A multilayer recurrent neural network for real-time synthesis of linear-quadratic optimal control systems

Author

Wang, Jun ; Wu, Guang

Author_Institution

Dept. of Ind. Technol., North Dakota Univ., Grand Forks, ND, USA

Volume

4

fYear

1994

fDate

27 Jun-2 Jul 1994

Firstpage

2506

Abstract

A multilayer recurrent neural network is proposed for synthesizing linear-quadratic optimal control systems by means of solving algebraic matrix Riccati equations in real time. The proposed recurrent neural network consists of four bidirectionally connected layers. Each layer consists of an array of neurons. The proposed recurrent neural network is shown to be capable of solving algebraic Riccati equations and synthesizing linear-quadratic control systems in real time. The operating characteristics of the recurrent neural network and closed-loop control systems are also demonstrated through two illustrative examples

Keywords

Riccati equations; closed loop systems; control system synthesis; linear quadratic control; linear systems; multilayer perceptrons; recurrent neural nets; algebraic matrix Riccati equations; bidirectionally connected layers; closed-loop control systems; linear-quadratic optimal control systems; multilayer recurrent neural network; operating characteristics; real-time synthesis; Control system synthesis; Control systems; Matrices; Multi-layer neural network; Network synthesis; Neurons; Optimal control; Real time systems; Recurrent neural networks; Riccati equations;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on

Conference_Location

Orlando, FL

Print_ISBN

0-7803-1901-X

Type

conf

DOI

10.1109/ICNN.1994.374614

Filename

374614