Neural-network predictive control for nonlinear dynamic systems with time-delay

A new recurrent neural-network predictive feedback control structure for a class of uncertain nonlinear dynamic time-delay systems in canonical form is developed and analyzed. The dynamic system has constant input and feedback time delays due to a communications channel. The proposed control structure consists of a linearized subsystem local to the controlled plant and a remote predictive controller located at the master command station. In the local linearized subsystem, a recurrent neural network with on-line weight tuning algorithm is employed to approximate the dynamics of the time-delay-free nonlinear plant. No linearity in the unknown parameters is required. No preliminary off-line weight learning is needed. The remote controller is a modified Smith predictor that provides prediction and maintains the desired tracking performance; an extra robustifying term is needed to guarantee stability. Rigorous stability proofs are given using Lyapunov analysis. The result is an adaptive neural net compensation scheme for unknown nonlinear systems with time delays. A simulation example is provided to demonstrate the effectiveness of the proposed control strategy.

[1]  Léon Personnaz,et al.  Nonlinear internal model control using neural networks: application to processes with delay and design issues , 2000, IEEE Trans. Neural Networks Learn. Syst..

[2]  B. Bequette.  Nonlinear control of chemical processes: a review , 1991 .

[3]  Petar V. Kokotovic,et al.  Instability analysis and improvement of robustness of adaptive control , 1984, Autom..

[4]  D. Himmelblau,et al.  Identification of Nonlinear Dynamic Processes with Unknown and Variable Dead Time Using an Internal Recurrent Neural Network , 1995 .

[5]  Blake Hannaford,et al.  Force reflection, shared control, and time delay in telemanipulation , 1989, Conference Proceedings., IEEE International Conference on Systems, Man and Cybernetics.

[6]  Thomas B. Sheridan,et al.  Space teleoperation through time delay: review and prognosis , 1993, IEEE Trans. Robotics Autom..

[7]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[8]  Shuzhi Sam Ge,et al.  Adaptive output feedback control for general nonlinear systems using multilayer neural networks , 1998, Proceedings of the 1998 American Control Conference. ACC (IEEE Cat. No.98CH36207).

[9]  Frank L. Lewis,et al.  Control of Robot Manipulators , 1993 .

[10]  D. Seborg,et al.  Control strategy for single-input single-output non-linear systems with time delays , 1988 .

[11]  Marios M. Polycarpou,et al.  High-order neural network structures for identification of dynamical systems , 1995, IEEE Trans. Neural Networks.

[12]  Frank L. Lewis,et al.  High-Level Feedback Control with Neural Networks , 1998, World Scientific Series in Robotics and Intelligent Systems.

[13]  Léon Personnaz,et al.  Internal model control using neural networks , 1996, Proceedings of IEEE International Symposium on Industrial Electronics.

[14]  Frank L. Lewis,et al.  Neural net robot controller with guaranteed tracking performance , 1995, IEEE Trans. Neural Networks.

[15]  Manfred Morari,et al.  Smith Predictor Design for Robust Performance , 1987, 1987 American Control Conference.

[16]  Mark W. Spong,et al.  Bilateral control of teleoperators with time delay , 1988, Proceedings of the 1988 IEEE International Conference on Systems, Man, and Cybernetics.

[17]  D. H. Mee.  An extension of predictor control for systems with control time-delays , 1973 .

[18]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[19]  K. Narendra,et al.  A New Adaptive Law for Robust Adaptation without Persistent Excitation , 1986, 1986 American Control Conference.

[20]  Ken-ichi Funahashi,et al.  On the approximate realization of continuous mappings by neural networks , 1989, Neural Networks.

[21]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1989, Math. Control. Signals Syst..

[22]  Costas Kravaris,et al.  Deadtime compensation for nonlinear processes , 1989 .

[23]  Dale E. Seborg,et al.  Time delay compensation for nonlinear processes , 1994 .

[24]  Tao Zhang,et al.  Nonlinear adaptive control using neural networks and its application to CSTR systems , 1999 .

[25]  Weibiao Zhou,et al.  A NEW MULTIVARIABLE DEADTIME CONTROL ALGORITHM , 1990 .

[26]  D. Seborg,et al.  An extension of the Smith Predictor method to multivariable linear systems containing time delays , 1973 .

[27]  K S Narendra,et al.  IDENTIFICATION AND CONTROL OF DYNAMIC SYSTEMS USING NEURAL NETWORKS , 1990 .

[28]  Frank L. Lewis,et al.  Neural Network Control Of Robot Manipulators And Non-Linear Systems , 1998 .

[29]  Frank L. Lewis,et al.  Multilayer neural-net robot controller with guaranteed tracking performance , 1996, IEEE Trans. Neural Networks.

[30]  Frank L. Lewis,et al.  Output feedback control of rigid robots using dynamic neural networks , 1996, Proceedings of IEEE International Conference on Robotics and Automation.

[31]  M. Malek-Zavarei,et al.  Time-Delay Systems: Analysis, Optimization and Applications , 1987 .

[32]  Zalman J. Palmor,et al.  Stability properties of Smith dead-time compensator controllers , 1980 .

[33]  Thomas B. Sheridan,et al.  A model-based predictive operator aid for telemanipulators with time delay , 1989, Conference Proceedings., IEEE International Conference on Systems, Man and Cybernetics.

[34]  Peter J. Gawthrop,et al.  Neural networks for control systems - A survey , 1992, Autom..

[35]  O Smith,et al.  CLOSER CONTROL OF LOOPS WITH DEAD TIME , 1957 .

[36]  Kumpati S. Narendra,et al.  Identification and control of dynamical systems using neural networks , 1990, IEEE Trans. Neural Networks.

[37]  Malur K. Sundareshan,et al.  Identification and decentralized adaptive control using dynamical neural networks with application to robotic manipulators , 1993, IEEE Trans. Neural Networks.