两自由度并联机器人的RBF神经网络辨识自适应控制  

RBF Neural Network Identification Adaptive Control of a Two DOF Parallel Robot

作　　者：陈正洪[1] 王勇[1] 李艳[1] 

机构地区：[1]山东大学机械工程学院

出　　处：《武汉理工大学学报（交通科学与工程版）》2008年第2期210-213,共4页Journal of Wuhan University of Technology（Transportation Science & Engineering）

基　　金：国家自然科学基金项目(批准号:50375085);山东省自然科学基金项目资助(批准号:Y2002F13)

摘　　要：针对平面两自由度五杆并联机器人的轨迹跟踪问题,提出了一种基于RBF神经网络的自适应PID控制方法.该控制方案利用RBF神经网络自适应学习辨识并联机器人系统的未知非线性动态,可以在线调整PID控制参数以实现高精度控制.仿真结果显示该控制策略可以精确实现对于并联五杆机器人的轨迹跟踪控制,该方法的自适应性和跟踪性能均优于传统的PID控制.With the development of parallel manipulators, the study of parallel mechanisms has become a hot point in mechanical fields. A parallel robot has several advantages over a serial robot, such as high mechanical rigidity, high payload, high precision and so on. Accurate trajectory control of a robot is essential in practical use of robot. This paper presents adaptive Proportion Integral Differential （PID） control algorithm based on Radial Basis Function （RBF） neural network for trajectory tracking of a two degree of freedom （DOF） parallel robot. In this scheme, a radial basis function neural network is used to approximate the unknown nonlinear dynamics of the robot, then the PID parameters can be adjusted online and high precision can be obtained. Simulation results show that the control algorithm can accurately track trajectories of a 2-DOF parallel robot. The results also indicate that the system robustness and tracking performance are superior to the classic PID method.

关 键 词：并联机器人 RBF神经网络 辨识 自适应PID控制 神经网络 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]