A novel neural optimal control framework with nonlinear dynamics: Closed-loop stability and simulation verification

doi:10.1016/j.neucom.2017.05.051

CORC > 自动化研究所 > 中国科学院自动化研究所 > 复杂系统管理与控制国家重点实验室 > 平行控制

	A novel neural optimal control framework with nonlinear dynamics: Closed-loop stability and simulation verification
	Wang, Ding1,2 ; Mu, Chaoxu 3
刊名	NEUROCOMPUTING
	2017-11-29
卷号	266 页码:353-360
关键词	Adaptive Dynamic Programming Adaptive System Learning Control Neural Network Optimal Regulator Stability
DOI	10.1016/j.neucom.2017.05.051
文献子类	Article
英文摘要	In this paper, we focus on developing adaptive optimal regulators for a class of continuous-time nonlinear dynamical systems through an improved neural learning mechanism. The main objective lies in that establishing an additional stabilizing term to reinforce the traditional training process of the critic neural network, so that to reduce the requirement with respect to the initial stabilizing control, and therefore, bring in an obvious convenience to the adaptive-critic-based learning control implementation. It is exhibited that by employing the novel updating rule, the adaptive optimal control law can be obtained with an excellent approximation property. The closed-loop system is constructed and its stability issue is handled by considering the improved learning criterion. Experimental simulations are also conducted to verify the efficient performance of the present design method, especially the major role that the stabilizing term performed. (C) 2017 Elsevier B.V. All rights reserved.
WOS关键词	SYSTEMS
WOS研究方向	Computer Science
语种	英语
WOS记录号	WOS:000408183900033
资助机构	National Natural Science Foundation of China(U1501251 ; Beijing Natural Science Foundation(4162065) ; Research Fund of Tianjin Key Laboratory of Process Measurement and Control(TKLPMC-201612) ; Early Career Development Award of SKLMCCS ; 61533017 ; 61233001)
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/20716]
专题	复杂系统管理与控制国家重点实验室_平行控制
作者单位	1.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Comp & Control Engn, Beijing 100049, Peoples R China 3.Tianjin Univ, Sch Elect & Informat Engn, Tianjin Key Lab Proc Measurement & Control, Tianjin 300072, Peoples R China
推荐引用方式 GB/T 7714	Wang, Ding,Mu, Chaoxu. A novel neural optimal control framework with nonlinear dynamics: Closed-loop stability and simulation verification[J]. NEUROCOMPUTING,2017,266:353-360.
APA	Wang, Ding,&Mu, Chaoxu.(2017).A novel neural optimal control framework with nonlinear dynamics: Closed-loop stability and simulation verification.NEUROCOMPUTING,266,353-360.
MLA	Wang, Ding,et al."A novel neural optimal control framework with nonlinear dynamics: Closed-loop stability and simulation verification".NEUROCOMPUTING 266(2017):353-360.