On State Estimation of discrete-time Markov jump linear systems
This paper is concerned with state estimation problem for discrete-time Markov jump linear systems. A novel recursive algorithm for estimating the state of the considered systems is obtained. Compared with the existing estimation algorithms for the systems under consideration, the novelty of the derived algorithm lies in using a bank of conditional expectation sets instead of a bank of Kalman filters to estimate the state. The algorithm is finite-dimensionally computable, and does not increase computation and storage capabilities in the number of the noise observation sequence. A numerical comparison of the algorithm with the interacting multiple model (IMM) algorithm is given.
State estimation Discrete time Conditional ezpectation Markov jump
Wei Liu Huaguang Zhang
School of Information Science and Engineering, Northeastern University, Shengyang 110004, China
国际会议
2009年中国控制与决策会议(2009 Chinese Control and Decision Conference)
广西桂林
英文
1110-1115
2009-06-17（万方平台首次上网日期，不代表论文的发表时间）