具有不确定噪声的连续时间广义系统确保估计性能的鲁棒Kalman滤波器  

Robust Kalman Filter of the Guaranteed Estimation Performance for a Continuous-Time Descriptor System with Uncertain Noise

作　　者：奚宏生[1] 殷保群[1] 

机构地区：[1]中国科学技术大学自动化系,合肥230026

出　　处：《控制理论与应用》2001年第5期782-784,791,共4页Control Theory & Applications

摘　　要：讨论了一类具有不确定噪声的连续时间广义随机控制系统的鲁棒Kalman滤波器的设计问题 .文中给出了确保估计误差性能指标的不确定噪声协方差矩阵扰动上界 .文章研究结果表明 ,在此界限内采用最坏情况下的最优滤波器实现对状态的估计 ,它不仅能极小化不确定下的最坏性能 ,而且也能确保估计误差性能指标达到给定的某个自由度 .This paper considers the design method of a robust Kalman filter for continuous time descriptor stochastic control systems with uncertain noise. The perturbating upper bounds on uncertain noise covariances are obtained so as to guarantee the performance index of estimation error. In particular, it is shown that the optimum estimator designed in the perturbating upper bounds can be used to minimize the worst performance in an uncertain case and guarantee that the deviation of the performance index of estimation error remains within a given free degree.

关 键 词：鲁棒Kalman滤波器 性能估计 连续时间广义系统 鲁棒性 

分 类 号：TP13[自动化与计算机技术—控制理论与控制工程]