Learning control of flexible manipulator with unknown dynamics

Author:

Chen Zhiguang,Yang Chenguang,Liu Xin,Wang Min

Abstract

Purpose The purpose of this paper is to study the controller design of flexible manipulator. Flexible manipulator system is a nonlinear, strong coupling, time-varying system, which is introduced elastodynamics in the study and complicated to control. However, due to the flexible manipulator, system has a significant advantage in response speed, control accuracy and load weight ratio to attract a lot of researchers. Design/methodology/approach Since the order of flexible manipulator system is high, designing controller process will be complex, and have a large amount of calculation, but this paper will use the dynamic surface control method to solve this problem. Findings Dynamic surface control method as a controller design method which can effectively solve the problem with the system contains nonlinear and reduced design complexity. Originality/value The authors assume that the dynamic parameters of flexible manipulator system are unknown, and use Radial Basis Function neural network to approach the unknown system, combined with the dynamic surface control method to design the controller.

Publisher

Emerald

Subject

Industrial and Manufacturing Engineering,Control and Systems Engineering

Reference25 articles.

1. Dynamic surface control method for a class of manipulator with uncertainty,2010

2. Chu, M. (2010), “Research on dynamic characteristics and active control of spatial flexible manipulator”, PhD dissertation, Beijing University of Posts and Telecommunications.

3. Dynamic learning from adaptive neural network control of a class of nonaffine nonlinear systems;IEEE Transactions on Neural Networks and Learning Systems,2014

4. Neural learning control of marine surface vessels with guaranteed transient tracking performance;IEEE Transactions on Industrial Electronics,2016

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3