Title :
A training rule which guarantees finite-region stability for a class of closed-loop neural-network control systems
Author :
Kuntanapreeda, Suwat ; Fullmer, R. Rees
Author_Institution :
Center for Self Organizing & Intelligent Syst., Utah State Univ., Logan, UT, USA
fDate :
5/1/1996 12:00:00 AM
Abstract :
A training method for a class of neural network controllers is presented which guarantees closed-loop system stability. The controllers are assumed to be nonlinear, feedforward, sampled-data, full-state regulators implemented as single hidden-layer neural networks. The controlled systems must be locally hermitian and observable. Stability of the closed-loop system is demonstrated by determining a Lyapunov function, which can be used to identify a finite stability region about the regulator point
Keywords :
Lyapunov methods; closed loop systems; feedforward neural nets; learning (artificial intelligence); neurocontrollers; nonlinear control systems; sampled data systems; stability; stability criteria; Lyapunov function; closed-loop neural-network control systems; guaranteed finite-region stability; locally hermitian systems; nonlinear feedforward sampled-data full-state regulators; observable systems; single hidden-layer neural networks; training rule; Adaptive control; Control systems; Feedforward neural networks; Lyapunov method; Neural networks; Nonlinear systems; Regulators; Shape control; Sliding mode control; Stability;
Journal_Title :
Neural Networks, IEEE Transactions on
