线性离散零和问题的改进滚动时域控制  

A Modified Receding Horizon Control for Discrete Linear Zero-Sum Games

作　　者：曹宁[1] 冯德志[1] 

机构地区：[1]东北大学信息科学与工程学院,辽宁沈阳110819

出　　处：《东北大学学报（自然科学版）》2012年第1期6-9,共4页Journal of Northeastern University(Natural Science)

基　　金：国家自然科学基金资助项目(50977008;60821063;61034005);国家高技术研究发展计划项目(2009AA04Z127);国家重点基础研究发展计划项目(2009CB320601)

摘　　要：提出一种改进的滚动时域控制算法来解决离散线性时不变系统的零和问题.与普通滚动时域控制不同的是,每一步中性能指标的终端权值矩阵将随着运算的进行不断更新,这等价于延长了时域长度.严格证明了该算法得到的控制律将收敛到无限零和问题的解,同时保证了闭环系统的一致最终指数稳定性,而不需要对终端状态、时域长度及终端性能指标施加额外的约束.最后仿真例子说明了该算法的有效性.The zero-sum games of discrete linear time-invariant （LTI） systems using a modified receding horizon control scheme were investigated. Different from conventional RHC, the proposed scheme updates its terminal weighting matrix in performance index as the stage moves forward. This is equivalent to lengthening the horizon size. The control policies generated by the proposed algorithm converge to the solution of the infinite horizon zero-sum games. Furthermore, it ensures the uniform ultimate exponential stability of closed-loop system without imposing any constraints on the terminal state, the horizon size, or the terminal cost. Simulation shows the effectiveness of the proposed algorithm.

关 键 词：滚动时域控制 零和 权值矩阵 线性离散系统 稳定性 

分 类 号：TG335.58[金属学及工艺—金属压力加工]