多关节机械臂的高阶滑模神经网络自适应控制  

High-order Sliding Mode Neural Network Adaptive Control of Multi-joint Manipulator

作　　者：张锦 李正楠[1] 殷玉枫 祁辰[1] 武奎扬 ZHANG Jin;LI Zhengnan;YIN Yufeng;QI Chen;WU Kuiyang(School of Mechanical Engineering,Taiyuan University of Science and Technology,Taiyuan 030024,China;Shanxi Traffic Vocational and Technical College,Taiyuan 030031,China)

机构地区：[1]太原科技大学机械工程学院,太原030024 [2]山西交通职业技术学院,太原030031

出　　处：《机械科学与技术》2021年第5期710-715,共6页Mechanical Science and Technology for Aerospace Engineering

基　　金：国家自然科学基金项目(U1610118);山西省交通运输厅科技计划项目(2019-1-9);山西省研究生创新项目(2019SY473)。

摘　　要：本文针对多关节机械臂提出了一种高阶滑模神经网络自适应控制策略。在机械臂的动力学方程的基础之上,设置了滑模面,并对该滑模面求二阶导数,利用高阶滑模控制理论设计了机械臂的控制方案;高阶滑模控制分两步实施,针对标称系统采用了齐次连续控制项,对系统中存在外部干扰的情况添加了补偿项,并对系统中存在的不确定性采用RBF神经网络进行逼近。最后,应用李雅普诺夫稳定性理论证明了系统的稳定性,并通过MATLAB/Simulink仿真与传统滑模控制比较,表明了该控制算法有效地提高了轨迹的跟踪速度和精度,降低了系统中存在的抖颤。In this paper,a high-order sliding mode neural network adaptive control strategy for multi-joint manipulator is proposed and studied.On the basis of the dynamic equation of the manipulator,the sliding surface is set up,and the second derivative of the sliding surface is obtained.The control scheme of the manipulator is designed with the high-order sliding mode control theory.The high-order sliding mode control adopts two parts.For the nominal system,the homogeneous continuous control term is adopted,and the compensation term is added for the external interference in the system,and the RBF neural network is used to approach the certainty in the system.Finally,the stability of the system is proved by the Lyapunov stability theory.Through the MATLAB/Simulink simulation,compared with the traditional sliding mode control,the control algorithm proposed effectively improves the tracking speed and accuracy of the trajectory,and reduces the chattering in the system.

关 键 词：多关节机械臂 滑模控制 神经网络 自适应 

分 类 号：TH113.2[机械工程—机械设计及理论]