摘要
针对异步均匀采样的线性离散系统,研究了最优线性分布式异步融合滤波问题。通过引入伯努利分布的随机变量,将异步系统同步化,给出了线性最小方差最优线性局部滤波器。推导了局部估值之间的误差互方差阵、先验估值和局部估值之间的误差互方差阵。提出了不带反馈的分布式递推线性无偏最小方差最优线性融合滤波器。所提出的算法比局部估计按矩阵加权融合滤波器具有更高的估计精度,与集中式融合精度相比具有精度损失。为进一步改善估计精度,又提出了与集中式融合精度相同的带反馈的分布式最优线性融合滤波器。仿真实验验证了所提算法的有效性。
The optimal linear distributed asynchronous fusion filter is studied for the linear discrete system with asynchronous uniform sampling.By introducing the Bernoulli distribution random variables,the asynchronous system is synchronized,and the linear minimum variance optimal linear local filter is presented.The error cross-variances matrix between local valuations and cross-variance matrix between prior and local valuations are derived.A distributed recursive optimal fusion filter without feedback is proposed in the linear unbiased minimum variance sense.The proposed algorithm has higher estimation accuracy than the local estimation matrix-weighted fusion filter.Compared with the centralized fusion,however,it has accuracy loss.In order to improve the estimation accuracy,a distributed recursive optimal linear fusion filter with feedback is also proposed,which has the same accuracy as the centralized fusion filter.Simulation results show the effectiveness of the proposed algorithms.
作者
姜帅
孙书利
JIANG Shuai;SUN Shuli(School of Electronic Engineering,Heilongjiang University,Harbin 150080,China)
出处
《黑龙江大学自然科学学报》
CAS
2021年第4期495-504,共10页
Journal of Natural Science of Heilongjiang University
基金
国家自然科学基金资助项目(61573132)。
关键词
异步采样系统
分布式融合滤波器
线性无偏最小方差
互协方差阵
反馈
asynchronous sampling system
distributed fusion filter
linear unbiased minimum variance
cross-covariance matrix
feedback
