ZHANG Xin1,2， QUAN Ying1
（1. School of Automation & Electrical Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China;2. Gansu Provincial Engineering Research Center for Artificial Intelligence and Graphics & Image Processing, Lanzhou 730070, China）
Abstract： In order to achieve high-precision tracking control of the end of manipulator, a fixed-time sliding mode tracking control strategy based on radial basis function (RBF) neural network is proposed. First, the dynamic model of the manipulator is established. Then the RBF neural network is combined with the fixed-time sliding mode surface to design the RBF fixed-time sliding mode controller to achieve high-precision control of the end trajectory of the manipulator. And the theoretical feasibility of the designed controller is proved by the Lyapunov stability theory. Finally, a simulation experiment is carried out with the two-joint manipulator as the research object. The results show that the fixed-time sliding mode tracking control strategy of the RBF neural network can estimate the uncertain parameters in the model, effectively improve the control effect, and make the controller have fixed-time convergence characteristics, which improves the convergence speed of the manipulator.
Key words： manipulator； radial basis function (RBF) neural network control； fixed-time sliding mode surface； Lyapunov function； convergence speed
References
［1］KANGRU T, RIIVES J, MAHMOOD K, et al. Suitability analysis of using industrial robots in manufacturing. Proceedings of the Estonian Academy of Sciences, 2019， 68(4): 383-388.
［2］HUA Y, GU Y X. Kinematics analysis of a robotic arm in a traffic cone automatic recovery and placement device. Mechanical Engineering and Technology, 2020， 9(1): 1-12.
［3］HIRZINGER G, BRUNNER B, LANDZETTEL K, et al. Space robotics-DLR’s telerobotic concepts, lightweight arms and articulated hands. Autonomous Robots, 2003, 14(2): 127-145.
［4］ARAD B, BALENDONCK J, BARTH R, et al. Development of a sweet pepper harvesting robot. Journal of Field Robotics, 2020, 37(6): 1027-1039.
［5］SUN P, WANG S Y, KARIMI H R, et al. Robust redundant input reliable tracking control for omnidirectional rehabilitative training walker. Mathematical Problems in Engineering, 2014, 2014(Pt.2): 636934.
［6］SOUHILA A B, FETHI D, ABDELHAFID O. Design of a sliding mode observer based on computed torque control for hyper dynamic manipulation. Journal Européen des Systèmes Automatisés, 2019, 52(5): 449-456.
［7］MIAO Z C, ZHANG W B, HANT L, et al. Fractional order integral sliding mode control for PMSM based on fractional order sliding mode observer. Journal of Measurement Science and Instrumentation, 2019, 10(4): 389-397.
［8］WANG D, HE H B, LIU D R. Adaptive critic nonlinear robust control: A survey. IEEE Transactions on Cybernetics, 2017, 47(10): 3429-3451.
［9］WANG M, BIAN G R, LI H S. A new fuzzy iterative learning control algorithm for single joint manipulator. Archives of Control Sciences, 2016, 26(3): 297-310.
［10］XU Y Y, WANG Y, XUE D B. Neural network control optimization and simulation of robot arm. Chinese Journal of Construction Machinery, 2018, 16(5): 416-420.
［11］ZHANG H, DONG H Y, ZHANG B P, et al. Research on beam supply control strategy based on sliding mode control. Archives of Electrical Engineering, 2020, 69(2): 349-364.
［12］SHI X P, LIU S R. Research progress of manipulator trajectory tracking control. Control Engineering, 2011, 18(1): 116-122+132.
［13］SU Y X, ZHENG C H. A new nonsingular integral terminal sliding mode control for robot manipulators. International Journal of Systems Science, 2020, 51(8): 1418-1428.
［14］WANG Y Y, JIANG S R, CHEN B, et al. A new continuous fractional-order nonsingular terminal sliding mode control for cable-driven manipulators. Advances in Engineering Software, 2018, 119: 21-29.
［15］LUAN F J, NA J, HUANG Y B, et al. Adaptive neural network control for robotic manipulators with guaranteed finite-time convergence. Neurocomputing, 2019, 337: 153-164.
［16］RUCHIK A, KUMAR N. Finite time control scheme for robot manipulators using fast terminal sliding mode control and RBFNN. International Journal of Dynamics and Control, 2019, 7(2): 758-766.
［17］POLYAKOV A. Nonlinear feedback design for fixed-time stabilization of linear control systems. IEEE Transactions on Automatic Control, 2012, 57(8): 2106-2110.
［18］WU D H, XIAO R, OUYANG H C, et al. Improved fixed-time sliding mode control method design of mechanical arm. Mechanical Science and Technology, 2021, 40(8): 1171-1176.
［19］YAO L P, HOU B L. Fixed-time terminal sliding mode control of ammunition transmission manipulator. Journal of Harbin Institute of Technology, 2021, 53(1): 109-116.
［20］LIU J K. Design of robot control system and MATLAB simulation. Beijing: Tsinghua University Press, 2008.
基于RBF神经网络的固定时间滑模控制策略研究
张鑫1,2， 权莹1
（1. 兰州交通大学 自动化与电气工程学院， 甘肃 兰州 730070；2. 甘肃省人工智能与图形图像处理工程研究中心， 甘肃 兰州 730070）
摘要：为了实现对机械臂末端的高精度跟踪控制， 本文提出了一种基于径向基函数(Radial basis function， RBF)神经网络的固定时间滑模跟踪控制策略。 首先， 建立机械臂的动力学模型。 然后， 将RBF神经网络和固定时间滑模面结合， 设计RBF固定时间滑模控制器， 以实现对机械臂末端轨迹的高精度控制； 并利用Lyapunov稳定性理论对所设计控制器的理论可行性进行了证明。 最后， 以二关节机械臂为研究对象进行仿真实验。 结果表明： RBF神经网络的固定时间滑模跟踪控制策略能估计模型中的不确定参数， 有效地改善了控制效果； 并使控制器具有固定时间收敛特性， 提高了机械臂的收敛速度。
关键词：机械臂； 径向基函数神经网络控制； 固定时间滑模面； Lyapunov函数； 收敛速度
引用格式：ZHANG Xin， QUAN Ying． Research on fixed time sliding mode control strategy based on RBF neural network． Journal of Measurement Science and Instrumentation， 2023， 14（2）： 218-225. DOI： 10．3969／j．issn．1674-8042．2023．02．011
[full text view]
