带ARMA有色噪声的广义系统信息融合Kalman平滑器  

INFORMATION FUSION KALMAN SMOOTHER FOR DESCRIPTOR SYSTEMS WITH ARMA COLORED NOISES

作　　者：陶贵丽[1] 刘文强[1] 侯九阳[1] 

机构地区：[1]黑龙江科技学院计算机与信息工程学院,哈尔滨150027

出　　处：《系统科学与数学》2010年第2期205-217,共13页Journal of Systems Science and Mathematical Sciences

基　　金：国家自然科学基金(60374026);黑龙江科技学院引进人才启动基金(07-47)共同资助课题

摘　　要：对于带自回归滑动平均(ARMA)有色观测噪声的多传感器广义离散随机线性系统,应用奇异值分解,提出了广义系统多传感器信息融合状态平滑问题。基于Kalman滤波方法,在线性最小方差信息融合准则下,给出了按矩阵加权融合降阶稳态广义Kalman平滑器。为了计算最优加权,提出了局部平滑误差协方差阵的计算公式。一个Monte Carlo仿真例子说明了所提方法的有效性。For multisensor descriptor discrete-time stochastic linear systems with autoregressive moving average（ARMA） colored observation noises, by using the singular value decomposition, the problem of multi-sensor information fusion state smooth is presented. Based on Kalman filtering method, a reduced order steady-state descriptor Kalman smoother weighted by matrices is proposed under the linear minimum variance information fusion criterion. In order to compute the optimal weights, the formulae of computing the covariance matrices among local smoothing errors are presented. A Monte Carlo simulation example shows the proposed method＇s effectiveness.

关 键 词：广义系统 多传感器信息融合 状态加权融合 有色噪声 KALMAN滤波 

分 类 号：TP202[自动化与计算机技术—检测技术与自动化装置]