针对带有执行器输入死区的不确定机械臂系统,提出了基于神经网络的自适应固定时间滑模控制方法。基于自适应神经网络和最小参数学习方法,设计了机械臂闭环系统的自适应神经网络滑模控制器,以有效地补偿机械臂的输入死区环节,且仅需一个在线更新参数。结合固定时间稳定性理论证明了所设计的控制器不仅能够实现滑模面的可达性,而且可保证闭环系统的位置跟踪误差信号在固定时间内收敛到以零为中心的任意小邻域内,然后指数收敛到零。最后,仿真结果验证了所提出控制方法的有效性,在一定程度上改善了机械臂跟踪控制的瞬态和稳态性能。
An adaptive fixed-time sliding mode control method based on neural network is proposed for uncertain manipulator systems with actuator input dead zone. Based on the adaptive neural network and the minimum parameter learning method, the adaptive neural network sliding mode controller of the closed loop system of the manipulator is designed to effectively compensate the input dead zone of the manipulator, and only one parameter is updated online. Based on the fixed-time stability theory, it is proved that the controller can not only achieve the reachability of the sliding mode surface, but also ensure that the position tracking error signal of the closed-loop system converges to any small neighborhood with zero as the center in a fixed time, and then exponentially converges to zero. Finally, the simulation results verify the effectiveness of the proposed control method, and improve the transient and steady-state performance of the manipulator's tracking control to a certain extent.
[1] 孙玉娇, 杨洪勇, 于美妍. 基于领航跟随的多机器人系统有限时间一致性控制研究[J]. 复杂系统与复杂性科学, 2020, 17(4): 66-72.
Sun Y J, Yang H Y, Yu M Y. The finite time consistency control of multi-robot systems based on leader-following systems based on leader-following[J]. Complex Systems and Complexity Science, 2020, 17(4): 66-72.
[2] 阮晓钢, 周静, 张晶晶, 等. 基于子目标搜索的机器人目标导向RRT路径规划算法[J]. 控制与决策, 2020, 35(10): 2543-2548.
Ruan X G, Zhou J,Zhang J J, et al. Robot goal guide RRT path planning based on sub-target search[J]. Control and Decision, 2020, 35(10): 2543-2548.
[3] Yen V T, Wang Y N, Cuong P V. Robust adaptive sliding mode neural networks control for industrial robot manipulators[J]. International Journal of Control Automation and Systems, 2019, 17(3): 783-792.
[4] Zhang C L, Yang T, Sun N, et al. An adaptive fuzzy control method of single-link flexible manipulators with input dead-zones[J].International Journal of Fuzzy Systems, 2020, 22(8): 2521-2533.
[5] Yu L, Fei S M, Huang J, et al. Trajectory switching control of robotic manipulators based onRBF neural networks[J]. Circuits Systems and Signal Processing, 2014, 33(4): 1119-1133.
[6] 朱伟, 陈坤, 王谦, 等. 基于自适应滑模控制的分数阶蔡氏电路系统动力学分析与控制[J]. 复杂系统与复杂性科学, 2018, 15(2): 87-94.
Zhu W, Chen K, Wang Q, et al. Dynamic analysis and control of fractional-order Chua’s circuit system based on adaptive sliding mode control[J]. Complex Systems and Complexity Science, 2018, 15(2): 87-94.
[7] 蔡运颂, 许璟, 牛玉刚. 基于自适应多尺度超螺旋算法的无人机集群姿态同步控制[J]. 自动化学报, 2023, 49(8): 1656-1666.
Cai Y S, Xu J, Niu Y G. Attitude consensus control of UAV swarm based on adaptive multi-scale super-twisting algorithm[J]. Acta Automatic Sinica, 2023, 49(8): 1656-1666.
[8] Ruchika, Naveen Kumar. Control of coordinated multiple mobile manipulators with neural network-based fast terminal sliding mode control[J]. International Journal of Dynamics and Control, 2024, 12: 796–812.
[9] 徐宝珍, 宋公飞, 王超, 等. 机械臂自适应非奇异快速终端滑模控制[J]. 电光与控制, 2021, 28(5): 46-50.
Xu B Z, Song G F, Wang C, et al. Adaptive non-singular fast terminal sliding mode control of manipulator[J]. Electronics Optics and Control,2021, 28(5): 46-50.
[10] Polyakov A. Nonlinear feedback design for fixed-time stabilization of linear control systems[J]. IEEE Transactions on Automatic Control, 2012, 57(8): 2106-2110.
[11] 魏源昊, 沈艳霞. 机械臂固定时间非奇异快速终端滑模控制[DB/OL].[2024-03-02].https://doi.org/10.14107/j.cnki.kzgc.20230709.
Wei Y H, Shen Y X. Fixed-time non-singular fast terminal sliding mode control for roboticarm[DB/OL].[2024-03-02].https://doi.org/10.14107/j.cnki.kzgc.20230709.
[12] Zhang L Y, Liu H, Tang D F, et al. Adaptive fixed-time fault-tolerant tracking control and its application for robot manipulators[J]. IEEE Transactions on Industrial Electronics, 2021, 69(3): 2956-2966.
[13] Liu A Q, Zhao H H, Song T, et al. Adaptive control of manipulator based on neural network[J]. Neural Computing and Applications, 2021, 33(9): 4077-4085.
[14] Wang F, Chao Z Q, Huang L B, et al. Trajectory tracking control of robot manipulator based on RBF neural network and fuzzy sliding mode[J]. Cluster Computing, 2019, 22(3): 5799-5809.
[15] Zhang S, Yang P X, Kong L H, et al. Neural networks-based fault tolerant control of a robot via fast terminal sliding mode[J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2021, 51(7): 4091-4101.
[16] He W, Dong Y T, Sun C Y. Adaptive neural impedance control of a robotic manipulator with input saturation[J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2016, 46(3): 334-344.
[17] Ni J, Liu L, Liu C, et al. Fast fixed-time nonsingular terminal sliding mode control and its application to chaos suppression in power system[J]. IEEE Transactions on Circuits and Systems-II: Express Briefs, 2016, 64(2): 151-155.
[18] Sai H Y, Xu Z B, He S, et al. Adaptive nonsingular fixed-time sliding mode control for uncertain robotic manipulators under actuator saturation[J]. ISA Transactions, 2022, 123: 46-60.
[19] Liu Z, Zhang O Y, Gao Y B, et al. Adaptive neural network-based fixed-time control for trajectory tracking of robotic systems[J]. IEEE Transactions on Circuits and Systems-II: Express Briefs, 2023, 70(1): 241-245.
[20] Moawad N M. Development of an adaptive radial basis function neural network estimator-based continuous sliding mode control for nonlinear systems[J]. ISA Transactions, 2019, 87(3): 200-216.
