无人平台水下机械手的模型逼近与高精度控制  

Model Approximation and High Precision Control of Underwater Manipulator on Unmanned Platform

作　　者：崔化超 黄儒[1] 徐振 CUI Huachao;HUANG Ru;XU Zhen(The 28th Research Institute of China Electronics Technology Group Corporation,Nanjing 210023,China)

机构地区：[1]中国电子科技集团公司第二十八研究所,南京210023

出　　处：《指挥信息系统与技术》2023年第6期66-70,100,共6页Command Information System and Technology

基　　金：装备发展部中国电科联合基金(6141B0806041a)资助项目。

摘　　要：针对海上无人装备水下作业过程对机械手的高精度控制要求,开展基于径向基函数(RBF)神经网络的水下机械手模型逼近与高精度控制问题研究。首先,基于拉格朗日建模方法,综合考虑水动力矩等影响因素,建立了水下机械手动力学模型,并给出了模型闭环稳定条件;然后,采用RBF神经网络对水下环境带来的不确定项进行模型逼近和补偿;最后,采用自适应滑模控制算法,对补偿后的机械手模型进行控制,实现了闭环系统的无静差控制。水下双关节机械手仿真试验验证了控制算法的收敛性和鲁棒性。Aiming at the high precision control requirements to the manipulator in the underwater operation process with marine unmanned equipment,the model approximation based on radial basis function(RBF) neural network and high precision control problem are studied.Firstly,based on the Lagrange modeling method,and considering the hydrodynamic torque and other influencing factors,the dynamics model of the underwater manipulator is established,and the closed-loop stability conditions of the model are proposed.Then,the RBF neural network is used to approach and compensate the uncertainty caused by underwater environment.Finally,with the adaptive sliding mode control algorithm,the compensated manipulator model is controlled,and the closed-loop system can be controlled without static error.The convergence and robustness of the control algorithm are verified by simulation experiment of an underwater double-joint manipulator.

关 键 词：水下机械手 模型逼近 径向基函数(RBF)神经网络 滑模控制 

分 类 号：TP241[自动化与计算机技术—检测技术与自动化装置]