Discrete-time systems neuro-Riccati equation solution

Author

Tamariz, Annabell D R ; Bottura, Celso P.

Author_Institution

Nucleus of Res. & Dev. in Comput. Sci., Cndido Mendes Univ., Brazil

Volume

4

fYear

2005

fDate

July 31 2005-Aug. 4 2005

Firstpage

2261

Abstract

In this article proposal for solving the discrete-time algebraic Riccati equation (DARE) using a multilayer recurrent neural network (RNN) approach is presented. Systems of coupled matricial nonlinear differential equations are derived describing the neural dynamics of the Neuro-riccati equation. By solving these coupled matrix equations using recurrent neural networks a symmetric and positive definite solution is obtained. Several examples demonstrate the effectiveness of this proposal and respective implementation.

Keywords

Riccati equations; discrete time systems; neurocontrollers; nonlinear differential equations; recurrent neural nets; discrete-time algebraic Riccati equation; discrete-time system; multilayer recurrent neural network; neuro-Riccati equation solution; nonlinear differential equations; Computer networks; Control systems; Couplings; Differential algebraic equations; Multi-layer neural network; Nonlinear equations; Proposals; Recurrent neural networks; Riccati equations; Symmetric matrices;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2005. IJCNN '05. Proceedings. 2005 IEEE International Joint Conference on

Conference_Location

Montreal, Que.

Print_ISBN

0-7803-9048-2

Type

conf

DOI

10.1109/IJCNN.2005.1556253

Filename

1556253