Identification of stochastic linear dynamic systems
Identification of stochastic linear dynamic systems
复制标题
随机线性动力系统的辨识
DOI：
10.1109/sap.1969.269932
复制
发表时间：
1969
期刊：
影响因子：
--
通讯作者：
R. Mehra
中科院分区：
文献类型：
--
作者：
R. Mehra
利用一种新的表示形式，导出了线性动态系统的极大似然辨识方程组。这些方程被证明是直接相关的线性动态系统的滤波和平滑方程。用Davidon共轭梯度法对一个四阶系统进行了数值计算，并给出了估计的方差。
Using a new form of representation, a set of equations has been derived for the maximum likelihood identification of linear dynamic systems. These equations are shown to be directly related to the filtering and smoothing equations for linear dynamic systems. Numerical results are obtained for a fourth order system using Davidon's Conjugate Gradient Method which also gives the variances of the estimates.