ICONIP 2006: Neural Information Processing pp 674-683 | Cite as
Reliable Robust Controller Design for Nonlinear State-Delayed Systems Based on Neural Networks
Conference paper
Abstract
An approach is investigated for the adaptive guaranteed cost control design for a class of nonlinear state-delayed systems. The nonlinear term is approximated by a linearly parameterized neural networks(LPNN). A linear state feedback H ∞ control law is presented. An adaptive weight adjustment mechanism for the neural networks is developed to ensure H ∞ regulation performance. It is shown that the control gain matrices and be transformed into a standard linear matrix inequality problem and solved via a developed recurrent neural network.
Keywords
Neural Network Wavelet Network Multilayer Neural Network State Space Approach Linear State Feedback
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
Preview
Unable to display preview. Download preview PDF.
References
- 1.Suykens, J.A.K., Vandewalle, J., De Moor, B.: Artificial neural networks for modelling and control of nonlinear systems. Kluwer Academic Publishers, Boston (1996)Google Scholar
- 2.Bass, E., Lee, K.Y.: Robust control of nonlinear system using norm-bounded neural networks. In: IEEE Int. Conf. on Neural Networks, vol. 4, pp. 2524–2529 (1994)Google Scholar
- 3.Lin, C.L.: Control of perturbed systems using neural networks. IEEE trans. Neural Netw. (9), 1046–1050 (1998)CrossRefGoogle Scholar
- 4.Suykens, J.A.K., Vandewalle, J., De Moor, B.: Artificial Neural Networks for Modelling and Control of nonlinear system. Kluwer, Norwell (1996)Google Scholar
- 5.Suykens, J.A.K., Vandewalle, J., De Moor, B.: Lur’s systems with multilayer perceptron and recurrent neural networks: Absolute stability and dissipativity. IEEE Trans. Automat. Contr. (44), 770–774 (1999)CrossRefMATHGoogle Scholar
- 6.Tanaka, K.: An approach to stability criteria of neural-network control systems. IEEE Trans. Neural Netw. (7), 629–642 (1996)CrossRefGoogle Scholar
- 7.Leu, Y.G., Lee, T.T., Wang, W.Y.: Online tuning of fuzzy-neural network for adaptive control of nonlinear dynamical systems. IEEE Trans. Syst. Man. Cybern. Part B (27), 1034–1043 (1997)CrossRefGoogle Scholar
- 8.Limanond, S., Si, J.: Neural-network-based control design: an LMI approach. IEEE Trans. Neural Netw. 9, 1429–1442 (1998)CrossRefGoogle Scholar
- 9.Suykens, J.A.K., Vandewalle, J., De Moor, B.: Artificial Neural Networks for Modelling and Control of Nonlinear Systems. Kluwer Academic Publishers, Norwell (1996)Google Scholar
- 10.Lin, C.-L., Lin, T.-Y.: An Design Approach for Neural Net-based Control Schemes. IEEE Trans. On. Automatic control (46), 1599–1605 (2001)CrossRefMATHGoogle Scholar
- 11.Lin, C.-L., L., T.-Y.: Approach to adaptive neural net-based H ∞ control design. IEE Proc.-Control Theory Appl. (4), 331–342 (2002)CrossRefGoogle Scholar
- 12.Dugard, L., Verriest, E.I.: Stability and control of time-delay systems, Prentice Hall, Springer-Verlag, Berlin (1997)Google Scholar
- 13.Lee, J.H., Kim, S.W., Kwon, W.H.: Memoryless H ∞ controllers for state delayed systems. IEEE Trans. Autom. Control (39), 159–162 (1994)CrossRefMATHMathSciNetGoogle Scholar
- 14.Niculescu, S.I.: H ∞ memoryless control with an a-stability constraint for time-delay systems: An LMI approach. IEEE Trans. Autom. Control (43), 739–748 (1998)CrossRefMATHMathSciNetGoogle Scholar
- 15.Choi, H.H., Chong, M.J.: An LMI approach to H ∞ controller design for linear time-delays. Automatical (3), 737–739 (1997)CrossRefGoogle Scholar
- 16.Kosmatopoulos, E.B., Polycarpou, M.M., Christodoulou, M.A., Ioan, P.A.: High-order neural networks structures for identification of dynamical systems. IEEE Trans. Neural Networks 6, 422–431 (1995)CrossRefGoogle Scholar
- 17.Sanner, R.M., Slotine, J.J.E.: Structurally dynamic wavelet networks for the adaptive control of uncertain robotic systems. In: Proc. IEEE 34th Conf. Decision and Control, New Orleans, LA, pp. 2460–2467 (December 1995)Google Scholar
- 18.Polycarpou, M.M., Ioannou, P.A.: Identification and control of nonlinear systems using neural network models: Design and stability analysis, Dept. Eng. Sys., Southern Calif., Los Angeles, Tech. Rep. (1991)Google Scholar
- 19.Sanchez, E.N., Perez, J.P.: Input-to-state stability (ISS) analysis for dynamic NN. IEEE Trans. Circuits Syst. I (46), 1395–1398 (1999)CrossRefMATHMathSciNetGoogle Scholar
- 20.Boyd, S., Ghaoui, L.E., Feron, E., Balakrishnan, V.: Linear matrix inequality in system and control theory. SIAM, Philadelphia (1994)Google Scholar
- 21.Stewart, G.W.: Introduction to matrix computation. Academic Press, Orlando (1973)Google Scholar
- 22.Chun-Liang, L., Chi-Chih, L., Teng-Hsien, H.: A neural networks for linear matrix inequality problems. IEEE Trans. On neural networks (11), 1078–1092 (2000)CrossRefGoogle Scholar
- 23.Stoorvogel, A.: The H ∞ Control Problem: A state Space Approach. Prentice-Hall, Upper Saddle River (1992)MATHGoogle Scholar
- 24.Marcus, C.M., Westervelt, R.M.: Stability of analog neural networks with time delay. Phys. Rev. A 39, 347–359 (1989)MathSciNetGoogle Scholar
- 25.Campbell, S.A., Driessche, P.: Frustration: stability and delay induced oscillations in a neural network model. SIAM J. Appl. Math. 56, 245–255 (1996)CrossRefMATHMathSciNetGoogle Scholar
- 26.Baldi, P., Atiya, A.F.: How delays affect neural dynamics and learning. IEEE Trans. Neural Networks (5), 612–621 (1994)CrossRefGoogle Scholar
- 27.Stoorvogel, A.: The H ∞ Control Problem: A State Space Approach. Prentice-Hall, Upper Saddle River (1992)MATHGoogle Scholar
Copyright information
© Springer-Verlag Berlin Heidelberg 2006