Title :
Nonlinearities in NARX polynomial models: representation and estimation
Author :
Aguirre, L.A. ; Corrêa, M.V. ; Cassini, C.C.S.
Author_Institution :
Programa de Pos Graduacao em Engenharia Eletrica, Univ. Fed. de Minas Gerais, Belo Horizonte, Brazil
fDate :
7/1/2002 12:00:00 AM
Abstract :
It is shown how nonlinearities are mapped in NARX polynomial models. General expressions are derived for the gain and eigenvalue functions in terms of the regressors and coefficients of NARX models. Such relationships are useful in grey-box identification problems. The results are illustrated using simulated and real data
Keywords :
autoregressive processes; eigenvalues and eigenfunctions; identification; modelling; polynomials; NARX polynomial model nonlinearities; eigenvalue functions; gain functions; grey-box identification problems; nonlinear autoregressive exogenous-input polynomial model; nonlinearity estimation; nonlinearity representation; regressors;
Journal_Title :
Control Theory and Applications, IEE Proceedings -
DOI :
10.1049/ip-cta:20020398