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

作　　者：孙家骏 柴琳[1] 郭启航 刘惠康[1] SUN Jia-jun;CHAI Liny;GUO Qi-hang;LIU Hui-kang(School of Information Science and Engineering,Wuhan University of Science and Technology,Wuhan Hubei 430081,China)

机构地区：[1]武汉科技大学信息科学与工程学院,湖北武汉430081

出　　处：《控制理论与应用》2024年第11期2071-2079,共9页Control Theory & Applications

基　　金：国家重点研发计划项目(2017YFC0805100)资助.

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.The three-dimensional motion mode of overhead crane has higher productivity,but its positioning and antiswing 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.

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 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置] TP183[自动化与计算机技术—控制科学与工程] TH21[机械工程—机械制造及自动化]