[1]倪元相,刘 芳.输出反馈式神经网络的机械臂轨迹跟踪控制[J].南京师大学报(自然科学版),2025,48(03):93-101.[doi:10.3969/j.issn.1001-4616.2025.03.011]
　Ni Yuanxiang,Liu Fang.Manipulator Motion Trajectory Tracking and Control Scheme var Output Feedback Style Neural Network[J].Journal of Nanjing Normal University(Natural Science Edition),2025,48(03):93-101.[doi:10.3969/j.issn.1001-4616.2025.03.011]
点击复制

输出反馈式神经网络的机械臂轨迹跟踪控制()

《南京师大学报（自然科学版）》[ISSN:1001-4616/CN:32-1239/N]

卷:
48
期数:
2025年03期
页码:
93-101
栏目:
计算机科学与技术
出版日期:
2025-06-20

文章信息/Info

Title:
Manipulator Motion Trajectory Tracking and Control Scheme var Output Feedback Style Neural Network
文章编号:
1001-4616(2025)03-0093-09
作者:
倪元相1; 刘 芳2
(1.广东理工学院电气与电子工程学院,广东 肇庆 526100)
(2.合肥工业大学电气与自动化工程学院,安徽合肥 230009)
Author(s):
Ni Yuanxiang1; Liu Fang2
(1.Electrical and Electronic Engineering College,Guangdong Technology College,Zhaoqing 526100,China)
(2.School of Electric Engineering and Automation,Hefei University of Technology,Hefei 230009,China)
关键词:
机械臂; 自适应跟踪控制; 人工神经网络; 角位置; 粒子群优化
Keywords:
robotic manipulator; adaptive tracking and control; artificial neural network; angular position; particle swarm optimization
分类号:
TP183
DOI:
10.3969/j.issn.1001-4616.2025.03.011
文献标志码:
A
摘要:
为提高干扰场景下机械臂运动轨迹的跟踪控制精度,提出了基于输出反馈和人工神经网络(ANN)的自适应机械臂控制方案. 通过3-DOF机械臂的运动学和动力学建模,推导出基于角位置信息的控制策略,其中考虑到了参数不确定性和动力模型误差,提高机械臂对未知干扰的鲁棒性. 使用以B样条函数(B-spline)为基函数的ANN,通过基于粒子群优化(PSO)算法的离线训练确定初始控制增益,并通过控制增益的在线更新提供自适应能力,实现跟踪误差和控制成本最小化. 仿真结果表明,所提方法在关节空间和笛卡尔空间中均能实现机械臂的准确控制和平滑移动,在有干扰场景下的控制性能显著优于比较方法,适用于激光切割、激光打印等高精度应用.
Abstract:
In order to improve the tracking and control accuracy of motion trajectories of robotic manipulator under disturbed conditions,an adaptive manipulator tracking and control scheme based on output feedback and artificial neural network(ANN)is proposed. With kinematics ands dynamics modeling of the 3-DOF manipulator,a control strategy based on angular position information is derived,in which the parameter uncertainty and dynamic model errors are considered,and the robustness of the manipulator to unknown disturbances is improved. Using the ANN with B-spline function as the basis function,the initial control gain is determined through offline training based on particle swarm optimization(PSO)algorithm,and the adaptive capability is provided through the online updates of the control gain,thereby minimizing tracking errors and control efforts. The simulation results show that the proposed method can achieve accurate control and smooth movement of the manipulator in both joint space and Cartesian space. The performance of the proposed method is significantly better than that of the comparison methods under disturbed conditions,and it is suitable for high-precision applications such as laser cutting and laser printing.

参考文献/References:

