Computer Engineering and Applications ›› 2015, Vol. 51 ›› Issue (9): 82-86.

Previous Articles     Next Articles

Trajectory tracking control of robot manipulator—model reference adaptive control for robot manipulator based on EC-RBF neural networks

YANG Jianfeng, ZHANG Cui, ZHANG Feng   

  1. College of Automation & Electrical Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China
  • Online:2015-05-01 Published:2015-05-15

机械臂轨迹跟踪控制——基于EC-RBF神经网络的机械臂模型参考自适应控制

杨剑锋,张  翠,张  峰   

  1. 兰州交通大学 自动化与电气工程学院,兰州 730070

Abstract: According to the problem that the tracking accuracy is not high enough in trajectory tracking control of robot manipulators, a model reference adaptive control scheme based on EC-RBF neural networks is adopted to achieve robot manipulator model identification and trajectory tracking control. This control scheme contains two RBF neural networks which are trained offline and online, using EC-RBF learning algorithm. The one is used to identify the robot manipulator’s model, and the other one is used to achieve its trajectory tracking control. Simulation result of 2-degree-of-freedom robot manipulator demonstrates that using this method for robot manipulator trajectory tracking control has high control accuracy, and the networks which gain high training speed because of the EC-RBF learning algorithm make the control process faster.

Key words: robot manipulator trajectory tracking, model reference adaptive control, Entropy Clustering-Radial Basis Function(EC-RBF) neural networks

摘要: 针对机械臂运动轨迹控制中存在的跟踪精度不高的问题,采用了一种基于EC-RBF神经网络的模型参考自适应控制方案对机械臂进行模型辨识与轨迹跟踪控制。该方案采用了两个RBF神经网络,运用EC-RBF学习算法,采用离线与在线相结合的方法来训练神经网络,一个用来实现对机械臂进行模型辨识,一个用来实现对机械臂轨迹跟踪控制。对二自由度机械臂进行仿真,结果表明,使用该控制方案对机械臂进行轨迹跟踪控制具有较高的控制精度,且因采用EC-RBF学习算法使网络具有更快的训练速度,从而使得控制过程较迅速。

关键词: 机械臂轨迹跟踪, 模型参考自适应控制, 熵聚类-径向基函数(EC-RBF)神经网络