A simple approach to nonlinear estimation of physical systems
Mathematical and Computer Modelling
By: G. Christakos
Links
- The Publications Warehouse does not have links to digital versions of this publication at this time
- Download citation as: RIS | Dublin Core
Abstract
Recursive algorithms for estimating the states of nonlinear physical systems are developed. This requires some key hypotheses regarding the structure of the underlying processes. Members of this class of random processes have several desirable properties for the nonlinear estimation of random signals. An assumption is made about the form of the estimator, which may then take account of a wide range of applications. Under the above assumption, the estimation algorithm is mathematically suboptimal but effective and computationally attractive. It may be compared favorably to Taylor series-type filters, nonlinear filters which approximate the probability density by Edgeworth or Gram-Charlier series, as well as to conventional statistical linearization-type estimators. To link theory with practice, some numerical results for a simulated system are presented, in which the responses from the proposed and the extended Kalman algorithms are compared. ?? 1988.
| Publication type | Article |
|---|---|
| Publication Subtype | Journal Article |
| Title | A simple approach to nonlinear estimation of physical systems |
| Series title | Mathematical and Computer Modelling |
| Volume | 11 |
| Issue | C |
| Year Published | 1988 |
| Language | English |
| Larger Work Type | Article |
| Larger Work Subtype | Journal Article |
| Larger Work Title | Mathematical and Computer Modelling |
| First page | 583 |
| Last page | 588 |
| Google Analytic Metrics | Metrics page |