Neural network solution for finite-horizon H-infinity constrained optimal control of nonlinear systems

In this paper, neural networks are used to approximately solve the finite-horizon constrained input H-infinity state feedback control problem. The method is based on solving a related Hamilton-Jacobi-Isaacs equation of the corresponding finite-horizon zero-sum game. The game value function is approximated by a neural network with time-varying weights. It is shown that the neural network approximation converges uniformly to the game-value function and the resulting almost optimal constrained feedback controller provides closed-loop stability and bounded L2 gain. The result is an almost optimal H-infinity feedback controller with time-varying coefficients that is solved a priori off-line. The effectiveness of the method is shown on the Rotational/Translational Actuator benchmark nonlinear control problem.

[1]  Robert T. Bupp s,et al.  A BENCHMARK PROBLEM FOR NONLINEAR CONTROL DESIGN , 1998 .

[2]  Randal W. Beard,et al.  Galerkin approximations of the generalized Hamilton-Jacobi-Bellman equation , 1997, Autom..

[3]  D. Bernstein.  Nonquadratic cost and nonlinear feedback control , 1993 .

[4]  Jean-Jacques E. Slotine,et al.  Stable adaptive control and recursive identification using radial Gaussian networks , 1991, [1991] Proceedings of the 30th IEEE Conference on Decision and Control.

[5]  Chen-Chung Liu,et al.  Adaptively controlling nonlinear continuous-time systems using multilayer neural networks , 1994, IEEE Trans. Autom. Control..

[6]  F. Lewis,et al.  Hamilton-Jacobi-Isaacs formulation for constrained input nonlinear systems , 2004, 2004 43rd IEEE Conference on Decision and Control (CDC) (IEEE Cat. No.04CH37601).

[7]  Shuzhi Sam Ge.  Robust adaptive NN feedback linearization control of nonlinear systems , 1996, Int. J. Syst. Sci..

[8]  B. Finlayson.  The method of weighted residuals and variational principles : with application in fluid mechanics, heat and mass transfer , 1972 .

[9]  A. Isidori,et al.  Disturbance attenuation and H/sub infinity /-control via measurement feedback in nonlinear systems , 1992 .

[10]  K. Teo,et al.  Solving Hamilton-Jacobi-Bellman equations by a modified method of characteristics , 2000 .

[11]  M. Hestenes.  Calculus of variations and optimal control theory , 1966 .

[12]  D. Bernstein.  Optimal nonlinear, but continuous, feedback control of systems with saturating actuators , 1995 .

[13]  Andrew R. Teel,et al.  Control of linear systems with saturating actuators , 1996 .

[14]  Eduardo Sontag,et al.  A general result on the stabilization of linear systems using bounded controls , 1994, IEEE Trans. Autom. Control..

[15]  W. Schmitendorf,et al.  Stability analysis for a class of linear controllers under control constraints , 1991 .

[16]  Dennis S. Bernstein,et al.  A BENCHMARK PROBLEM FOR NONLINEAR CONTROL DESIGN , 1998 .

[17]  Manolis A. Christodoulou,et al.  Adaptive control of unknown plants using dynamical neural networks , 1994, IEEE Trans. Syst. Man Cybern..

[18]  Jie Huang,et al.  Numerical approach to computing nonlinear H-infinity control laws , 1995 .

[19]  Frank L. Lewis,et al.  Hamilton-Jacobi-Isaacs Formulation for Constrained Input Systems: Neural Network Solution , 2004 .

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

[21]  F. Lewis,et al.  Neural network H/sub /spl infin// state feedback control with actuator saturation: the nonlinear benchmark problem , 2005 .

[22]  Randal W. Bea.  Successive Galerkin approximation algorithms for nonlinear optimal and robust control , 1998 .

[23]  Frank L. Lewis,et al.  A Neural Network Solution for Fixed-Final Time Optimal Control of Nonlinear Systems , 2006, 2006 14th Mediterranean Conference on Control and Automation.

[24]  A. Schaft.  L/sub 2/-gain analysis of nonlinear systems and nonlinear state-feedback H/sub infinity / control , 1992 .

[25]  Frank L. Lewis,et al.  Nearly optimal control laws for nonlinear systems with saturating actuators using a neural network HJB approach , 2005, Autom..

[26]  M. Bardi,et al.  Optimal Control and Viscosity Solutions of Hamilton-Jacobi-Bellman Equations , 1997 .

[27]  Ben M. Chen.  Robust and H[∞] control , 2000 .

[28]  Richard S. Sutton,et al.  Neural networks for control , 1990 .

[29]  Joe Brewer,et al.  Kronecker products and matrix calculus in system theory , 1978 .

[30]  M. Balas.  MODAL CONTROL OF CERTAIN FLEXIBLE DYNAMIC SYSTEMS , 1978 .

[31]  Marios M. Polycarpou,et al.  Stable adaptive neural control scheme for nonlinear systems , 1996, IEEE Trans. Autom. Control..

[32]  F. Lewis,et al.  A Hamilton-Jacobi setup for constrained neural network control , 2003, Proceedings of the 2003 IEEE International Symposium on Intelligent Control.

[33]  M. Corless,et al.  An ℒ2 disturbance attenuation solution to the nonlinear benchmark problem , 1998 .

[34]  T. Basar,et al.  H∞-0ptimal Control and Related Minimax Design Problems: A Dynamic Game Approach , 1996, IEEE Trans. Autom. Control..

[35]  Kurt Hornik,et al.  Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks , 1990, Neural Networks.

[36]  I. Sandberg.  Notes on uniform approximation of time-varying systems on finite time intervals , 1998 .

[37]  P. Hartman.  Ordinary Differential Equations , 1965 .