Neural Networks Based Learning Control for a Piezoelectric Nanopositioning System
Neural Networks Based Learning Control for a Piezoelectric Nanopositioning System
复制标题
DOI：
10.1109/tmech.2020.2997801
复制
发表时间：
2020-12
期刊：
影响因子：
--
通讯作者：
Linghuan Kong;Dan Li;Jianxiao Zou;Wei He
中科院分区：
文献类型：
--
作者：
Linghuan Kong;Dan Li;Jianxiao Zou;Wei He
在这篇文章中，基于近似模型的控制和基于神经网络的自适应控制的压电纳米定位系统的运动跟踪的解决方案，分别进行了研究。为了减小未知迟滞非线性的影响，引入扰动观测器对迟滞非线性进行估计，并考虑未知压电纳米定位系统的标称部分，得到基于近似模型的控制。利用神经网络的在线学习能力处理标称部分对应的未知部分，提出了一种自适应神经网络控制方法，提高了控制精度。与现有的工作相比，所提出的控制方法的一个很大的好处是，基于神经网络的学习算法开发的压电纳米定位系统的不确定性，在一个在线的方式，使闭环系统可以自动管理，获得满意的运动跟踪。利用李雅普诺夫稳定性理论，证明了所有误差信号都是半全局一致最终有界的。最后通过实验验证了该控制方法的有效性。
In this article, approximation model-based control and neural networks-based adaptive control are investigated for obtaining the solution to the motion tracking of a piezoelectric nanopositioning system, respectively. In order to reduce the effect of unknown hysteresis nonlinearity, a disturbance observer is introduced to estimate it. By considering nominal parts of an unknown piezoelectric nanopositioning system, approximation model-based control is obtained. The unknown parts corresponding to nominal parts are dealt with by the online learning ability of neural networks, and an adaptive neural network control is proposed to improve control accuracy. Compared with existing works, a great benefit of the proposed control method is that the neural networks-based learning algorithm is developed to deal with uncertainty of a piezoelectric nanopositioning system in an online way such that the closed-loop system can be governed automatically, obtaining satisfactory motion tracking. With Lyapunov stability theory, it is proved that all error signals are semiglobally uniformly ultimately bounded. Experiment is carried out to verify the effectiveness of the proposed control.