Markov跳变系统MVF滤波器设计  

MVF Filtering for Markov Jump Systems

作　　者：闻继伟[1] 刘飞[1] 

机构地区：[1]江南大学自动化研究所,江苏无锡214122

出　　处：《系统工程》2009年第6期99-104,共6页Systems Engineering

基　　金：国家自然科学基金资助项目(60574001);新世纪优秀人才支持计划项目(NCET-05-0485);江南大学创新团队发展计划项目

摘　　要：针对离散时间Markov跳变系统设计最小方差有限脉冲响应滤波器。这类滤波器在一段有限的滚动时域上利用可测输入和输出的线性函数来估计系统的状态,并使估计状态能尽可能接近实际状态,即满足无偏差条件。通过最小化估计误差的方差,可以得到最优滤波器。为了便于工程应用,假设每一个采样时刻的跳变模态和系统的输入、输出均是可知的。最小方差有限脉冲响应滤波器分别以序列形式和迭代形式给出。数值示例验证了所提方法的可行性和有效性。A Minimum Variance Finite Impulse Response Filter （MVF filter） is designed for a set of discrete-time linear systems with randomly jumping parameters described by a finite state Markov process. The MVF filter processes the measured inputs and outputs on the finite receding horizon linearly under the unbiased condition and this kind of optimal filter is obtained by minimizing the estimation error variance. In terms of engineering application, we assume the complete access to the jump modes and system inputs and outputs at every sampling time. The MVF filtering is presented in the batch form and recursive form respectively. A numerical example is given to verify the feasibility and efficiency of the proposed method.

关 键 词：MARKOV跳变系统 卡尔曼滤波器 最小方差有限脉冲响应滤波器 有限滚动时域 无偏差条件 

分 类 号：TP13[自动化与计算机技术—控制理论与控制工程]