对于带观测时滞的线性离散时变随机控制优化问题,提出了观测变换方法,把带观测时滞状态空间模型等效地转换为无观测时滞的状态空间模型,接着应用卡尔曼(Kalman)滤波方法,在线性最小方差最优融合准则下,给出按矩阵、按对角阵和按标量加权三种最优信息融合卡尔曼(Kalman)滤波器,可分为局部最优全局次优的.融合器的精度高于每一个局部Kalman估值器的精度.可以减少用增广状态方法计算负担大的缺点.为了计算最优加权,给出了计算局部估计误差互协方差公式.对于带观测时滞的三传感器目标跟踪系统的Monte Carlo仿真例子证明了算法的有效性.%For the linear discrete time - variance stochastic control systems with time - delayed measurements, a measurement transformation approach was presented, which transforms the equivalent state space model with measurement delays into the state space model without measurement delays. And then using the Kalman filtering method, under the linear minimum variance optimal weighted fusion rules, three distributed optimal fusion Kalman filters weighted by matrices, diagonal matrices and scalars were presented. They are locally optimal and globally subopti-mal. The accuracy of the fuser is higher than that of each local Kalman estimator. They overcome the drawback that the augmented state method requires a large computational burden. In order to compute the optimal weights, the formulae of computing the cross - covariances among local estimation errors were given. A Monte Carlo simulation example for the three - sensor target tracking system with time - delayed measurements shows its effectiveness.
展开▼
