中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 智能化团队
Data-Driven Zero-Sum Neuro-Optimal Control for a Class of Continuous-Time Unknown Nonlinear Systems With Disturbance Using ADP

文献类型：期刊论文

作者Wei, Qinglai1; Song, Ruizhuo2; Yan, Pengfei1
刊名IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
出版日期2016-02-01
卷号27期号:2页码:444-458
关键词Adaptive Critic Designs Adaptive Dynamic Programming (Adp) Approximate Dynamic Programming Neurodynamic Programming Nonlinear Systems Optimal Control Recurrent Neural Network (Rnn) Reinforcement Learning
DOI10.1109/TNNLS.2015.2464080
文献子类Article
英文摘要This paper is concerned with a new data-driven zero-sum neuro-optimal control problem for continuous-time unknown nonlinear systems with disturbance. According to the input-output data of the nonlinear system, an effective recurrent neural network is introduced to reconstruct the dynamics of the nonlinear system. Considering the system disturbance as a control input, a two-player zero-sum optimal control problem is established. Adaptive dynamic programming ( ADP) is developed to obtain the optimal control under the worst case of the disturbance. Three single-layer neural networks, including one critic and two action networks, are employed to approximate the performance index function, the optimal control law, and the disturbance, respectively, for facilitating the implementation of the ADP method. Convergence properties of the ADP method are developed to show that the system state will converge to a finite neighborhood of the equilibrium. The weight matrices of the critic and the two action networks are also convergent to finite neighborhoods of their optimal ones. Finally, the simulation results will show the effectiveness of the developed data-driven ADP methods.
WOS关键词OPTIMAL TRACKING CONTROL ; DYNAMIC-PROGRAMMING ALGORITHM ; ADAPTIVE OPTIMAL-CONTROL ; OPTIMAL-CONTROL SCHEME ; KERNEL HILBERT-SPACES ; H-INFINITY CONTROL ; FEEDBACK-CONTROL ; APPROXIMATION ERRORS ; STABILITY ANALYSIS ; POLICY ITERATION
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:000372020500021
资助机构Beijing Natural Science Foundation(4132078 ; National Natural Science Foundation of China(61034002 ; China Postdoctoral Science Foundation(2013M530527) ; Fundamental Research Funds for the Central Universities(FRF-TP-14-119A2) ; Open Research Project from SKLMCCS(20150104) ; Early Career Development Award of State Key Laboratory of Management and Control for Complex Systems ; 4143065) ; 61304079 ; 61273140 ; 61374105)
源URL[http://ir.ia.ac.cn/handle/173211/11368]  
专题自动化研究所_复杂系统管理与控制国家重点实验室_智能化团队
作者单位1.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China
2.Univ Sci & Technol Beijing, Sch Automat & Elect Engn, Beijing 100083, Peoples R China
推荐引用方式
GB/T 7714		 Wei, Qinglai,Song, Ruizhuo,Yan, Pengfei. Data-Driven Zero-Sum Neuro-Optimal Control for a Class of Continuous-Time Unknown Nonlinear Systems With Disturbance Using ADP[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2016,27(2):444-458.
APA Wei, Qinglai,Song, Ruizhuo,&Yan, Pengfei.(2016).Data-Driven Zero-Sum Neuro-Optimal Control for a Class of Continuous-Time Unknown Nonlinear Systems With Disturbance Using ADP.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,27(2),444-458.
MLA Wei, Qinglai,et al."Data-Driven Zero-Sum Neuro-Optimal Control for a Class of Continuous-Time Unknown Nonlinear Systems With Disturbance Using ADP".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 27.2(2016):444-458.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。