The H∞ control problem
Artificial Neural Networks for Modelling and Control of Non-Linear Systems
Artificial Neural Networks for Modelling and Control of Non-Linear Systems
Reliable robust controller design for nonlinear state-delayed systems based on neural networks
ICONIP'06 Proceedings of the 13th international conference on Neural information processing - Volume Part III
Neural adaptive regulation of unknown nonlinear dynamical systems
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Robust neural adaptive stabilization of unknown systems withmeasurement noise
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
A neural network for linear matrix inequality problems
IEEE Transactions on Neural Networks
High-order neural network structures for identification of dynamical systems
IEEE Transactions on Neural Networks
Switching fuzzy dynamic output feedback H∞ control for nonlinear systems
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
| Hi-index | 0.00 |
In this paper, a new approach is investigated for adaptivedynamic neural network-based H∞ control,which is designed for a class of non-linear systems with unknownuncertainties. Currently, non-linear systems with unknownuncertainties are commonly used to efficiently and accuratelyexpress the real practical control process. Therefore, it is ofcritical importance but a great challenge and still at its earlyage to design a stable and robust controller for such a process. Inthe proposed research, dynamic neural networks were constructed toprecisely approximate the non-linear system with unknownuncertainties first, a non-linear state feedbackH∞ control law was designed next, then anadaptive weighting adjustment mechanism for dynamic neural networkswas developed to achieve H∞ regulationperformance, and last a recurrent neural network was employed as aneuro-solver to efficiently and numerically solve the standard LMIproblem so as to obtain the appropriate control gains. Finally,case studies further verify the feasibility and efficiency of theproposed research.