具有多丢包的随机奇异系统的分布式后验滤波器

Distributed Posterior Filter for Stochastic Singular Systems with Multiple Packet Dropouts

考虑网络传输过程中的随机数据包丢失现象,研究带有多个传感器的局部随机奇异线性系统的分布式后验滤波问题。首先,基于典范型分解将原奇异系统转化为快、慢两个降阶子系统。快子系统的后验滤波由已有结果给出,然后针对慢子系统提出局部后验滤波器,且推导了任两个传感器子系统之间的互协方差矩阵的计算公式;进而由线性最小方差意义下的矩阵加权融合算法获得原始奇异系统的分布式融合后验滤波器。仿真研究验证了算法的有效性。

Considering the phenomena of random data packet dropouts in the data transmission,the distributed posterior filtering problem is studied for stochastic singular linear systems with multiple sensors. Firstly,based on decomposition in canonical form,the original singular system is transformed into fast and slow two subsystems. For the fast subsystem,the local posterior filter is given by the existing results. For the slow subsystem,the local posterior filter is proposed and the cross-covariance matrices between any two sensor subsystems are derived. Further,the distributed fusion posterior filter is obtained for the original singular system based on the fusion algorithm weighted by matrices in the linear minimum variance sense. Simulation research verifies the effectiveness of the proposed algorithm.