多模型多传感器信息融合Kalman平滑器  

Multi-model and multi-sensor information fusion Kalman smoother

作　　者：孙书利[1] 

机构地区：[1]黑龙江大学自动化系,黑龙江哈尔滨150080

出　　处：《控制理论与应用》2005年第2期211-217,共7页Control Theory & Applications

基　　金：国家自然科学基金资助项目(60374026);黑龙江省教育厅基金资助项目(10541174);黑龙江大学杰出青年基金资助项目(JC2004-04);黑龙江大学自动控制重点实验室资助项目.

摘　　要：基于标量加权的线性最小方差最优信息融合算法,对多模型多传感器离散线性随机系统,给出了一种分布式标量加权信息融合固定滞后Kalman平滑器.它只需计算加权标量系数,可减小在融合中心的计算负担.当各子系统存在稳态滤波时,又给出了标量加权信息融合稳态平滑器,它计算量小,便于实时应用.并给出了两个子系统之间的平滑误差互协方差阵的计算公式.仿真例子验证了其有效性.Based on the optimal information fusion algorithm weighted by scalars in the linear minimum variance sense,a distributed information fusion fixed_lag Kalman smoother weighted by scalars is given for discrete linear stochastic system with multiple model and multiple sensors.It only requires the computation of scalar weights,so that the calculated burden in the fusion center can be reduced.The information fusion steady_state smoother weighted by scalars is also given when all subsystems have steady_state filtering.It has a small calculation and is convenient to apply in real time.The computation formula for the smoothing error cross_covariance matrix is given between any two subsystems.A simulation example shows its effectiveness.

关 键 词：多模型多传感器系统 标量加权最优信息融合准则 固定滞后平滑器 Kalman滤波方法 

分 类 号：TP202.4[自动化与计算机技术—检测技术与自动化装置]