关于机器人的机械臂对目标轨迹跟踪优化控制  

Optimal Trajectory Tracking Control for Robot Manipulator

作　　者：石佳玉[1] 马建伟[1] 张海涛[1] 宋晓娜[1] 

机构地区：[1]河南科技大学信息工程学院,河南洛阳471023

出　　处：《计算机仿真》2016年第12期338-341,389,共5页Computer Simulation

基　　金：国家自然科学基金(61203047)

摘　　要：针对上界不确定机械臂的轨迹跟踪问题,提出了一种基于RBF神经网络的滑模控制与模糊控制相结合的控制方法,分别采用状态反馈和滑模变结构对系统确定部分和不确定部分进行控制,同时建立模糊系统用来进行系统控制量的切换。而对于实际系统中所存在的不确定因素上界难以预测的问题,根据神经网络的特点,提出利用自适应神经网络对不确定部分的上界进行在线学习。最后对上述控制方法进行了仿真验证,得到了预期的控制效果。仿真结果表明,在存在外部扰动和模型误差的情况下,改进控制器可以实现对系统期望轨迹的稳定跟踪。Aiming at the trajectory tracking problem of uncertain upper bound manipulator, a control method combining sliding mode control and fuzzy control based on RBF neural network is proposed, state feedback and sliding mode variable structure are used to control the certain and uncertain part of system, at the same time the fuzzy system is used for switch of the system control. Because the uncertain upper bound is difficult to predict in the actual system, the upper bound of uncertain part can be learned online by adaptive neural network according to its feature. Finally, the control method is verified by simulation. Expected control results are obtained. The simulation results show that the controller can achieve stable tracking for the desired trajectory of system with disturbance and model error.

关 键 词：不确定上界 神经网络 滑模控制 模糊控制 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置]