IJPAM: Volume 49, No. 3 (2008)

A FILTER FOR NONLINEAR SYSTEMS BY MEANS
OF DETERMINISTIC NONLINEAR OBSERVERS

M.P. Di Ciccio$^1$, A. Germani$^2$, P. Pepe$^3$
$^{1,2,3}$Ingegneria Elettrica e Informazione
Universitá degli Studi dell'Aquila
Poggio di Roio, L'Aquila, 67040, ITALY
$^1$e-mail: diciccio@ing.univaq.it
$^2$e-mail: germani@ing.univaq.it
$^3$e-mail: pepe@ing.univaq.it


Abstract.In this paper a novel algorithm for filtering of nonlinear systems corrupted by noise in the state equations and measurements is presented. It is based on two steps. The first step makes use of a standard nonlinear observer in order to compute the prediction state estimation. The second step makes use of the extended Kalman filter for computing the correction, by means of a linearization around the previously computed prediction state estimation. The estimation is provided at sampling times, with arbitrarily chosen sampling period.

Received: August 14, 2008

AMS Subject Classification: 93C10, 93E10, 93E11

Key Words and Phrases: nonlinear systems, stochastic systems, extended Kalman-Bucy filter, nonlinear observers

Source: International Journal of Pure and Applied Mathematics
ISSN: 1311-8080
Year: 2008
Volume: 49
Issue: 3