针对水下机械臂在复杂水流环境下操作精度的提升问题，提出了一种基于自适应神经网络的滑膜控制策略。采用Newton-Euler法构建了适用于恒定均匀水流影响的双关节水下机械臂动力学模型，以提高模型精度并充分考虑实际应用中的环境因素。针对模型中存在的错误和不可预知的外部干扰，设计了融入自适应神经网络的滑膜控制器，有效补偿模型不准确带来的误差，抵抗多种类型的不确定外部扰动，从而显著改善了水下机械臂的轨迹跟踪速度和准确性。通过Matlab/Simulink平台进行仿真实验显示，相比于传统的PD滑模控制算法，提出的自适应神经网络滑膜控制方法在均匀水流干扰下，大大提高了水下机械臂的跟踪响应速度和精度，增强了系统在动态变化水流条件和模型不确定性面前的适应性。该策略的实施不仅提升了控制精度和响应速度，还保证了系统的稳定性，为水下机械臂在现代化海洋牧场等复杂水下作业环境中的应用提供了可行的解决方案。
To address the problem of improving the operating accuracy of underwater robotic arms in complex water current environments, a slip membrane control strategy based on adaptive neural network is proposed. A kinetic model of a double-jointed underwater robotic arm applicable to the influence of constant and uniform water currents is constructed by using the Newton-Euler method in order to improve the model accuracy and fully consider the environmental factors in practical applications. In response to the errors and unpredictable external disturbances in the model, a sliding film controller incorporating an adaptive neural network is designed to effectively compensate for the errors brought about by model inaccuracies and resist multiple types of uncertain external disturbances, thus significantly improving the trajectory tracking speed and accuracy of the underwater robotic arm. Simulation experiments via the Matlab/Simulink platform show that, compared with the traditional PD sliding mode control algorithm, the proposed adaptive neural network sliding film control method greatly improves the tracking speed and accuracy of the underwater robotic arm under the uniform water current disturbances, and enhances the adaptability of the system in the face of dynamically changing water current conditions and model uncertainties. The implementation of this strategy not only improves the control accuracy and response speed, but also ensures the stability of the system, which provides a feasible solution for the application of underwater robotic arms in complex underwater operating environments, such as modernised sea ranches.
2025,47(4): 76-83 收稿日期：2024-4-25
DOI：10.3404/j.issn.1672-7649.2025.04.013
分类号：U664.6
基金项目：农业农村部财政专项2024（B050101，B050102）；广东省财政专项资金项目（2024-03024025）；海南省科技专项资助（ZDYF2022GXJS347）；海南省自然科学基金资助（323MS121）；中国水产科学研究院基本科研业务费资助（2023TD58，2023TD93）
作者简介：唐宇(2000-),男,硕士研究生,研究方向为船舶工程和渔业安全
参考文献：
[1] WANG H H, HE X, CHEN Y, et al. Underwater soft robotichand with multisource coupling bioinspired soft palm and six fingers driven by water hydraulic.[J] ArXiv abs/2106.07011, 2021.
[2] OSCAR M M, CARLOS S C. Design, Modelling, control and simulation of biomimetic underwater robot[C]//2019 Latin American Robotics Symposium (LARS), 2019 Brazilian Symposiumon Robotics (SBR) and 2019 Workshopon Roboticsin Education (WRE), RioGrande, Brazil, 2019.
[3] XUE F Y, FAND Z F. Design and kinematics analysis for a cable driven underwater snake arm robot[J]. Journal of Physics: ConferenceSeries, 2020, 1654(1): 012028.
[4] 赵飞. 六自由度水下机械臂设计与分析[J]. 机电工程, 2023, 40(8): 1248-1258.
ZHAO F. Design and analysis of six-degree-of-freedom underwater robotic arm[J]. Electromechanical Engineering, 2023, 40(8): 1248-1258.
[5] 李琦琦, 徐向荣, 张卉. 基于自适应神经网络的机械臂滑模轨迹跟踪控制[J]. 工程设计学报, 2023, 30(4): 512520.
LI Q Q, XU X R, ZHANG H. Adaptive neural network based tracking control of sliding mode trajectory of robotic arm[J]. Journal of Engineering Design, 2023, 30(4): 512520.
[6] 陈丰毅, 解明扬, 张民, 等. 基于自适应神经网络的四旋翼无人机轨迹跟踪控制[J]. 控制工程, 2023, 30(7): 1267-1275.
CHEN F Y, XIE M Y, ZHANG M, et al. Trajectory tracking control of quadcopter UAV based on adaptive neural network[J]. Control Engineering, 2023, 30(7): 1267-1275.
