Constrained optimal control of bilinear systems using neural network based HJB solution

Author

Adhyaru, Dipak M. ; Kar, I.N. ; Gopal, M.

Author_Institution

Dept. of Electr. Eng., Indian Inst. of Technol., New Delhi

fYear

2008

fDate

1-8 June 2008

Firstpage

4137

Lastpage

4142

Abstract

In this paper, a Hamilton-Jacobi-Bellman (HJB) equation based optimal control algorithm is proposed for a bilinear system. Utilizing the Lyapunov direct method, the controller is shown to be optimal with respect to a cost functional, which includes penalty on the control effort and the system states. In the proposed algorithm, Neural Network (NN) is used to find approximate solution of HJB equation using least squares method. Proposed algorithm has been applied on bilinear systems. Necessary theoretical and simulation results are presented to validate proposed algorithm.

Keywords

Lyapunov methods; least squares approximations; neurocontrollers; nonlinear control systems; optimal control; Hamilton-Jacobi-Bellman equation; Lyapunov direct method; bilinear systems; constrained optimal control; least squares method; neural network; Control systems; Cost function; Equations; Feedback control; Least squares methods; Lyapunov method; Neural networks; Nonlinear systems; Optimal control; Stability;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2008. IJCNN 2008. (IEEE World Congress on Computational Intelligence). IEEE International Joint Conference on

Conference_Location

Hong Kong

ISSN

1098-7576

Print_ISBN

978-1-4244-1820-6

Electronic_ISBN

1098-7576

Type

conf

DOI

10.1109/IJCNN.2008.4634394

Filename

4634394