变负载柔性机械臂复合学习控制

曹怀磊; 邓文翔; 姚建勇

doi:10.7652/xjtuxb202201007

您当前的位置：

首页 >

文章列表页 >

变负载柔性机械臂复合学习控制

专题控制策略 | 更新时间：2025-05-08

- 变负载柔性机械臂复合学习控制
- Composite Learning Control for Variable Load Flexible Manipulator
- 西安交通大学学报 2022年56卷第1期页码：61-69
- 作者机构：
  
  南京理工大学机械工程学院,南京,210094
- 作者简介：
- 基金信息：
  
  : 2021-07-31。作者简介: 曹怀磊(1996—),男,硕士生;邓文翔(通信作者),男,讲师。基金项目: 国家自然科学基金资助项目(51905271,52075262);江苏省自然科学基金资助项目(BK20190459)
- DOI：10.7652/xjtuxb202201007
  中图分类号： TP241
- 网络首发：2022-01-10，
  
  纸质出版：2022
- 稿件说明：
移动端阅览
曹怀磊, 邓文翔, 姚建勇. 变负载柔性机械臂复合学习控制[J]. 西安交通大学学报, 2022,56(1):61-69.

CAO Huailei, DENG Wenxiang, YAO Jianyong. Composite Learning Control for Variable Load Flexible Manipulator[J]. 2022, 56(1): 61-69.
曹怀磊, 邓文翔, 姚建勇. 变负载柔性机械臂复合学习控制[J]. 西安交通大学学报, 2022,56(1):61-69. DOI： 10.7652/xjtuxb202201007.

CAO Huailei, DENG Wenxiang, YAO Jianyong. Composite Learning Control for Variable Load Flexible Manipulator[J]. 2022, 56(1): 61-69. DOI： 10.7652/xjtuxb202201007.

摘要

针对末端负载质量变化的柔性连杆机械臂运动轨迹跟踪控制问题

提出了一种结合径向基神经网络(RBFNN)和干扰观测器(DOB)的复合学习控制方法。利用RBFNN逼近连杆柔性引起的非线性不确定性

构造DOB实时估计包括负载变化、非线性摩擦、RBFNN逼近误差等效应的集中干扰

将两者用于控制器的前馈补偿设计以提升系统跟踪性能

同时设计鲁棒反馈控制律保证系统的稳定性。通过Lyapunov稳定性理论证明了所提控制方法可保证跟踪误差的有界性和闭环系统的稳定性。基于柔性机械臂平台的对比实验结果表明:所提控制方法在不同负载下可以保持跟踪精度在0.5%以内

负载变化引起的误差变化不超过2%; 与仅使用神经网络的控制方法相比

跟踪性能提升了24.7%。

Abstract

Aiming at the trajectory tracking control problem of flexible link manipulators with varying tip load mass

a composite learning control(NNDORC)method combining radial basis neural network(RBFNN)and disturbance observer(DOB)is proposed. This method adopts RBFNN to approximate the nonlinear uncertainty caused by flexibility of links

and constructs DOB to estimate real-time concentrated disturbances including load change

nonlinear friction and RBFNN approximation error. The controller feedforward compensation design facilitates improving the system tracking performance

and the corresponding robust feedback control law ensures the system stability. The Lyapunov stability theory verifies that the proposed control method can guarantee the boundedness of the tracking error and the stability of the closed-loop system. Comparative experiments on the flexible manipulator platform show that the proposed control method can maintain the tracking accuracy within 0.5% under different loads

and the error change caused by the varying loads gets below 2%. Compared with the control method only using neural network

the proposed method improves the tracking performance by 24.7%.

关键词

Keywords

references

段书用, 李昌洛, 韩旭, 等. 机械臂动力学分析及关节非线性摩擦模型建立 [J]. 机械工程学报, 2020, 56(9): 18-28.DUAN Shuyong, LI Changluo, HAN Xu, et al. Forward-inverse dynamics analysis of robot arm trajectories and development of a nonlinear friction model for robot joints [J]. Journal of Mechanical Engineering, 2020, 56(9): 18-28

齐志刚, 黄攀峰, 刘正雄, 等. 空间冗余机械臂路径规划方法研究 [J]. 自动化学报, 2019, 45(6): 1103-1110.QI Zhigang, HUANG Panfeng, LIU Zhengxiong, et al. Research on path planning method of spatial redundant manipulator [J]. Acta Automatica Sinica, 2019, 45(6): 1103-1110

杜志江, 王伟, 闫志远, 等. 基于模糊强化学习的微创外科手术机械臂人机交互方法 [J]. 机器人, 2017, 39(3): 363-370.DU Zhijiang, WANG Wei, YAN Zhiyuan, et al. A physical human-robot interaction algorithm based on fuzzy reinforcement learning for minimally invasive surgery manipulator [J]. Robot, 2017, 39(3): 363-370

KIANG C T, SPOWAGE A, YOONG C K. Review of control and sensor system of flexible manipulator [J]. Journal of Intelligent & Robotic Systems, 2015, 77(1): 187-213

SUBEDI D, TYAPIN I, HOVLAND G. Review on modeling and control of flexible link manipulators [J]. Modeling, Identification and Control, 2020, 41(3): 141-163

RAOUF F, MOHAMAD S, MAAROUF S, et al. Distributed adaptive control strategy for flexible link manipulators [J]. Robotica, 2017, 35(7): 1562-1584

