An approach to stability criteria of neural-network control systems
- 1 May 1996
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 7 (3) , 629-642
- https://doi.org/10.1109/72.501721
Abstract
This paper discusses stability of neural network (NN)-based control systems using Lyapunov approach. First, it is pointed out that the dynamics of NN systems can be represented by a class of nonlinear systems treated as linear differential inclusions (LDI). Next, stability conditions for the class of nonlinear systems are derived and applied to the stability analysis of single NN systems and feedback NN control systems. Furthermore, a method of parameter region (PR) representation, which graphically shows the location of parameters of nonlinear systems, is proposed by introducing new concepts of vertex point and minimum representation. From these concepts, an important theorem, which is useful for effectively finding a Lyapunov function, is derived. Stability criteria of single NN systems are illustrated in terms of PR representation. Finally, stability of feedback NN control systems, which consist of a plant represented by an NN and an NN controller, is analyzed.Keywords
This publication has 11 references indexed in Scilit:
- An approach to stability analysis of second order fuzzy systemsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Adaptive model-based neural network controlPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Linear Matrix Inequalities in System and Control TheoryPublished by Society for Industrial & Applied Mathematics (SIAM) ,1994
- Fuzzy stability criterion of a class of nonlinear systemsInformation Sciences, 1993
- Stability analysis and design of fuzzy control systemsFuzzy Sets and Systems, 1992
- Neural network controller characteristics with regard to adaptive controlIEEE Transactions on Systems, Man, and Cybernetics, 1992
- Identification and control of dynamical systems using neural networksIEEE Transactions on Neural Networks, 1990
- Neural network architectures for robotic applicationsIEEE Transactions on Robotics and Automation, 1989
- A multilayered neural network controllerIEEE Control Systems Magazine, 1988
- Fuzzy identification of systems and its applications to modeling and controlIEEE Transactions on Systems, Man, and Cybernetics, 1985