Stable adaptive control with recurrent neural networks for square MIMO non-linear systems
作者： Salem Zerkaoui , Fabrice Druaux , Edouard Leclercq , Dimitri Lefebvre
DOI: 10.1016/J.ENGAPPAI.2008.12.005
关键词:
摘要: In this paper, stable indirect adaptive control with recurrent neural networks is presented for square multivariable non-linear plants unknown dynamics. The scheme made of an instantaneous model, a controller based on fully connected ''Real-Time Recurrent Learning'' (RTRL) and online parameters updating law. Closed-loop performances as well sufficient conditions asymptotic stability are derived from the Lyapunov approach according to rate parameter. Robustness also considered in terms sensor noise model uncertainties. then applied Tennessee Eastman Challenge Process order illustrate efficiency proposed method real-world problems.
acm.org
elsevier.com
sci-hub.se 参考文章(26)
William S. Levine, The Control Handbook ,(2005)
David Zipser, Ronald J. Williams, Gradient-based learning algorithms for recurrent networks and their computational complexity Backpropagation. pp. 433- 486 ,(1995)
Ken-Ichi Funahashi, On the approximate realization of continuous mappings by neural networks Neural Networks. ,vol. 2, pp. 183- 192 ,(1989) , 10.1016/0893-6080(89)90003-8
Dianhui Wang, Paul Bao, Enhancing the estimation of plant Jacobian for adaptive neural inverse control Neurocomputing. ,vol. 34, pp. 99- 115 ,(2000) , 10.1016/S0925-2312(00)00319-2
Edouard Leclercq, Fabrice Druaux, Dimitri Lefebvre, Salem Zerkaoui, Autonomous learning algorithm for fully connected recurrent networks Neurocomputing. ,vol. 63, pp. 25- 44 ,(2005) , 10.1016/J.NEUCOM.2004.04.007
Wing-Fai Chang, Man-Wai Mak, A conjugate gradient learning algorithm for recurrent neural networks Neurocomputing. ,vol. 24, pp. 173- 189 ,(1999) , 10.1016/S0925-2312(98)00104-0
J.J. Downs, E.F. Vogel, A plant-wide industrial process control problem Computers & Chemical Engineering. ,vol. 17, pp. 245- 255 ,(1993) , 10.1016/0098-1354(93)80018-I
Ronald J. Williams, David Zipser, A learning algorithm for continually running fully recurrent neural networks Neural Computation. ,vol. 1, pp. 270- 280 ,(1989) , 10.1162/NECO.1989.1.2.270
Jin Wang, Sensitivity identification enhanced control strategy for nonlinear process systems Computers & Chemical Engineering. ,vol. 27, pp. 1631- 1640 ,(2003) , 10.1016/S0098-1354(03)00117-0
Barbara Hammer, On the approximation capability of recurrent neural networks Neurocomputing. ,vol. 31, pp. 107- 123 ,(2000) , 10.1016/S0925-2312(99)00174-5