摘要
讨论了载体位置无控、姿态受控情况下,空间机械臂姿态、末端爪手协调运动的自适应神经网络控制问题。由拉格朗日方法,建立了漂浮基空间机械臂的系统动力学方程。以此为基础,借助于RBF神经网络技术、GL矩阵及其乘积算子定义,对空间机械臂系统进行了神经网络建模。最后针对空间机械臂所有惯性参数未知的情况下,设计了空间机械臂载体姿态与机械臂末端爪手协调运动的自适应神经网络控制方案。提出的控制方案不要求系统动力学方程具有关于惯性参数的线性性质,且无需预知系统惯性参数的任何信息;并无需对神经网络进行离线训练、学习,因此更便于实时应用。一个平面两杆漂浮基空间机械臂系统的数值仿真,证实了该控制方案的有效性。
The control problem of coordinated motion of a free-floating space manipulator is discussed. Through the Lagrangian approach, the dynamic equation of the free-floating space manipulator was derived. Based on the above results, the free-floating space manipulator system was modeled by the RBF neural network technique, the GL matrix and its product operator. With all unknown inertial parameters, the adaptive neural network control scheme for coordinated motion between the base attitude and the end-effector of the free-floating space manipulator was developed. This proposed control scheme need neither linearly parameterize the dynamic equation of the system and know any actual inertial parameters, nor train and learn neural network offiine. Thusly it is prone to a real-time and online application. A planar free-floating space manipulator with two links was simulated to verify the feasibility of the proposed control scheme.
出处
《工程力学》
EI
CSCD
北大核心
2009年第7期181-187,共7页
Engineering Mechanics
基金
国家自然科学基金项目(10372022
10672040)
福建省自然科学基金项目(E0410008)
