控制理论与应用2024,Vol.41Issue(9) :1692-1697.DOI:10.7641/CTA.2023.20713

梯度提升最小二乘支持向量回归的压电执行器磁滞特性建模

Hysteresis characteristics modeling of piezoelectric actuator by gradient boosting least-squares support vector regression

王建成 李强亚 刘涛 谭永红 阎帅
控制理论与应用2024,Vol.41Issue(9) :1692-1697.DOI:10.7641/CTA.2023.20713

梯度提升最小二乘支持向量回归的压电执行器磁滞特性建模

Hysteresis characteristics modeling of piezoelectric actuator by gradient boosting least-squares support vector regression

王建成 1李强亚 1刘涛 1谭永红 2阎帅1
扫码查看

作者信息

  • 1. 大连理工大学控制科学与工程学院,辽宁大连 116024
  • 2. 上海师范大学信息与机电工程学院,上海 201814
  • 折叠

摘要

针对用于精密运动定位的压电执行器具有磁滞效应的问题,本文提出一种基于梯度提升最小二乘支持向量回归(GB-LSSVR)的建模方法.首先,通过引入磁滞算子构造拓展的输入空间,将磁滞的多值映射转换为一对一映射.然后,建立基于GB-LSSVR的磁滞模型,设计可保证收敛粒子群算法(GCPSO)对GB-LSSVR模型参数进行优化.最后,将所提出方法用于实际预测一个压电执行器的位移.结果表明,该方法相对于经典的最小二乘支持向量回归(LSSVR)和截断最小二乘支持向量回归(T-LSSVR)算法,能得到更加准确的结果.

Abstract

Concerning the problem of hysteresis effect related to piezoelectric actuators used for precise motion posi-tioning,a modeling method is proposed based on the gradient boosting least-squares support vector regression(GB-LSSVR).Firstly,an expanded input space is constructed by introducing a hysteretic operator,such that the multi-valued mapping of hysteresis is transformed into a one-to-one mapping.Then the hysteresis model is established based on the GB-LSSVR,of which the parameters are optimized by the guaranteed convergence particle swarm optimization(GCPSO)algorithm.Finally,the proposed method is applied to practically predict the displacement of a piezoelectric actuator.The re-sults show that the proposed method could obtain more accurate result compared to the classical algorithms of least-squares support vector regression and truncated least-squares support vector regression.

关键词

压电执行器/磁滞效应/磁滞算子/最小二乘支持向量机/可保证收敛粒子群算法/梯度提升

Key words

piezoelectric actuator/hysteresis effect/hysteretic operator/least-squares support vector machine/guaran-teed convergence particle swarm optimization/gradient boosting

引用本文复制引用

基金项目

国家自然科学基金项目(62327807)

国家自然科学基金项目(62361136585)

教育部重点基地平台科研专题项目(DUT21LAB113)

出版年

2024
控制理论与应用
华南理工大学 中国科学院数学与系统科学研究院

控制理论与应用

CSTPCD北大核心
影响因子:1.076
ISSN:1000-8152
段落导航相关论文