Using steady-state prior knowledge to constrain parameter estimates in nonlinear system identification

M.V. Correa1,2, L.A. Aguirre1, R.R. Saldanha1
1Programa de Pós Graduação em Engenharia Elétrica, Universidade Federal de Minas Gerais, Belo Horizonte, MG, Brazil
2Curso de Engenharia Elétrica, Centro Universit⋡rio do Leste de Minas Gerais—UNILESTE-MG Cel, Fabriciano, MG, Brazil

Tóm tắt

This work investigates the use of prior knowledge in the parameter estimation of NARMAX polynomial models. The problem of parameter estimation is then formulated in such a way that the estimated models have specified features. This formulation results in a constrained optimization problem, which is solved using the ellipsoid algorithm. This technique is applied to a real DC-DC buck converter. In this system, the static relation is known from the theory but identification data are located over a rather narrow range around an operating point. Although obtained from dynamical data, the models provide good approximation to the nonlinear static function.

Từ khóa

#Steady-state #Parameter estimation #Nonlinear systems #Polynomials #Stability #Constraint optimization #Ellipsoids #Buck converters #Least squares approximation #Yield estimation

Tài liệu tham khảo

korenberg, 1985, orthogonal identification of nonlinear difference equation models, Mid West Symp Circuits and Systems 10.1080/00207178808906169 10.1080/0020718508961129 ogata, 1995, Discrete-Time Control Systems 10.1002/aic.690440114 10.1109/20.767367 sjöberg, 1995, nonlinear back-box modeling in system identification: a unified overview, Automatica, 31, 1691, 10.1016/0005-1098(95)00120-8 suykens, 1997, <formula><tex>${\rm nl}_{q}$</tex></formula> theory: checking and imposing stability of recurrent neural networks for nonlinear modeling, IEEE Transactions on Signal Processings, 45, 2682, 10.1109/78.650094 10.1016/0005-1098(93)90124-C 10.1016/0009-2509(74)80089-8 10.1049/ip-cta:20020398 10.1049/ip-cta:19982112 10.1287/opre.29.6.1039 10.1080/00207728808964057 10.1007/BFb0121078 10.1080/00207178908953472 10.1109/81.855463 10.1080/00207179508921557 10.1016/0005-1098(95)00146-8