Design of Predictive Controllers by Dynamic Programming and Neural Networks

Authors

Chen-Wen Yen, National Sun Yat-Sen UniversityFollow
Mark L. Nagurka, Marquette UniversityFollow

Document Type

Conference Proceeding

Language

eng

Publication Date

6-4-2003

Publisher

Institute of Electrical and Electronic Engineers (IEEE)

Source Publication

Proceedings of the 2003 American Control Conference

Source ISSN

0743-1619

Abstract

This paper proposes a method for the design of predictive controllers for nonlinear systems. The method consists of two phases, a solution phase and a learning phase. In the solution phase, dynamic programming is applied to obtain a closed-loop control law. In the learning phase, neural networks are used to simulate the control law. This phase overcomes the "curse of dimensionality" problem that has often hindered the implementation of control laws generated by dynamic programming. Experimental results demonstrate the effectiveness of the method

Comments

Accepted version. Published as a part of Proceedings of the 2003 American Control Conference, June 4-6, 2003. DOI. © 2003 IEEE. Used with permission.

Recommended Citation

Yen, Chen-Wen and Nagurka, Mark L., "Design of Predictive Controllers by Dynamic Programming and Neural Networks" (2003). Mechanical Engineering Faculty Research and Publications. 225.
https://epublications.marquette.edu/mechengin_fac/225