漂浮基空间机械臂鲁棒自适应滑模神经网络控制  

Robust adaptive sliding mode neural network control for floating-based space manipulator

作　　者：徐桂新 宋齐 于潇雁[1,2] 陈力[1,2] Xu Guixin;Song Qi;Yu Xiaoyan;Chen Li(School of Mechanical Engineering and Automation,Fuzhou University,Fujian Fuzhou,350116,China;Key Laboratory of Fluid Power and Electro-Hydraulic Intelligent Control in Fujian University,Fujian Fuzhou,350116,China)

机构地区：[1]福州大学机械工程及自动化学院,福建福州350116 [2]流体动力与电液智能控制福建省高校重点实验室(福州大学),福建福州350116

出　　处：《机械设计与制造工程》2021年第12期23-28,共6页Machine Design and Manufacturing Engineering

基　　金：福建省工业机器人基础部件技术重大研发平台(2014H21010011);国家自然科学基金资助项目(51741502)。

摘　　要：针对存在外部干扰的漂浮基刚性空间机械臂,提出了基于径向基函数神经网络(RBFNNs)的鲁棒自适应控制器。该方法将滑模技术、RBFNNS分块逼近技术以及自适应技术相结合,实现了在实际模型与理想模型存在误差情况下高精度的位置跟踪以及快速逼近,更好地保证了机械臂在动态环境下的稳定性,提高了系统的性能,并基于Lyapunov稳定性定理确定了机械臂系统的稳定性。最后通过MATLAB仿真计算,证明了所设计的控制方法的优越性。A robust adaptive controller based on radial basis function neural networks(RBFNNs) is proposed for a floating rigid space manipulator with external disturbances. This method combines sliding mode technology, RBFNNs block approximation technology and adaptive technology to realize high-precision position tracking and fast approximation when there are errors between the actual model and the ideal model, better ensure the stability of the manipulator in the dynamic environment, i.e. external interference, and improve the performance of the system. The stability of the system is determined based on Lyapunov stability theorem. Finally, the superiority of the control method designed in this paper is proved by MATLAB simulation.

关 键 词：漂浮基机械臂 径向基函数神经网络 自适应控制 鲁棒控制 滑模控制 

分 类 号：TP241[自动化与计算机技术—检测技术与自动化装置]