当前位置: X-MOL 学术Asian J. Control › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Neural network adaptive finite-time control of stochastic nonlinear systems with full state constraints
Asian Journal of Control ( IF 2.7 ) Pub Date : 2020-03-18 , DOI: 10.1002/asjc.2321
Qidan Zhu 1, 2 , Yongchao Liu 1, 2
Affiliation  

This paper investigates the issue of neural network adaptive finite-time tracking control for stochastic nonlinear systems subject to full state constraints. In the controller design process, neural networks are employed to cope with the packed uncertainties and the log-type barrier Lyapunov functions are introduced to prevent the violation of the state constraints. By using approximated-based neural networks and adaptive backstepping technique, a novel finite-time control approach is presented. The designed control method not only makes the tracking error converge to a small neighborhood of the origin in a finite time, but also surmounts the effect of state constraints to system performance. A numerical simulation example is provided to illustrate the validity of the designed control method.

中文翻译:

具有全状态约束的随机非线性系统的神经网络自适应有限时间控制

本文研究了受全状态约束的随机非线性系统的神经网络自适应有限时间跟踪控制问题。在控制器设计过程中,采用神经网络来处理打包的不确定性,并引入对数型障碍 Lyapunov 函数来防止违反状态约束。通过使用基于近似的神经网络和自适应反推技术,提出了一种新颖的有限时间控制方法。所设计的控制方法不仅使跟踪误差在有限时间内收敛到原点的一个小邻域,而且克服了状态约束对系统性能的影响。提供了一个数值模拟例子来说明所设计的控制方法的有效性。
更新日期:2020-03-18
down
wechat
bug