An input-output based robust stabilization criterion for neural-network control of nonlinear systems

IEEE Transactions on Neural Networks

Volumn 12, Issue 6, 2001, Pages 1491-1497

  De Fernandez Canete J ^a   Barreiro, A ^b   Garcia Cerezo A ^a   Garcia Moral I ^a  

^a UNIVERSITY OF MÁLAGA   (Spain)

^b UNIVERSITY OF VIGO   (Spain)

Author keywords

Conicity criterion; Neural control; Robustness; Stabilization

Indexed keywords

CLOSED LOOP CONTROL SYSTEMS; FEEDBACK CONTROL; LEARNING ALGORITHMS; LYAPUNOV METHODS; NONLINEAR CONTROL SYSTEMS; ROBUSTNESS (CONTROL SYSTEMS); STABILITY CRITERIA; SYSTEM STABILITY; THEOREM PROVING; TRANSFER FUNCTIONS;

CONICITY CRITERION; NEURAL CONTROL;

NEURAL NETWORKS;

EID: 0035506245     PISSN: 10459227     EISSN: None     Source Type: Journal    
DOI: 10.1109/72.963785     Document Type: Article

References (18)

1. First- and second-order methods for learning: Between steepest descent and Newton's method
2. Approximation by superposition of sigmoidal functions
3. Robust stability of fuzzy control systems based on conicity conditions
4. Stability analysis of dynamical neural networks
5. Amodified backpropagation method to avoid false local minima
6. Robustness analysis of nonlinear feedback systems and input-output approach
7. Networks and the best approximation property
8. Explicit constructions of quadratic Lyapunov functions for the small-gain, positivity, circle and Popov theorems, and their applications to robust stability
9. Degree of approximation results for feedforward networks approximating unknown mappings and their derivatives
10. Robust design of rule-based fuzzy controllers
11. Nlq theory: A neural control framework with global asymptotic stability criteria
12. Lur'e systems with multilayer perceptron and recurrent neural networks: Absolute stability and dissipativity
13. On graphs, conic relations and input-output stability of nonlinear feedback systems
14. Stable control of nonlinear systems using neural networks
15. New relationship between input-output and Lyapunov stability