DocumentCode
2430013
Title
Time optimal control using CMAC neural networks
Author
Kraft, L.G. ; Dietz, Darryl
Author_Institution
Dept. of Electr. Eng., New Hampshire Univ., Durham, NH, USA
Volume
3
fYear
1994
fDate
29 June-1 July 1994
Firstpage
2943
Abstract
A particular form of neural network called CMAC has been shown to have many characteristics well-suited to real time control problems. In this paper, the CMAC concept is applied to a time optimal control problem. An example system (DC servomotor) is analyzed using both simulation and real-time laboratory experiments. The neural network based controller is capable of handling both linear and nonlinear systems, is very efficient in real-time operation and the results extend to higher order systems.
Keywords
DC motors; cerebellar model arithmetic computers; machine control; neurocontrollers; real-time systems; servomotors; time optimal control; CMAC neural networks; DC servomotor; real time control; switching curve learning; time optimal control; Analytical models; Computational complexity; Control systems; Laboratories; Neural networks; Nonlinear control systems; Nonlinear systems; Optimal control; Real time systems; Servomotors;
fLanguage
English
Publisher
ieee
Conference_Titel
American Control Conference, 1994
Print_ISBN
0-7803-1783-1
Type
conf
DOI
10.1109/ACC.1994.735108
Filename
735108
Link To Document