机械科学与技术2018，Vol.37Issue(5)：669-674,6.DOI:10.13433/j.cnki.1003-8728.2018.0503
多连杆机械臂GA-RBF神经网络轨迹跟踪控制
GA-RBF Neural Network Control for Trajectory Tracking of Multilink Robot Arm
摘要
Abstract
A new closed loop adaptive control system of GA-RBF neural network is designed to solve the problem of incomplete information and external disturbance of multilink robot arm model system.The system uses radial basis function (RBF) neural network to approximate and compensate the system model errors and external disturbance.Based on the computed torque method of manipulator,it realizes trajectory tracking control;based on genetic algorithm (GA) and the online optimization of RBF network weights,it ensures that the manipulator control system can get stable in a shorter period of time,to achieve high precision tracking trajectory,and improves the performance of trajectory tracking.The effectiveness of the proposed method is verified by the results of MATLAB simulation.关键词
计算力矩法/RBF神经网络/遗传算法/机械臂/轨迹跟踪/MATLABKey words
computational torque method/RBF neural network/genetic algorithm/mechanical arm/trajectory tracking/MATLAB分类
矿业与冶金引用本文复制引用
肖凡,李光,周鑫林..多连杆机械臂GA-RBF神经网络轨迹跟踪控制[J].机械科学与技术,2018,37(5):669-674,6.基金项目
湖南省自然科学基金项目(2018JJ4079)资助 （2018JJ4079）
