Adaptive dynamic programming-based optimal control of unknown nonaffine nonlinear discrete-time systems with proof of convergence

作     者：Zhang, Xin Zhang, Huaguang Sun, Qiuye Luo, Yanhong 

作者机构：Northeastern Univ Sch Informat Sci & Engn Shenyang 110819 Liaoning Peoples R China 

出 版 物：《NEUROCOMPUTING》 (神经计算)

年 卷 期：2012年第91卷

页      面：48-55页

核心收录：

学科分类：08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：National Natural Science Foundation of China [50977008, 61034005, 60904101, 61104010] National Basic Research Program of China [2009CB320601] Science and Technology Research Program of the Education Department of Liaoning Province [LT2010040] National High Technology Research and Development Program of China [2012AA040104] 

主　　题：Optimal control Adaptive dynamic programming Recurrent neural network System identification 

摘      要：In this paper, a novel neuro-optimal control scheme is proposed for unknown nonaffine nonlinear discrete-time systems by using adaptive dynamic programming (ADP) method. A neuro identifier is established by employing recurrent neural networks (RNNs) model to reconstruct the unknown system dynamics. The convergence of the identification error is proved by using the Lyapunov theory. Then based on the established RNN model, the ADP method is utilized to design the approximate optimal controller. Two neural networks (NNs) are used to implement the iterative algorithm. The convergence of the action NN error and weight estimation errors is demonstrated while considering the NN approximation errors. Finally, two numerical examples are used to demonstrate the effectiveness of the proposed control scheme. (C) 2012 Published by Elsevier B.V.