Evolutionary programming Kalman filter

A robust Kalman filtering (KF) algorithm based on the evolutionary programm ing (EP) technique is proposed in this paper, for uncertain systems with un known-but-bounded uncertain parameters which are described by interval syst ems. This algorithm takes advantage of the global optima-searching capabili ty of EP to find the optimal KF results at every iteration, which include b oth the upper-lower boundaries and the nominal trajectory of the optimal es timates of the system state vectors. One prominent feature of this EP filte ring algorithm is that it assumes the same statistical conditions and provi des the same optimal estimates as the conventional KF scheme. Both linear a nd nonlinear systems are studied. Two typical computer simulation examples are given with comparison, which verify the merits of the new method - it y ields more accurate estimation results and is less conservative as compared to the existing interval Kalman filtering (IKF). (C) 2000 Elsevier Science Inc. All rights reserved.