研究了带有一步随机滞后和不连续丢包离散随机线性系统的线性估计问题.通过一个满足Ber-noulli分布的随机变量来描述这种可能的滞后和丢包现象.基于所建立的新模型,利用射影理论提出了一个在线性最小方差意义下的递推的最优线性滤波器.并给出了稳态线性滤波器存在的一个充分条件.当不存在随机滞后和丢包时,所提出的滤波器退化为标准的Kalman滤波器.
It is concerned with the linear estimation problem for discrete-time stochastic linear systems with one-step random delays and inconsecutive packet dropouts. A new model is constructed to describe the phenomena of the possible delay and packet dropouts by using a Bernoulli distributed stochastic variable. Based on the new developed model, a recursive optimal linear filter is presented in the linear minimum variance sense by projection theory. A sufficient condition for the existence of the steady-state linear filter is given. The proposed filter is reduced to the standard Kalman filter when there are no random delays and packet dropouts.