期刊
NEURAL NETWORKS
卷 134, 期 -, 页码 54-63出版社
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.neunet.2020.09.020
关键词
Adaptive dynamic programming; Reinforcement learning; Particle swarm optimization; Neural networks; Tracking control; Nonlinear interconnected systems
资金
- National Natural Science Foundation of China [61973330 61773075, 62073085, 61533017, 61603387]
- Guangdong Introducing Innovative, China [2019ZT08X340]
- Entrepreneurial Teams of The Pearl River Talent Recruitment Program'', China [2019ZT08X340]
- Fundamental Research Funds for the Central Universities, China [2019NTST25]
- State Key Laboratory of Synthetical Automation for Process Industries, China [2019-KF-23-03]
This paper develops a local tracking control scheme for unknown nonlinear interconnected systems using particle swarm optimized neural networks (PSONN), which increases the success rate of system execution. The effectiveness of the developed PSONN-based LTC scheme is demonstrated through simulation results of two examples.
In this paper, a local tracking control (LTC) scheme is developed via particle swarm optimized neural networks (PSONN) for unknown nonlinear interconnected systems. With the local input-output data, a local neural network identifier is constructed to approximate the local input gain matrix and the mismatched interconnection, which are utilized to derive the LTC. To solve the local Hamilton-Jacobi-Bellman equation, a local critic NN is established to estimate the proper local value function, which reflects the mismatched interconnection. The weight vector of the local critic NN is trained online by particle swarm optimization, thus the success rate of system execution is increased. The stability of the closed-loop unknown nonlinear interconnected system is guaranteed to be uniformly ultimately bounded through Lyapunov's direct method. Simulation results of two examples demonstrate the effectiveness of the developed PSONN-based LTC scheme. (C) 2020 Elsevier Ltd. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据