多关节机械臂的高阶滑模神经网络自适应控制

张锦; 李正楠; 殷玉枫; 祁辰; 武奎扬

doi:10.13433/j.cnki.1003-8728.20200128

多关节机械臂的高阶滑模神经网络自适应控制

doi: 10.13433/j.cnki.1003-8728.20200128

张锦^{1, 2,},
李正楠¹,
殷玉枫^1, ,,
祁辰¹,
武奎扬¹

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

基金项目:

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

详细信息

作者简介:
张锦(1983-)，博士研究生，研究方向为机电装备电液系统与智能控制技术，29297690@qq.com

通讯作者:
殷玉枫，教授，yufengyin@tyust.edu.cn

中图分类号: TH113.2
计量
- 文章访问数: 166
- HTML全文浏览量: 35
- PDF下载量: 33
- 被引次数: 0
出版历程
- 收稿日期: 2020-01-15
- 刊出日期: 2021-05-01

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

ZHANG Jin^{1, 2
,},
LI Zhengnan¹,
YIN Yufeng^{1
, ,},
QI Chen¹,
WU Kuiyang¹

1.
School of Mechanical Engineering, Taiyuan University of Science and Technology, Taiyuan 030024, China
2.
Shanxi Traffic Vocational and Technical College, Taiyuan 030031, China

摘要

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。
- 多关节机械臂 /
- 滑模控制 /
- 神经网络 /
- 自适应
Abstract: 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.
- multi-joint manipulator /
- sliding mode control /
- neural network /
- adaptive control

HTML全文

图 1 低阶滑模神经网络自适应控制关节1仿真曲线

下载: 全尺寸图片幻灯片

图 2 低阶滑模神经网络自适应控制关节2仿真曲线

下载: 全尺寸图片幻灯片

图 3 高阶滑模神经网络自适应控制关节1仿真曲线

下载: 全尺寸图片幻灯片

图 4 高阶滑模神经网络自适应控制关节2仿真曲线

下载: 全尺寸图片幻灯片

参考文献(14)

[1]	蔡自兴. 机器人学基础[M]. 北京: 清华大学出版社, 2012 CAI Z X. Fundamentals of robotics[M]. Beijing: Tsinghua University Press, 2012 (in Chinese)
[2]	钱前, 张爱华. 多关节机械臂轨迹跟踪自适应神经网络滑模控制[J]. 自动化仪表, 2018, 39(12): 39-42, 47 https://www.cnki.com.cn/Article/CJFDTOTAL-ZDYB201812010.htm QIAN Q, ZHANG A H. Self-adaptive neural network sliding mode control for trajectory tracking of multi-joint manipulator[J]. Process Automation Instrumentation, 2018, 39(12): 39-42, 47 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-ZDYB201812010.htm
[3]	董玉明, 俞立, 朱俊威. 基于自适应滑模的移动机械臂跟踪控制[J]. 控制工程, 2019, 26(1): 43-49 https://www.cnki.com.cn/Article/CJFDTOTAL-JZDF201901008.htm DONG Y M, YU L, ZHU J W. Adaptive sliding mode tracking control for mobile manipulators[J]. Control Engineering of China, 2019, 26(1): 43-49 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-JZDF201901008.htm
[4]	刘益标, 陈均. 基于径向基函数神经网络控制的机械臂轨迹误差研究[J]. 机床与液压, 2018, 46(15): 105-108 doi: 10.3969/j.issn.1001-3881.2018.15.024 LIU Y B, CHEN J. Research on trajectory error of mechanical arm based on radial basis function neural network control[J]. Machine Tools & Hydraulics, 2018, 46(15): 105-108 (in Chinese) doi: 10.3969/j.issn.1001-3881.2018.15.024
[5]	张程, 张卓. 自适应鲁棒控制在机械臂轨迹跟踪中的应用[J]. 组合机床与自动化加工技术, 2019(1): 86-89, 93 https://www.cnki.com.cn/Article/CJFDTOTAL-ZHJC201901023.htm ZHANG C, ZHANG Z. Application of adaptive robust control of the manipulator trajectory tracking[J]. Modular Machine Tool & Automatic Manufacturing Technique, 2019(1): 86-89, 93 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-ZHJC201901023.htm
[6]	吴浩楠, 胡立坤, 陈果, 等. 六自由度机械臂无模型自适应滑模控制[J]. 广西大学学报, 2019, 44(2): 387-395 https://www.cnki.com.cn/Article/CJFDTOTAL-GXKZ201902011.htm WU H N, HU L K, CHEN G, et al. Model-free adaptive sliding mode control method for 6-DOF manipulator[J]. Journal of Guangxi University, 2019, 44(2): 387-395 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-GXKZ201902011.htm
[7]	许洋洋, 王莹, 薛东彬. 机械臂神经网络控制优化与仿真[J]. 中国工程机械学报, 2018, 16(5): 416-420 https://www.cnki.com.cn/Article/CJFDTOTAL-GCHE201805008.htm XU Y Y, WANG Y, XUE D B. Neural network control optimization and simulation of robot arm[J]. Chinese Journal of Construction Machinery, 2018, 16(5): 416-420 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-GCHE201805008.htm
[8]	郑晓斌. 基于模糊滑模变结构的工业机械臂控制系统研究[J]. 陕西理工大学学报, 2019, 35(1): 22-27 doi: 10.3969/j.issn.1673-2944.2019.01.005 ZHENG X B. Research into industrial robotic arm control system based on fuzzy sliding mode variable structure[J]. Journal of Shaanxi University of Technology, 2019, 35(1): 22-27 (in Chinese) doi: 10.3969/j.issn.1673-2944.2019.01.005
[9]	DOAN Q V, LE T D, LE Q D, et al. A neural network-based synchronized computed torque controller for three degree-of-freedom planar parallel manipulators with uncertainties compensation[J]. International Journal of Advanced Robotic Systems, 2018, 15(2): 1-13
[10]	FANG Y M, ZHANG W H, YE X P. Variable structure control for space robots based on neural networks[J]. International Journal of Advanced Robotic Systems, 2014, 11(3): 35 doi: 10.5772/56371
[11]	HE W, YAN Z C, SUN Y K, et al. Neural-learning-based control for a constrained robotic manipulator with flexible joints[J]. IEEE Transactions on Neural Networks and Learning Systems, 2018, 29(12): 5993-6003 doi: 10.1109/TNNLS.2018.2803167
[12]	VAN PHAM C, WANG Y N. Robust adaptive trajectory tracking sliding mode control based on neural networks for cleaning and detecting robot manipulators[J]. Journal of Intelligent & Robotic Systems, 2015, 79(1): 101-114 doi: 10.1007/s10846-014-0162-2
[13]	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 doi: 10.1080/00207179.2018.1436774
[14]	刘金琨. RBF神经网络自适应控制及MATLAB仿真[M]. 北京: 清华大学出版社, 2015 LIU J K. RBF neural network adaptive control and MATLAB simulation[M]. Beijing: Tsinghua University Press, 2015 (in Chinese)