NNCTRL - a CANCSD toolkit for MATLAB(R)

Author

Nørgaard, M. ; Ravn, O. ; Poulsen, N.K. ; Hansen, L.K.

Author_Institution

Dept. of Autom., Tech. Univ., Lyngby, Denmark

fYear

1996

Firstpage

368

Lastpage

373

Abstract

A set of tools for computer-aided neuro-control system design (CANCSD) has been developed for the MATLAB environment. The tools can be used for construction and simulation of a variety of neural network based control systems. The design methods featured in the toolkit are: direct inverse control, internal model control, feedforward, feedback linearization, optimal control, instantaneous linearization, and nonlinear predictive control. Furthermore, the toolkit has been given a flexible design which allows for incorporation of the user´s personal control algorithms

Keywords

control system CAD; feedback; feedforward; linearisation techniques; neurocontrollers; nonlinear control systems; optimal control; predictive control; simulation; CAD toolkit; MATLAB environment; NNCTRL; computer-aided design; direct inverse control; feedback linearization; feedforward; internal model control; neural network; neuro-control system; nonlinear predictive control; optimal control; Computational modeling; Computer languages; Control system synthesis; Design methodology; Inverse problems; Linear feedback control systems; MATLAB; Mathematical model; Neural networks; Optimal control;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer-Aided Control System Design, 1996., Proceedings of the 1996 IEEE International Symposium on

Conference_Location

Dearborn, MI

Print_ISBN

0-7803-3032-3

Type

conf

DOI

10.1109/CACSD.1996.555320

Filename

555320