Neural critic learning with accelerated value iteration for nonlinear model predictive control

Peng Xin; Ding Wang; Ao Liu; Junfei Qiao

doi:10.1016/j.neunet.2024.106364

Neural critic learning with accelerated value iteration for nonlinear model predictive control

Neural Netw. 2024 May 6:176:106364. doi: 10.1016/j.neunet.2024.106364. Online ahead of print.

Authors

Peng Xin¹, Ding Wang², Ao Liu³, Junfei Qiao⁴

Affiliations

¹ Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China; Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing University of Technology, Beijing 100124, China; Beijing Institute of Artificial Intelligence, Beijing University of Technology, Beijing 100124, China; Beijing Laboratory of Smart Environmental Protection, Beijing University of Technology, Beijing 100124, China. Electronic address: xinpeng@emails.bjut.edu.cn.
² Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China; Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing University of Technology, Beijing 100124, China; Beijing Institute of Artificial Intelligence, Beijing University of Technology, Beijing 100124, China; Beijing Laboratory of Smart Environmental Protection, Beijing University of Technology, Beijing 100124, China. Electronic address: dingwang@bjut.edu.cn.
³ Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China; Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing University of Technology, Beijing 100124, China; Beijing Institute of Artificial Intelligence, Beijing University of Technology, Beijing 100124, China; Beijing Laboratory of Smart Environmental Protection, Beijing University of Technology, Beijing 100124, China. Electronic address: liuao@emails.bjut.edu.cn.
⁴ Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China; Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing University of Technology, Beijing 100124, China; Beijing Institute of Artificial Intelligence, Beijing University of Technology, Beijing 100124, China; Beijing Laboratory of Smart Environmental Protection, Beijing University of Technology, Beijing 100124, China. Electronic address: adqiao@bjut.edu.cn.

PMID: 38754288
DOI: 10.1016/j.neunet.2024.106364

Abstract

In practical industrial processes, the receding optimization solution of nonlinear model predictive control (NMPC) is always a very knotty problem. Based on adaptive dynamic programming, the accelerated value iteration predictive control (AVI-PC) algorithm is developed in this paper. Integrating iteration learning with the receding horizon mechanism of NMPC, a novel receding optimization solution pattern is exploited to resolve the optimal control law in each prediction horizon. Besides, the basic architecture and the specific form of the AVI-PC algorithm are demonstrated, including the relationship among the iterative learning process, the prediction process, and the control process. On this basis, the convergence and admissibility conditions are established, and the relevant properties are comprehensively analyzed when the accelerated factor satisfies the established conditions. Furthermore, the accelerated value iterative function is approximated through the single critic network constructed by utilizing the multiple linear regression method. Finally, the plentiful simulation experiments are conducted from various perspectives to verify the effectiveness and progressiveness of the AVI-PC algorithm.

Keywords: Accelerated mechanism; Adaptive critic designs; Neural networks; Nonlinear model predictive control; Value iteration.