Control of nonlinear dynamical systems using neural networks. II. Observability, identification, and control
- 1 January 1996
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 7 (1), 30-42
- https://doi.org/10.1109/72.478390
Abstract
Summary:The input-output decoupling problem is studied for a class of recursive nonlinear systems (RNSs), i. e. for systems, modelled by higher order nonlinear difference equations, relating the input, the output and a finite number of their time shifts. The solution of the problem via regular static feedback known for discrete-time nonlinear systems in state space form, is extended to RNSs. Necessary and sufficient conditions for local solvability of the problem are proposed. This is the alternative to be used when some nonlinear input-outpt models cannot be realized in the state-space formKeywords
This publication has 16 references indexed in Scilit:
- Identification of Nonlinear Dynamical Systems Using Neural NetworksPublished by Elsevier BV ,1997
- Recursive identification using feedforward neural networksInternational Journal of Control, 1995
- Control of nonlinear dynamical systems using neural networks: controllability and stabilizationIEEE Transactions on Neural Networks, 1993
- Issues in system identificationIEEE Control Systems, 1991
- Identification and control of dynamical systems using neural networksIEEE Transactions on Neural Networks, 1990
- Nonlinear Dynamical Control SystemsPublished by Springer Science and Business Media LLC ,1990
- A multilayered neural network controllerIEEE Control Systems Magazine, 1988
- Functional reproducibility of general multivariable analytic non-linear systemsInternational Journal of Control, 1987
- Inversion of multivariable linear systemsIEEE Transactions on Automatic Control, 1969
- Invertibility of linear time-invariant dynamical systemsIEEE Transactions on Automatic Control, 1969