Improved Adaptive Critic for Neural Optimal Control of Constrained Nonlinear Discrete-Time Systems

被引：0

作者：

Zhao, Mingming ^{[1
,2
]}

Wang, Ding ^{[1
,2
]}

Ha, Mingming ^{[3
]}

机构：

[1] Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China

[2] Beijing Univ Technol, Beijing Key Lab Computat Intelligence & Intellige, Beijing 100124, Peoples R China

[3] Univ Sci & Technol Beijing, Sch Automat & Elect Engn, Beijing 100083, Peoples R China

来源：

PROCEEDINGS OF THE 39TH CHINESE CONTROL CONFERENCE | 2020年

基金：

北京市自然科学基金; 中国国家自然科学基金;

关键词：

Adaptive dynamic programming; iterative adaptive critic; control constraints; neural networks; nonlinear discrete-time systems;

D O I：

暂无

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

There always exist approximation errors during neural network control processes, which may cause the estimation value to exceed the control constraint when the optimal control input reaches to a neighborhood of the constraint. In this paper, through a new neural network training approach, the near-optimal control problem for a class of nonlinear discrete-time systems with control constraints is solved. Based on the nonquadratic performance index and the dual heuristic dynamic programming scheme, the iterative algorithm is developed with convergence guarantee and is also implemented by using three neural networks. At last, two examples are given to demonstrate the effectiveness of the proposed optimal control scheme.

引用

页码：1934 / 1939

页数：6

共 11 条

[1] Discrete-time nonlinear HJB solution using approximate dynamic programming: Convergence proof [J].

Al-Tamimi, Asma ;

Lewis, Frank L. ;

Abu-Khalaf, Murad .

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS, 2008, 38 (04) :943-949

[2] Event-Triggered Adaptive Critic Control Design for Discrete-Time Constrained Nonlinear Systems [J].

Ha, Mingming ;

Wang, Ding ;

Liu, Derong .

IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS, 2020, 50 (09) :3158-3168

[3] Iterative ADP learning algorithms for discrete-time multi-player games [J].

Jiang, He ;

Zhang, Huaguang .

ARTIFICIAL INTELLIGENCE REVIEW, 2018, 50 (01) :75-91

[4]

Lyshevski SE, 1998, P AMER CONTR CONF, P3699, DOI 10.1109/ACC.1998.703328

[5] Adaptive critic designs [J].

Prokhorov, DV ;

Wunsch, DC .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1997, 8 (05) :997-1007

[6] Control of linear systems with saturating actuators [J].

Saberi, A ;

Lin, ZL ;

Teel, AR .

IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 1996, 41 (03) :368-378

[7] Self-Learning Optimal Regulation for Discrete-Time Nonlinear Systems Under Event-Driven Formulation [J].

Wang, Ding ;

Ha, Mingming ;

Qiao, Junfei .

IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2020, 65 (03) :1272-1279

[8] Optimal control of unknown nonaffine nonlinear discrete-time systems based on adaptive dynamic programming [J].

Wang, Ding ;

Liu, Derong ;

Wei, Qinglai ;

Zhao, Dongbin ;

Jin, Ning .

AUTOMATICA, 2012, 48 (08) :1825-1832

[9] A New Design of H-Infinity Piecewise Filtering for Discrete-Time Nonlinear Time-Varying Delay Systems via T-S Fuzzy Affine Models [J].

Wei, Yanling ;

Qiu, Jianbin ;

Shi, Peng ;

Lam, Hak-Keung .

IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS, 2017, 47 (08) :2034-2047

[10]

Werbos P. J, 1992, HDB INTELLIGENT CONT

← 1 2 →