基于RBF神经网络的SCARA机器人轨迹跟踪滑模自适应控制

兰州理工大学学报 ›› 2026, Vol. 52 ›› Issue (2): 39-47.

基于RBF神经网络的SCARA机器人轨迹跟踪滑模自适应控制

王保民^*, 董春亭, 黄贵林, 齐湛江, 刘洪芹

兰州理工大学机电工程学院, 甘肃兰州 730050

收稿日期:2023-04-21 出版日期:2026-04-28 发布日期:2026-04-28
通讯作者: 王保民(1972-),男,甘肃天水人,博士,教授. Email:wbm2007@163.com
基金资助:
国家自然科学基金(51965038)

Adaptive sliding mode trajectory tracking control for SCARA robot based on RBF neural network

WANG Bao-min, DONG Chun-ting, HUANG Gui-lin, QI Zhan-jiang, LIU Hong-qin

School of Mechanical and Electrical Engineering, Lanzhou University of Technology, Lanzhou 730050, China

Received:2023-04-21 Online:2026-04-28 Published:2026-04-28

摘要/Abstract

摘要： 针对SCARA机器人轨迹跟踪控制过程的干扰问题,建立了SCARA机器人动力学模型.基于分析摩擦对机器人关节的影响,引入高速摩擦补偿项建立了机器人关节粘滞-库仑摩擦改进模型,提出了基于RBF神经网络的SCARA机器人轨迹跟踪滑模自适应控制方法,并采用Lyapunov方法分析了控制系统的稳定性和收敛性.以台达DRS40L3型SCARA机器人为研究对象,对该控制系统的跟踪精度和稳定性进行了仿真实验.结果表明,RBF神经网络滑模自适应控制SCARA机器人轨迹跟踪误差最大值、跟踪误差均方根和输入力矩均方根都比PID控制显著减小,运用该方法可以对SCARA机器人进行高精度轨迹跟踪.

关键词: SCARA机器人, 轨迹跟踪, RBF神经网络, 滑模, 自适应控制

Abstract: To address disturbance effects in the trajectory tracking control of the SCARA robot, a dynamic model of the SCARA robot is established. On the basis of analyzing the influence of friction on robot joints, a high-speed friction compensation term is introduced to establish a Viscous and Coulomb friction improvement model for robot joints. A sliding-mode adaptive control strategy for SCARA robot trajectory tracking is proposed based on an RBF neural network, and the stability and convergence of the control system are analyzed by using the Lyapunov method. The tracking accuracy and stability of the control system are simulated and experimented with the Delta DRS40L3 SCARA robot as the research object. The results show that, compared with the PID algorithm, the maximum error, the mean square value of the tracking error, and the root mean square of the input moment of the SCARA robot trajectory tracking by the RBF neural network sliding mode adaptive control have been substantially reduced. The proposed method enables high-precision trajectory tracking for SCARA robots.

Key words: SCARA robot, trajectory tracking, RBF neural network, sliding mode, adaptive control

中图分类号:

TH113

王保民, 董春亭, 黄贵林, 齐湛江, 刘洪芹. 基于RBF神经网络的SCARA机器人轨迹跟踪滑模自适应控制[J]. 兰州理工大学学报, 2026, 52(2): 39-47.

WANG Bao-min, DONG Chun-ting, HUANG Gui-lin, QI Zhan-jiang, LIU Hong-qin. Adaptive sliding mode trajectory tracking control for SCARA robot based on RBF neural network[J]. Journal of Lanzhou University of Technology, 2026, 52(2): 39-47.

导出引用管理器 EndNote|Reference Manager|ProCite|BibTeX|RefWorks

链接本文: https://journal.lut.edu.cn/CN/

https://journal.lut.edu.cn/CN/Y2026/V52/I2/39

参考文献

[1] 李琳,林燕龙,邹焱飚.Scara机器人关节摩擦建模与补偿的实验与仿真 [J].系统仿真学报,2019,31(8):1572-1581.
[2] 谢冬梅,曲道奎,徐方,等.基于解耦控制的SCARA机器人轨迹跟踪控制器设计 [J].系统仿真学报,2006(增刊2):931-934.
[3] 张蕾,刘宇航,王晓华,等.融合速度信息的机械臂自适应轨迹跟踪控制方法 [J].西安交通大学学报,2022,56(7):47-55.
[4] 陈军,姜卫东.改进RBF神经网络的机械臂轨迹跟踪控制方法 [J].机械设计与制造,2022(12):269-272.
[5] HERNANDEZ-GUZMAN V M,ORRANTE-SAKANASSI J.Global PID control of robot manipulators equipped with PMSMs [J].Asian Journal of Control,2018,20(1):236-249.
[6] LUVIANO-JUAREZ A,CORTES-ROMERO J,SIRA-RAMIREZ A.Trajectory tracking control of a mobile robot through a flatness-based exact feedforward linearization scheme [J].Journal of Dynamic Systems Measurement and Control,2015,137(5):1-8.
[7] PILTAN F,KIM C H,KIM J M.Advanced adaptive fault diagnosis and tolerant control for robot manipulators [J].Energies,2019,12(7):1-22.
[8] GOPINATH S,KAR I N.Iterative learning control scheme for manipulators including actuator dynamics [J].Mechanism and Machine Theory,2004,39(12):1367-1384.
[9] 吴晓,朱世强,刘松国.基于PDAG算法的工业机器人轨迹跟踪 [J].中国机械工程,2010,21(19):2302-2307.
[10] GROTJAHM M,HEIMANN B.Model-based feedforward control in industrial robotics [J].International Journal of Robotics Research,2002,21(1):45-60.
[11] 叶锦华,吴海彬.不确定轮式移动机器人统一自适应神经网络H∞控制 [J].中国机械工程,2017,28(2):150-155.
[12] 冯治国.基于计算力矩的助行腿机器人神经网络补偿控制 [J].中国机械工程,2013,24(16):2173-2179.
[13] 贺红林,刘文光,汪洋.直接驱动机器人的函数链神经网络-PD复合控制 [J].中国机械工程,2012,23(21):2601-2606.
[14] 李正楠,张锦,殷玉枫,等.多关节机械臂的分数阶滑模变结构神经网络自适应控制 [J].机械科学与技术,2021,40(2):270-275.
[15] 杨超,郭佳,张铭钧.基于RBF神经网络的作业型AUV自适应终端滑模控制方法及实验研究 [J].机器人,2018,40(3):336-345.
[16] 闫昊.SCARA机器人动力学分析及鲁棒性控制研究 [D].哈尔滨:哈尔滨工业大学,2014.
[17] 王保民,齐湛江,闫瑞翔,等.基于随机权重粒子群算法的SCARA机器人动力学参数辨识 [J].西安交通大学学报,2021,55(9):20-27.
[18] 陶岳,赵飞,曹巨江.协作机器人关节摩擦特性辨识与补偿技术 [J].组合机床与自动化加工技术,2019(4):28-31.
[19] 林建雄.基于动力学模型的工业机器人力矩补偿控制研究 [D].无锡:江南大学,2019.
[20] 张锦,李正楠,殷玉枫,等.多关节机械臂的高阶滑模神经网络自适应控制 [J].机械科学与技术,2021,40(5):710-715.
[21] 爱普生机器人.SCARA机器人用户手册 [EB/OL].[2019-11-08].http://www.epson.com.cn/robots/.
[22] 刘金琨.机器人控制系统的设计与Matlab仿真-基本设计方法 [M].北京:清华大学出版社,2016.