广义非线性最小二乘测量参数平差的快速差分迭代解算  

Faster Difference Iterative Algorithm of Nonlinear Data Processing

作　　者：宁伟[1] 陶华学[2] 卿熙宏[2] 

机构地区：[1]徐州师范大学工学院 [2]山东科技大学地球信息科学与工程学院,泰安市岱宗大街223号271019

出　　处：《武汉大学学报（信息科学版）》2005年第7期617-620,共4页Geomatics and Information Science of Wuhan University

基　　金：国家自然科学基金资助项目(40174003)。

摘　　要：针对数字化建设中涉及的多类型、多精度、多源、动态非线性最小二乘测量参数平差问题,提出了一种新的解算模型。该模型通过构造适当的差分点列,避免了一阶或二阶导数计算,对于模型复杂或者导数不存在的函数模型而言,具有适应面广、算法简单等特点,为广义非线性数据处理中的参数估计问题的解决开拓了又一新的思路。A new fast difference iterative solution model is proposed to adjust parameters of surveying and mapping by least-squares method with multi-type, multi-precision, multi-source dynamic and nonlinear data in digitalized construction, which can avoid computing derivative completely and reduce calculation of Jacobi matrix. At the same time, a matrix sequence, which can approximately substitute for second-order partial derivative matrix by recurrence method, is constituted to make the rate of convergence of the algorithm model faster. This creates a new solution to solve the generalized nonlinear least squares adjustment of surveying and mapping by parameters.

关 键 词：广义非线性最小二乘 测量平差 参数估计 快速差分迭代 

分 类 号：P207.2[天文地球—测绘科学与技术]