论文部分内容阅读
针对一类具有测量数据丢失的不确定离散随机系统,研究了鲁棒状态估计问题,基于间断观测滤波算法和规则最小二乘优化理论,给出一种Kalman形式的递推滤波算法.对于测量数据丢失的问题,采用已知概率的Bernoulli随机序列,使得对于所有可能的测量数据丢失和所能容许的不确定性,间断观测鲁棒状态估计递推算法是稳定的.最后,通过数值仿真和对比结果验证了所提出算法的可行性.
For a class of uncertain discrete stochastic systems with measured data loss, the robust state estimation problem is studied. Based on the discontinuous observed filtering algorithm and the rule least square optimization theory, a Kalman-style recursive filtering algorithm is given. For the measurement data Lost problems, the Bernoulli random sequence with known probability is used, so that the recursive algorithm of robust robustness estimation is stable for all possible lost and tolerable uncertainties of measurement data.Finally, by numerical simulation and comparison The result verifies the feasibility of the proposed algorithm.