带有色观测噪声的广义系统信息融合Kalman平滑器  

Information fusion Kalman smoother with colored noise measurement for descriptor systems

作　　者：陶贵丽[1] 刘文强[1] 孙成发[1] 

机构地区：[1]黑龙江科技学院计算机与信息工程学院,黑龙江哈尔滨150027

出　　处：《大庆石油学院学报》2009年第2期93-97,共5页Journal of Daqing Petroleum Institute

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

摘　　要：对于被多传感器观测的带有色观测噪声的广义离散线性随机系统,应用奇异值分解,并通过对观测方程的状态变换,将其变换为带相关噪声的2个降阶多传感器子系统;应用Kalman滤波方法,在线性最小方差加权融合准则下,给出按块对角阵标量加权融合降阶广义Kalman平滑器.MonteCarlo仿真结果表明该方法的有效性.For discrete linear stochastic descriptor systems measured by multiple sensors with colored measurement noises,using the singular value decomposition,by means of a state transformation of the observation equation,the system is converted into two reduced-order subsystems with correlated noises.Based on Kalman filtering method,fusion reduced-order descriptor Kalman smoother weighted by scalars is proposed under the linear least variance optimal fusion criterion by block-diagonal matrices.A Monte Carlo simulation example shows its effectiveness.

关 键 词：广义系统 有色观测噪声 标量加权融合 奇异值分解 Kalman滤波方法 

分 类 号：O211.64[理学—概率论与数理统计]