基于小波基模糊神经网络的漂浮基柔性空间机械臂轨迹跟踪控制  

WAVELET BASED FUZZY NEURAL NETWORK CONTROL FOR FREE-FLOATING SPACE FLEXIBLE MANIPULATOR TO TRACK DESIRED TRAJECTORY

作　　者：黄登峰[1] 陈力[1] 

机构地区：[1]福州大学机械工程及自动化学院,福州350108

出　　处：《工程力学》2012年第12期360-364,共5页Engineering Mechanics

基　　金：国家自然科学基金项目(11072061;10672040);福建省自然科学基金项目(2010J01003)

摘　　要：讨论了载体位置不受控、姿态受控情况下,参数未知漂浮基柔性空间机械臂关节空间协调运动的轨迹跟踪控制问题。依据系统动量守恒关系和拉格朗日第二类方程,由假设模态法,建立了漂浮基柔性空间机械臂的系统动力学方程。以此为基础,针对系统参数未知的情况,设计了一种小波基模糊神经网络的控制方案,以使柔性空间机械臂的载体姿态到达期望位置的同时,机械臂关节铰能够协调地跟踪关节空间的期望轨迹。该方案具有无需预知柔性空间机械臂的模型和系统参数的优点,且网络权值是通过在线学习进行调整,节省了离线训练的时间。系统的数值仿真表明了所提出方案的有效性和可行性。The trajectory tracking control for the coordinated motion of a free-floating space flexible manipulator with unknown parameters is developed. With the momentum conservation law, the Lagrange equation of the second kind is utilized to model the dynamic function of the space flexible manipulator incorporating the assumed mode method. In case of system parameters are unknown, a wavelet based fuzzy neural network control scheme is designed. The control scheme can control the base attitude and joint angle of manipulator to track desired trajectories in joint space simultaneously. It requires no prior knowledge about a dynamic model and system parameters, and saves the off-line training time because the network weights are adjusted through online learning. Simulation result demonstrates the validity and feasibility of the proposed control scheme.

关 键 词：漂浮基柔性空间机械臂 小波基模糊神经网络 参数未知 关节空间 协调运动 轨迹跟踪控制 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置]