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

作     者：Frank L.LEWIS 

作者机构：Automation and Robotics Research InstituteUniversity of TexasArlington TX 76118USA 

出 版 物：《控制理论与应用（英文版）》 (控制理论与应用)

年 卷 期：2007年第5卷第1期

页      面：1-11页

学科分类：0711[理学-系统科学] 07[理学] 08[工学] 081101[工学-控制理论与控制工程] 0811[工学-控制科学与工程] 071102[理学-系统分析与集成] 081103[工学-系统工程] 

基　　金：This work was supported by the National Science Foundation (ECS-0501451) Army Research Office (W91NF-05-1-0314) 

主　　题：Constrained input system Hamilton-Jacobi-Isaacs H-infinity control Finite-horizon zero-sum games Neural network control 

摘      要：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.