[7] 乌云嘎, 徐会希, 姜志, 斌. 基于RBF神经网络的新型AUV自抗扰控制方法[J]. 舰船科学技术, 2023, 45(18): 85-91.
U Y G, XU H X, JIANG Z B. A novel AUV self-immunity control method based on RBF neural network[J]. Ship Science and Technology, 2023, 45(18): 85-91.
[8] 张成举, 王聪, 曹伟等. 欠驱动USV神经网络自适应轨迹跟踪控制[J]. 哈尔滨工业大学学报, 2020, 52(12): 17.
ZHANG C J, WANG C, CAO W, et al. Adaptive trajectory tracking control of underdriven USV neural network[J]. Journal of Harbin Institute of Technology, 2020, 52(12): 17.
[9] 高阳, 张晓晖, 高玉儿, 等. 基于神经网络和模糊补偿的水下机械臂控制[J]. 计算机工程与应用, 2022, 58(15): 317-323.
GAO Y, ZHANG X H, GAO Y E, et al. Underwater robotic arm control based on neural network and fuzzy compensation[J]. Computer Engineering and Application, 2022, 58(15): 317-323.
[10] 付涛, 王大镇, 弓清忠, 等. 改进神经网络自适应滑模控制的机器人轨迹跟踪控制[J]. 大连理工大学学报, 2014, 54(5): 523-530.
FU T, WANG D Z, GONG Q Z, et al. Improved neural network adaptive sliding mode control for robot trajectory tracking control[J]. Journal of Dalian University of Technology, 2014, 54(5): 523-530.
[11] 李正楠, 殷玉枫, 张锦, 等. 多关节机械臂反演滑模神经网络干扰观测器控制[J]. 机械设计, 2021, 38(3): 126131.
LI Z N, YIN Y F, ZHANG J, et al. Inverse sliding mode neural network interference observer control for a multi-joint robotic arm[J]. Mechanical Design, 2021, 38(3): 126131.
[12] 孟琪迪, 南新元, 张永兴. 基于PD型迭代学习的机械臂轨迹跟踪控制[J]. 组合机床与自动化加工技术, 2022, (11): 62-65+69.
MENG Q D, NAN X Y, ZHANG Y X. Trajectory tracking control of robotic arm based on PD-type iterative learning[J]. Combined Machine Tools and Automated Machining Technology, 2022, (11): 62-65+69.
[13] 张卉, 朱永飞, 刘雪飞, 等. 基于模糊迭代Q学习的冶金工业机器人轨迹跟踪控制研究[J]. 工程设计学报, 2022, 29(5): 564-571.
ZHANG H, ZHU Y F, LIU X F, et al. Research on trajectory tracking control of metallurgical industrial robots based on fuzzy iterative Q-learning[J]. Journal of Engineering Design, 2022, 29(5): 564-571.
[14] 梁相龙, 姚建勇. 带有输出约束的液压机械臂自适应神经网络力跟踪控制[J/OL]. 控制理论与应用, 110[20240120].
LIANG X L, YAO J Y. Adaptive neural network force tracking control of hydraulic manipulator arm with output constraints[J/OL]. Control Theory and Applications, 110[20240120].
[15] 赵兴强, 刘振, 高存臣. 机械臂系统自适应神经网络滑模控制器设计[J]. 控制工程, 2023, 30(9): 1624-1629.
ZHAO X Q, LIU Z, GAO C C. Design of adaptive neural network sliding mode controller for robotic arm system[J]. Control Engineering, 2023, 30(9): 1624-1629.
[16] 袁凯, 刘延俊, 孙景余, 等. 基于模糊RBF神经网络的水下机械臂控制研究[J]. 工程设计学报, 2019, 26(6): 675-682.
YUAN K, LIU Y J, SUN J Y, et al. Research on underwater robotic arm control based on fuzzy RBF neural network[J]. Journal of Engineering Design, 2019, 26(6): 675-682.
[17] 赵伟, 张晓晖, 杨松楠. 基于动力学模型分块逼近的水下机械臂RBF滑模控制算法研究[J]. 西安理工大学学报, 2021, 37(4): 555-561.
ZHAO W, ZHANG X H, YANG S N. Research on RBF sliding mode control algorithm of underwater robotic arm based on block approximation of dynamic model[J]. Journal of Xi'an University of Technology, 2021, 37(4): 555-561.
[18] 葛大会, 尤云祥, 冯爱春. 海流环境下二关节机械臂动力学建模及其跟踪控制[J]. 应用数学和力学, 2023, 44(6): 666-678.
GE D H, YOU Y X, FENG A C. Dynamics modelling of a two-jointed robotic arm and its tracking control in a sea current environment[J]. Applied Mathematics and Mechanics, 2023, 44(6): 666-678.
