一种用于压电致动器的基于神经网络的滞后模型。

A neural-network-based hysteresis model for piezoelectric actuators.

作者信息

Ma Lianwei, Shen Yu, Li Jinrong

机构信息

School of Information Science and Engineering, Ningbo Institute of Technology, Zhejiang University, Ningbo 315100, China.

Department of Applied Physics, Zhejiang University of Science and Technology, Hangzhou 310023, China.

出版信息

Rev Sci Instrum. 2020 Jan 1;91(1):015002. doi: 10.1063/1.5121471.

DOI:10.1063/1.5121471

PMID:32012591

Abstract

In this paper, a new neural network based hysteresis model is presented. First of all, a variable-order hysteretic operator (VOHO) is proposed via the characteristics of the motion point trajectory. Based on the VOHO, a basic hysteresis model (BHM) is constructed. Next, the input space is expanded from one-dimension to two-dimension based on the BHM so that the method of neural networks can be used to approximate the mapping between the expanded input space and the output space. Finally, three experiments involved with a piezoelectric actuator were implemented to validate the neural hysteresis model. The results of the experiments suggest that the proposed approach is effective.

摘要

本文提出了一种基于神经网络的新型磁滞模型。首先，通过运动点轨迹的特性提出了一种变阶磁滞算子（VOHO）。基于该VOHO，构建了一个基本磁滞模型（BHM）。接下来，基于BHM将输入空间从一维扩展到二维，以便能够使用神经网络方法来逼近扩展输入空间与输出空间之间的映射。最后，进行了三个涉及压电致动器的实验来验证神经磁滞模型。实验结果表明所提出的方法是有效的。