一类未知非线性系统中有限域最优跟踪控制的迭代DHP算法  

The Iterative DHP Algorithm for Finite-Horizon Optimal Tracking Control for a Class of Nonlinear Systems

作　　者：吴天庆[1] 陈全发 廖芳芳 WU Tian-qing;CHEN Quan-fa;LIAO Fang-fang(School of Computer Engineering,Shangqiu University,Shangqiu476000;School of Mathematics and Finance,Xiangnan University,Chenzhou423000 China)

机构地区：[1]商丘学院计算机工程学院,河南商丘476000 [2]湘南学院数学与金融学院,湖南郴州423000

出　　处：《湘潭大学学报（自然科学版）》2019年第1期82-92,共11页Journal of Xiangtan University(Natural Science Edition)

基　　金：国家自然科学基金项目NNSF(11701487);湖南省教育厅优秀青年项目(17B258)

摘　　要：针对一类未知非线性离散时间系统,提出了一种无模型时域有限差分最优跟踪控制方案.在有限时域最优控制理论的框架下,将跟踪控制问题转化为误差动态调节器,引入迭代自适应动态规划(ADP)算法,通过双启发式动态规划(DHP)技术,分别用三个神经网络逼近误差动力学、成本函数和控制率,结合成本函数和控制率的收敛性分析,得到有限时域最优控制器.通过仿真实例验证了跟踪控制方案的有效性.A model-free finite-horizon optimal tracking control scheme for a class of unknown nonlinear discrete-time systems is proposed in this paper.The tracking control problem is converted into designing a regulator for the tracking error dynamics under the framework of finite-horizon optimal control theory.The iterative adaptive dynamic programming(ADP)algorithm is introduced,via dual heuristic dynamic programming(DHP)technique,three neural networks are taken to approximate the error dynamics,the cost function,and the control law,respectively,with convergence analysis in terms of cost function and control law,obtain the finite-horizon optimal controller.The effectiveness of the tracking control scheme is verified by simulation.

关 键 词：离散时间系统 最优跟踪 自适应动态规划 双启发式动态规划 有限时域最优跟踪控制 神经网络 神经控制 

分 类 号：TP13[自动化与计算机技术—控制理论与控制工程]