Research upon Multistage Optimal Control by Wavelet Neural Network

Author

Hu, Xiaoping ; Lue, Hongsheng ; He, Jianmin

Author_Institution

Dept. of Manage. Sci. & Eng., Southeast Univ., Nanjing

Volume

1

fYear

0

fDate

0-0 0

Firstpage

2655

Lastpage

2658

Abstract

For having stronger learning and generalizing power of functions, wavelet neural network (WNN) can solve multistage optimal control problem. In the course of solving, optimal control law was fitted by using WNN, and a Lagrangian function was constructed to translate into optimization problem from optimal control one. A weight factor was introduced to regulate tradeoff between control system and fit performance by utilizing WNN from the state space to the action space, and then the optimal control performance was reached. Simulation example shows that WNN can solve the multistage optimal control problem better, and different value of weight factor affects the simulation result

Keywords

generalisation (artificial intelligence); learning (artificial intelligence); multivariable control systems; optimal control; optimisation; state-space methods; wavelet transforms; Lagrangian function; action space; control system; generalization; learning; multistage optimal control; optimization; state space; wavelet neural network; Control systems; Electronic mail; Energy management; Engineering management; Helium; Lagrangian functions; Neural networks; Optimal control; Power engineering and energy; State-space methods; lagrangian function; multistage optimal control; optimization; wavelet neural network;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Control and Automation, 2006. WCICA 2006. The Sixth World Congress on

Conference_Location

Dalian

Print_ISBN

1-4244-0332-4

Type

conf

DOI

10.1109/WCICA.2006.1712844

Filename

1712844