的模型。提出采用部分参数带权的相关平差法解决九参数和十参数模型的法方程式系数阵秩亏问题。最后,利用我国实际数据检核了这些模型。计算表明,这种方法能有效地将坐标系的定向参数和地面网的定向系统差参数分开。揭示了我国地面水平网的尺度参数与高程网的尺度参数不一致,并给出了它们的参考值。     

粗差数学期望平移模型的理论研究

现有文献对数学期望平移模型的理论分析仅考虑了观测值统计独立的特殊情况。基于观测值统计相关的一般情况，导出了数学期望平移参数估值（Ｓｉ）的简明表达式。在此基础上，采用统计预测理论对Ｓｉ进行了直观的理论解释，扩展了统计学文献中的有关结论。借助于实例，分析了Ｓｉ与最小二乘残差的本质区别。     

顾及系数矩阵常数列的总体最小二乘迭代解法

介绍总体最小二乘的奇异值分解法(SVD)和混合总体最小二乘法(LS-TLS),基于间接平差原理推导一种总体最小二乘迭代解法,可以用来解决系数矩阵含常数列的总体最小二乘平差问题。最后分别对系数矩阵不含常数列和系数矩阵含常数列的算例进行验证,得到的结果与采用奇异值分解法和混合总体最小二乘法计算的结果相同,表明算法的有效性。     

病态加权总体最小二乘的广义岭估计解法

针对加权情形下的变量误差(EIV)模型,采用广义岭估计法处理总体最小二乘平差的病态性问题. 结合最优化准则和协方差传播率推导了未知参数的改正数求解公式;根据参数估计值的均方误差最小化原理,通过求偏导数列出广义岭估计中岭参数的迭代解式,并讨论了广义岭参数的含义和作用,给出了确定岭参数的L-曲线法. 通过算例比较分析了加权最小二乘估计、总体最小二乘估计、加权最小二乘岭估计、总体最小二乘岭估计、加权最小二乘的广义岭估计和总体最小二乘广义岭估计,叙述了加权总体最小二乘的广义岭估计的优缺点.