引用本文:孙家骏,柴琳,郭启航,刘惠康.三维运动模式下的桥式吊车神经网络滑模控制[J].控制理论与应用,2024,41(11):2071~2079.[点击复制]
SUN Jia-jun,CHAI Lin,GUO Qi-hang,LIU Hui-kang.Neural network sliding mode control of overhead crane in three-dimensional motion mode[J].Control Theory and Technology,2024,41(11):2071~2079.[点击复制]
三维运动模式下的桥式吊车神经网络滑模控制
Neural network sliding mode control of overhead crane in three-dimensional motion mode
摘要点击 158  全文点击 37  投稿时间：2022-08-16  修订日期：2023-06-04
查看全文  查看/发表评论  下载PDF阅读器
DOI编号  10.7641/CTA.2023.20728
  2024,41(11):2071-2079
中文关键词  三维运动模式  定位与防摆  滑模控制  神经网络  最小参数学习法
英文关键词  three-dimensional motion mode  positioning and anti-swing  sliding mode control  neural network  minimum parameter learning method
基金项目  国家重点研发计划项目(2017YFC0805100)资助.
作者单位E-mail
孙家骏 武汉科技大学 838822738@qq.com 
柴琳* 武汉科技大学 chailin@wust.edu.cn 
郭启航 武汉科技大学  
刘惠康 武汉科技大学  
中文摘要
      三维运动模式下的桥式吊车具有更高的生产效率, 但其定位与防摆控制也更具挑战性. 针对该问题, 本文提出一种基于最小参数学习的神经网络滑模控制方法. 首先, 建立了包含机械摩擦力和空气阻力的全驱动动力学模型, 解决了系统由于欠驱动特性导致控制器难以设计的问题; 随后, 设计了基于指数趋近律的滑模控制器, 引入径向基函数(radial basis functions, RBF)神经网络的最小参数学习法对系统的不确定性模型进行逼近; 并对控制器的稳定性进行了严格的数学证明. 仿真与实验结果表明, 本文所提控制方法在有/无外界干扰的情况下, 都能实现吊车的精确定位与负载摆动的有效抑制.
英文摘要
      The three-dimensional motion mode of overhead crane has higher productivity, but its positioning and anti-swing control is also more challenging. To address this problem, this paper proposes a neural network sliding mode control method based on minimum parameter learning. Firstly, a full-drive dynamics model including mechanical friction and air resistance is established to solve the problem that the system is difficult to design the controller due to the underdrive characteristics; then a sliding mode controller based on the exponential convergence law is designed and a minimal parameter learning method based on radial basis functions (RBF) neural network is introduced to approximate the uncertainty model of the system. A rigorous mathematical proof of the stability of the controller is presented. The simulation and experimental results show that the proposed control method can achieve the precise positioning of the crane and the effective suppression of the load swing with and without external disturbances.