Title :
Neuro-based optimal regulator for a class of system with uncertainties
Author :
Xu, Bing Bong ; Tsuji, Toshio ; Hatagi, Michio ; Kaneko, Makoto
Author_Institution :
Fac. of Eng., Hiroshima Univ., Japan
Abstract :
This paper proposes a neuro-based optimal regulator (NBOR) for a class of system with uncertainties. In this paper, we show how the neural network output compensates the control input based on the Riccati equation and how the compensatory solution of the Riccati equation is estimated by the least-squares method. Then, the NBOR is applied to systems with uncertainties in order to illustrate its effectiveness and applicability
Keywords :
Riccati equations; compensation; least squares approximations; neurocontrollers; optimal control; uncertain systems; NBOR; Riccati equation; compensatory solution; least-squares estimation; neuro-based optimal regulator; uncertainties; Control system synthesis; Control systems; Neural networks; Nonlinear control systems; Nonlinear dynamical systems; Optimal control; Regulators; Riccati equations; Robust control; Uncertainty;
Conference_Titel :
Industrial Technology, 1996. (ICIT '96), Proceedings of The IEEE International Conference on
Conference_Location :
Shanghai
Print_ISBN :
0-7803-3104-4
DOI :
10.1109/ICIT.1996.601683
