A preliminary study on optimal input design for nonlinear systems
Authors:
- 1 December 2013
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 01912216,p. 4931-4936
Abstract
In this paper, an initial study is made on the optimal input design for Wiener systems that consists of a FIR filter, followed by a polynomial nonlinearity. A design method, based on the dispersion function, is introduced, in order to find an optimal set of elementary designs. For the considered class of Wiener systems, it is shown that these elementary designs are couples of successive input values. However, concatenation of these elementary designs is not straight forward. By imposing symmetry conditions on the total design, a solution is obtained that can be realized as a time sequence and that is optimal in the subspace of symmetric designs.Keywords
This publication has 4 references indexed in Scilit:
- Experiment design for the identification of a simple Wiener system2012
- On optimal input design for nonlinear FIR-type systems2010
- Monotonic convergence of a general algorithm for computing optimal designsThe Annals of Statistics, 2010
- Optimal Input Design for Identification of Non-linear Systems: Learning From the Linear CaseAmerican Control Conference (ACC), 2007