State and Parameter Estimation Using Unscented Kalman Filter
Loading...
Date
2012-12-09
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
The Extended Kalman Filter is a bayesian state estimation used for nonlinear
models or systems. This filter may however fail to produce accurate results depending
on the degree of nonlinearity of the system. The Unscented Kalman Filter
on the other hand can be applied to highly nonlinear systems or models. Comparisons
between the two filters are made using two systems. The first system is a four
degrees of freedom shear building with time-varying system parameters and the
second is a nonlinear hysteric damping system with unknown system parameters.
The results indicated that the latter provides consistent as well as more accurate
state and parameter estimates than the extended kalman filter for nonlinear
systems.
Description
A thesis Submitted to Department of Mathematics
in Partial Fulfillment of the Requirements for the Degree
of
Master of Philosophy
College of Science.December,2012