Article
Real-Time Nonlinear Optimal Control using Neural Networks
Proceedings of the American Control Conference (1994, Baltimore, MD)
Abstract
In this paper, a neural network based controller which optimizes a finite horizon quadratic cost function is developed for a class of nonlinear systems. The controller converges to its optimal value real-time eliminating the need for a priori knowledge of the nonlinearity and the initial conditions. The method makes use of the optimality conditions obtained from the Hamiltonian directly. These conditions are realized by a series of neural networks which converge to the optimal control iteratively in real-time. A nonlinear system to demonstrate its applicability is also included.
Meeting Name
American Control Conference (1994: Jun. 29-Jul. 1, Baltimore, MD)
Department(s)
Electrical and Computer Engineering
Sponsor(s)
National Science Foundation (U.S.)
United States. Army Research Office
University of Missouri--Rolla. Intelligent Systems Center
Keywords and Phrases
- Computer simulation,
- Control nonlinearities,
- Control theory,
- Finite element method,
- Mathematical models,
- Nonlinear control systems,
- Optimal control systems,
- Optimization,
- Real time systems,
- Dynamical systems,
- Finite horizon quaratic cost function,
- Optimality conditions,
- Real time nonlinear optimal control,
- Neural networks
International Standard Book Number (ISBN)
0-780317831
Document Type
Article - Conference proceedings
Document Version
Citation
File Type
text
Language(s)
English
Rights
© 1994 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.
Publication Date
6-1-1994
Publication Date
01 Jun 1994
Disciplines
Citation Information
Jaipaul K. Antony and Levent Acar. "Real-Time Nonlinear Optimal Control using Neural Networks" Proceedings of the American Control Conference (1994, Baltimore, MD) Vol. 3 (1994) p. 2926 - 2930 ISSN: 0743-1619 Available at: http://works.bepress.com/levent-acar/35/
This work has been partially supported by NSF Grant NSF ECS-9309486, by ARO Grant DAAHO4-93-G-0214, and by the Intelligent Systems Center of the University of Missouri-Rolla.