BELHERAZEM A, CHENAFA M. Passivity based adaptive control of a single-link flexible manipulator [J]. Automatic Control and Computer Sciences, 2021, 55(1): 1-14

XU Bin. Composite learning control of flexible-link manipulator using NN and DOB [J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2018, 48(11): 1979-1985

YANG Xinxin, GE S S, HE Wei. Dynamic modelling and adaptive robust tracking control of a space robot with two-link flexible manipulators under unknown disturbances [J]. International Journal of Control, 2018, 91(4): 969-988

YANG Yan, LIU Zhijie, MA Ge. Adaptive distributed control of a flexible manipulator using an iterative learning scheme [J]. IEEE Access, 2019, 7: 145934-145943

XING Xueyan, LIU Jinkun. Modeling and robust adaptive iterative learning control of a vehicle-based flexible manipulator with uncertainties [J]. International Journal of Robust and Nonlinear Control, 2019, 29(8): 2385-2405

FAREH R, AL-SHABI M, BETTAYEB M, et al. Robust active disturbance rejection control for flexible link manipulator [J]. Robotica, 2020, 38(1): 118-135

刘延芳, 刘宏, 孟瑶. 负载不确定的柔性机械臂自适应自抗扰控制 [J]. 哈尔滨工业大学学报, 2017, 49(7): 12-19.LIU Yanfang, LIU Hong, MENG Yao. Adaptive active disturbance rejection control of flexible manipulators with uncertain payload [J]. Journal of Harbin Institute of Technology, 2017, 49(7): 12-19

GAO Hejia, HE Wei, ZHOU Chen, et al. Neural network control of a two-link flexible robotic manipulator using assumed mode method [J]. IEEE Transactions on Industrial Informatics, 2019, 15(2): 755-765

陈文楷, 石英, 崔刚, 等. 基于模糊神经的柔性臂变负载控制方法 [J]. 控制工程, 2009, 16(6): 717-719, 786.CHEN Wenkai, SHI Ying, CUI Gang, et al. Load varying control of flexible manipulator base on fuzzy-neural [J]. Control Engineering of China, 2009, 16(6): 717-719, 786

RAHMANI B, BELKHEIRI M. Adaptive neural network output feedback control for flexible multi-link robotic manipulators [J]. International Journal of Control, 2019, 92(10): 2324-2338

杨航, 刘凌, 倪骏康, 等. 双关节刚性机器人自适应BP神经网络算法 [J]. 西安交通大学学报, 2018, 52(1): 129-135, 164.YANG Hang, LIU Ling, NI Junkang, et al. An adaptive BP neural network algorithm for 2-joint rigid robots [J]. Journal of Xi'an Jiaotong University, 2018, 52(1): 129-135, 164

刘凌, 李志成, 张莹. 面向双关节机械臂的参数可调RBF神经网络控制 [J]. 西安交通大学学报, 2021, 55(4): 1-7.LIU Ling, LI Zhicheng, ZHANG Ying. A RBF neural network control method with adjustable parameters for 2-joint robot manipulators [J]. Journal of Xi'an Jiaotong University, 2021, 55(4): 1-7

JIANG Naijing, ZHANG Shu, XU Jian, et al. Model-free control of flexible manipulator based on intrinsic design [J/OL]. IEEE/ASME Transactions on Mechatronics [2020-05-01]. https:∥ieeexplore.ieee.org/sta mp/stamp.jsp?tp=&arnumber=9290444

RAHIMI H N, NAZEMIZADEH M. Dynamic analysis and intelligent control techniques for flexible manipulators: a review [J]. Advanced Robotics, 2014, 28(2): 63-76

LU Lu, CHEN Zheng, YAO Bin, et al. A two-loop performance-oriented tip-tracking control of a linear-motor-driven flexible beam system with experiments [J]. IEEE Transactions on Industrial Electronics, 2013, 60(3): 1011-1022. [22] SUBEDI D, TYAPIN I, HOVLAND G. Dynamic modeling of planar multi-link flexible manipulators [J]. Robotics, 2021, 10(2): 70

ZHONG Zhen, YANG Xinxin. Tracking and vibration control for a space robotic system with rigid and flexible manipulator [C]∥Proceedings of the 2017 IEEE International Conference on Cybernetics and Intelligent Systems(CIS)and IEEE Conference on Robotics, Automation and Mechatronics(RAM). Piscataway, NJ, USA: IEEE, 2017: 518-523

YAO Jianyong, JIAO Zongxia, MA Dawei. Adaptive robust control of DC motors with extended state observer [J]. IEEE Transactions on Industrial Electronics, 2014, 61(7): 3630-3637

ZHANG Yueyuan, KIM D, ZHAO Yudong, et al. PD control of a manipulator with gravity and inertia compensation using an RBF neural network [J]. International Journal of Control, Automation and Systems, 2020, 18(12): 3083-3092

YAO Jianyong, JIAO Zongxia, MA Dawei. Extended-state-observer-based output feedback nonlinear robust control of hydraulic systems with backstepping [J]. IEEE Transactions on Industrial Electronics, 2014, 61(11): 6285-6293.-------

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

相变冷却换热器动态热响应降阶预测方法研究

采用动力学模态分解和长短期记忆网络的压缩空气储气装置流场动态预测方法

新能源汽车热管理系统协同优化策略

高超声速飞行器干扰补偿与解耦最优反步控制策略

机械臂非奇异快速终端滑模迭代学习轨迹跟踪控制研究