DocumentCode :
487778
Title :
Adaptive Control of Unknown Dynamical Systems via Neural Network Approach
Author :
Lan, Ming-Shong
Author_Institution :
Rockwell International Science Center, Thousand Oaks, CA 91360
fYear :
1989
fDate :
21-23 June 1989
Firstpage :
910
Lastpage :
915
Abstract :
The feasibility of using an artificial neural network for controlling an unknown dynamical plant is investigated. A layered neural network is employed to learn the inverse dynamics of the unknown dynamical plant and acts as a feedforward controller to control the plant. This inverse dynamics is represented by the connection weights between the layers; these weights are adjusted based on the difference between the actual control input to the plant and the estimated input for achieving an actual plant output according to the inverse-dynamics model. The error back propagation scheme and the delta rule are used in the learning process. Simulation results are in this paper.
Keywords :
Adaptive control; Artificial neural networks; Biological neural networks; Control systems; Error correction; Feedback loop; Manipulators; Neural networks; Programmable control; Robot kinematics;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
American Control Conference, 1989
Conference_Location :
Pittsburgh, PA, USA
Type :
conf
Filename :
4790320
Link To Document :
بازگشت