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

作　　者：肖凡[1] 李光[1] 周鑫林[1] Xiao Fan, Li Guang , Zhou Xinlin(School of Mechanical Engineering, Hunan University of Technology, Hu＇nan Zhuzhou 412007, Chin)

机构地区：[1]湖南工业大学机械工程学院,湖南株洲412007

出　　处：《机械科学与技术》2018年第5期669-674,共6页Mechanical Science and Technology for Aerospace Engineering

基　　金：湖南省自然科学基金项目(2018JJ4079)资助

摘　　要：针对多连杆机械臂模型系统信息不完整、存在外界干扰等问题,设计了一种新型的GA-RBF神经网络闭环自适应控制系统。该系统利用径向基函数(RBF)神经网络来逼近并补偿系统的模型误差和外界扰动,在基于计算力矩法的基础上实现对机械臂的轨迹跟踪控制,并采用遗传算法(GA)对RBF神经网络权值进行在线优化,确保机械臂控制系统能在更短时间内获得稳定,实现了高精度的轨迹跟踪,提高了轨迹跟踪的性能。MATLAB数值仿真的结果验证了该方法的有效性。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 MATLAB 

分 类 号：TG156[金属学及工艺—热处理]