[1]QIN Z,XU Z D,SUN Q C,et al. Investigation of intelligent substation inspection robot by using mobile data[J]. International journal of humanoid robotics,2023,20(3):237-249.
[2]汤云峰,赵静,谢非,等. 基于改进遗传算法的机器人路径规划方法[J]. 南京师范大学学报(工程技术版),2021,27(3):49-55.
[3]FANG Y,HU J,LIU W,et al. Smooth and time-optimal S-curve trajectory planning for automated robots and machines[J]. Mechanism and machine theory,2019,137(1):127-153.
[4]侯宇翔,高焕兵,杜传胜,等. 改进人工势场法的机械臂轨迹规划[J]. 组合机床与自动化加工技术,2023,39(4):54-57,62.
[5]LIU Z,XU J,CHENG Q,et al. Trajectory planning with minimum synthesis error for industrial robots using screw theory[J]. International journal of precision engineering and manufacturing,2018,19(2):183-193.
[6]DAI C,LEFEBVRE S,YU K M,et al. Planning jerk-optimized trajectory with discrete time constraints for redundant robots[J]. IEEE transactions on automation science and engineering,2020,17(4):1711-1724.
[7]于雷,于博. 异类粒子群算法的机械臂轨迹多目标规划[J]. 组合机床与自动化加工技术,2020,31(5):31-35.
[8]ZHANG X,HUANG Y,RONG Y,et al. Optimal trajectory planning for wheeled mobile robots under localization uncertainty and energy efficiency constraints[J]. Sensors,2021,21(2):335-347.
[9]朱永强,鲍官军. 机械臂关节空间轨迹的累积非支配赋值NSGA-II算法规划[J]. 机械设计与制造,2022,19(9):300-304.
[10]RAHEEM K M H,NAJAF A N. Simulation 3-DOF RRR robotic manipulator under PID controller[J]. Journal of engineering and applied sciences,2020,15(2):410-414.
[11]刘军,段书凯,李天舒,等. 机械臂的自旋忆阻RBF神经网络控制系统设计[J]. 仪器仪表学报,2018,39(8):212-219.
[12]CHANG Z,HAO L,YAN Q,et al. Research on manipulator tracking control algorithm based on RBF neural network[J]. Journal of physics conference series,2021,1802(3):1-8.
[13]LIU Q,LI D,GE S S,et al. Adaptive bias RBF neural network control for a robotic manipulator[J]. Neurocomputing,2021,447(1):213-223.
[14]LIN C J,SIE T Y,CHU W L,et al. Tracking control of pneumatic artificial muscle-activated robot arm based on sliding-mode control[J]. Actuators,2021,10(3):66-83.
[15]WANG H,FANG L,SONG T,et al. Model-free adaptive sliding mode control with adjustable funnel boundary for robot manipulators with uncertainties[J]. Review of scientific instruments,2021,92(6):1-10.
[16]ZHAO J,XIU B,WANG J,et al. Adaptive task-space cooperative tracking control for manipulators with a desired trajectory estimator and avelocity observer[J]. International journal of robust and nonlinear control,2022(7):32-49.
[17]郑先杰,丁萌,武海雷,等. 线驱连续型机械臂无模型自适应控制[J]. 华中科技大学学报(自然科学版),2023,51(2):116-121.
[18]ZHANG Z,YANG S,ZHENG L.A Punishment mechanism-combined recurrent neural network to solve motion-planning problem of redundant robot manipulators[J]. IEEE transactions on cybernetics,2023,67(4):357-369.
[19]欧劲松,李蓉,尹辉,等. 基于奇异摄动的柔性关节机械臂约束跟随控制研究[J]. 应用数学和力学,2023,44(5):513-524.
[20]SIRA-RAMÍREZ H,AGUILAR-ORDUÑA M A,ZURITA-BUSTAMANTE E W. On the sliding mode control of MIMO nonlinear systems:an input-output approach[J]. International journal of robust and nonlinear control,2019,29(3):715-735.
[21]张宇涵,于潇雁,陈力. 基于泰勒级数的空间机器人时延神经网络控制[J]. 福州大学学报(自然科学版),2022,50(3):351-358.
[22]KHATIR S,KHATIR T,BOUTCHICHA D,et al. An efficient hybrid TLBO-PSO-ANN for fast damage identification in steel beam structures using IGA[J]. Smart structures and systems,2020,25(5):605-617.
[23]BELTRAN-CARBAJAL F,SILVA-NAVARRO G. Output feedback dynamic control for trajectory tracking and vibration suppression[J]. Applied mathematical modelling,2020,79(1):793-808.

备注/Memo

备注/Memo:
收稿日期:2023-08-11.
基金项目:国家自然科学基金资助项目(51907044)、广东省普通高校特色创新类资助项目(2021WTSCX112).
通讯作者:倪元相,副教授,研究方向:人工智能应用,机械优化设计与智能控制. E-mail:251859972@qq.com
更新日期/Last Update: 2025-06-20