带丢包Markov切换线性系统的状态估计问题研究

State Estimation for Jump Markov Linear Systems with Packet Dropouts

针对一类带丢包的Markov切换系统,提出一种含有双Markov切换参数的交互式多模型算法.该算法利用一个二态的Markov链对系统是否丢包进行建模,得到双Markov链系统,通过定义乘积集将两个Markov切换参数所对应的模型集进行融合,并给出单个模型集中各模型与乘积集中各模型的对应关系.在此基础上,以交互式多模型算法为框架,采用分层的方法,并利用一种新的最优估计算法对双Markov链系统进行滤波.仿真实验证明了该算法的有效性.

This study is devoted to the state estimation problem for a class of jump M arkov linear systems w ith packet dropouts. The behavior of packet dropouts is described by a tw o-state（ i. e.,packet-dropping and normal） M arkov chain w ith know n transition probability matrix,w hich is independent of the system dynamics. Therefore,the obtained system can be modeled as a jump M arkov linear system w ith tw o sw itching parameters. A product set is defined to combine the tw o mode sets and the corresponding relationship betw een models in the product set and models in the individual mode set is given. Based on the product set,w e cast the model into the framew ork of the interacting multiple model（ IM M） algorithm and the filtering steps are carried out in a layered manner. Furthermore,an optimal estimation algorithm is combined w ith the IM M to obtain the filtering results of the system. A maneuvering target tracking example is presented to prove the effectiveness of the proposed algorithm.