A hyperstable neural network for the modelling and control of nonlinear systems
A multivariable hyperstable robust adaptive decoupling control algorithm based on a neural network is presented for the control of nonlinear multivariable coupled systems with unknown parameters and structure. The Popov theorem is used in the design of the controller. The modelling errors, coupling action and other uncertainties of the system are identified on-line by a neural network. The identified results are taken as compensation signals such that the robust adaptive control of nonlinear systems is realised. Simulation results are given.
KeywordsComputer control neural networks nonlinear systems adaptive control
Unable to display preview. Download preview PDF.
- Garces F, Warwick K, Craddock C 1998 Multiple PID mapping using neural networks in a MIMO generator system.Proc. Int. Conf. Control 98, Swansea, pp 503-508Google Scholar
- Guonam F, Rui Y 1989 A microcomputer controller optimal adaptive flight simulator servo system.Acta Autom. Sin. 15: 193–199Google Scholar
- Hunt K J, Irwin G W, Warwick K (eds) 1995Neural network engineering in dynamic control systems (Berlin: Springer-Verlag).Google Scholar
- Karny M, Warwick K, Kurkova V (eds) 1998Dealing with complexity: a neural network approach (New York: Springer-Verlag)Google Scholar
- Narendra K S 1991 Adaptive control using neural networks. InNeural networks for control (eds) W T Miller, R S Sutton, P W Werbos (Cambridge, MA: MIT Press) pp 115–142Google Scholar
- Praly L 1983 Robustness of model reference adaptive control.Proc. 3rd Yale Workshop on the Applications of Adaptive Systems Theory, Yale University, New Haven, CTGoogle Scholar
- Rohrs C E, Valavani L, Athans M, Stein G 1982 Robustness of adaptive control algorithms in the presence of unmodelled dynamics.Proc. 21st IEEE Conf. Decision & Control, Orlando, Florida, pp3-llGoogle Scholar