带相关噪声、随机观测滞后和丢失的随机不确定系统的最优线性估值器  

Optimal linear estimator for stochastic uncertain systems with correlated noises, random measurement delays and losses

作　　者：王欣[1] 孙书利[1] 

机构地区：[1]黑龙江大学电子工程学院,黑龙江哈尔滨150080

出　　处：《控制理论与应用》2017年第5期609-618,共10页Control Theory & Applications

基　　金：国家自然科学基金项目(61573132);黑龙江省杰出青年基金项目(JC201412);黑龙江省博士后基金项目(LBH–Z1226);黑龙江省高校科技创新团队支持项目(2012TD007)资助~~

摘　　要：对带有限步相关噪声、乘性噪声、多步随机观测滞后和丢失的复杂网络化控制系统,根据相关噪声的步数,分析了噪声和状态、噪声和观测、噪声和新息、观测和新息、状态和新息之间的相关性,给出了相关阵的递推计算公式.利用射影理论,提出了线性最小方差最优线性估值器,包括滤波器、预报器和平滑器.一个网络监测环境下的三容器水箱系统的实例仿真,验证了算法的有效性.For the complex networked control systems(NCSs) with finite-step correlated noises, multiplicative noises,multi-step random measurement delays and losses, we analyze the correlations between the noise and state, the noise and measurement, the noise and innovation, the measurement and innovation, and the state and innovation in terms of the step number of correlated noises. Moreover, the recursive formulas of correlation matrices are derived. The linear minimum variance optimal linear estimators, including filter, predictor and smoother, are presented by using projection theory. A simulation example of the three-tank water system under a network monitoring environment shows the effectiveness of the proposed algorithms.

关 键 词：有限步相关噪声 乘性噪声 随机观测滞后和丢失 最优线性估值器 射影理论 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]