Robust quasi-LPV control based on neural state-space models

IEEE Transactions on Neural Networks

Volumn 13, Issue 2, 2002, Pages 355-368

  Bendtsen, Jan Dimon ^a   Trangbæk, Klaus ^b  

^a AALBORG UNIVERSITY   (Denmark)

^b Mechanical Development   (Denmark)

Author keywords

Linear fractional transformation (LFT); Linear matrix inequalities (LMIs); Multilayer perceptrons (MLPs); Neural networks; Quasi linear parameter varying (LPV) control

Indexed keywords

CONSTRAINT THEORY; FEEDBACK CONTROL; NONLINEAR SYSTEMS; ROBUSTNESS (CONTROL SYSTEMS); STATE SPACE METHODS;

LINEAR FRACTIONAL TRANSFORMATION (LFT); QUASI LINEAR PARAMETER VARYING (LPV) CONTROL;

NEURAL NETWORKS;

EID: 0036505996     PISSN: 10459227     EISSN: None     Source Type: Journal    
DOI: 10.1109/72.991421     Document Type: Article

References (26)

1. Transformation of neural state-space models into LFT models for robust control design
2. Issues in the application of neural networks for tracking based on inverse control
3. Gain scheduling control of nonlinear plant using a RBF neural network
4. Adaptive control of a class of nonlinear discrete-time systems using neural networks
5. Input-output stability theory for direct neurofuzzy controllers
6. A neural approach for control of non-linear systems with feedback linearization
7. A dynamic recurrent neural-network-based adaptive observer for a class of nonlinear systems
8. Control of nonlinear dynamical systems using neural network: Controllability and stabilization
9. Using neural networks to improve gain scheduling techniques for linear parameter-varying systems
10. Robust nonlinear system identification using neural-network models
11. Stable local neural control of un-certain systems
12. Gain scheduling via linear fractional transformations
13. The complex structured singular value
14. Research on gain scheduling
15. LPV control and full block multipliers
16. Robust mixed control and LPV control and full block scalings
17. Stable neural controllers for nonlinear dynamic systems
18. Nonlinear system identification using neural state-space models, applicable in robust control design
19. Global asymptotic stability criteria for multilayer recurrent neural networks with applications to modeling and control
20. Lur'e systems with multilayer perceptron and recurrent neural networks: Absolute stability and dissipativity