具不确定观测和相关噪声的最优递推滤波  

Optimal Recursive Estimation with Uncertain Observation and Time-Correlated Disturbances

作　　者：盛梅[1] 汤玉东[1] 邹云[1] 

机构地区：[1]南京理工大学自动化系,南京210094

出　　处：《宇航计测技术》2005年第2期38-42,共5页Journal of Astronautic Metrology and Measurement

基　　金：国家自然科学基金 (60 4740 78)

摘　　要：应用正交投影定理,对于噪声相关系统,在观测不确定的情况下,求出了状态向量的卡尔曼滤波公式。在线性最小方差准则下,解决了状态噪声一步相关,相同时刻的测量噪声和状态噪声相关,以及测量噪声和状态噪声在相邻时刻均相关的情况下的滤波问题,并给出了递推滤波公式。仿真算例说明了它们的有效性。Considers the least mean-squared error linear estimation problem, using covariance information, in linear discrete-time stochastic systems with uncertain observations for the case where the state and measurement noises are correlated both at the same time and the neighbored time, while the state noises are not white. The different kinds of estimation problem treated include one-stage prediction and filtering. Employing the Orthogonal Projection Lemma and the features of the observations derives the recursive algorithm out. Simulation result shows the effectiveness of the algorithm.

关 键 词：递推滤波 不确定 相关噪声 观测 最优 最小方差准则 状态噪声 测量噪声 卡尔曼滤波 投影定理 相关系统 状态向量 声相关 公式 仿真 

分 类 号：TP271.8[自动化与计算机技术—检测技术与自动化装置] TP273.4[自动化与计算机技术—控制科学与工程]