基于GA-SVM逆系统的机械臂内模控制  

Internal Model Control Based on GA-SVM and Inverse System of Manipulator

作　　者：胡立坤[1] 王頔[1] 黄文琴[1] 

机构地区：[1]广西大学电气工程学院,南宁530004

出　　处：《控制工程》2014年第3期415-418,共4页Control Engineering of China

基　　金：国家自然科学基金资助项目(51177018);广西自然科学基金项目(2012GXNSFBA053144)

摘　　要：六自由度机械臂系统具有强耦合、多输入多输出、非线性的特性,且难以求解精确的动力学模型。针对上述问题,提出了一种基于GA-SVM逆系统的六自由度机械臂内模控制方法。将逆系统方法用于六自由度机械臂的解耦可以有效简化控制器的设计,为了避免逆系统方法复杂的解析过程,采用基于支持向量机(SVM)辨识逆系统模型以实现解耦,并用遗传算法(GA)优化SVM系统参数以提高模型的准确性。同时,为了弥补SVM辨识逆系统的误差以及抑制系统存在的扰动,设计内模控制器以保证系统的鲁棒性和稳定性。实验结果表明,该方法不需要知道六自由度机械臂的数学模型和内部结构,也能实现各关节位置的快速精确定位控制,且具有良好的鲁棒性,结构简单,需要调节的参数少,易于工程实现。6 DOF manipulator is a strongly coupled, nonlinear and multiple input multiple output control plant, and it is difficult to obtain an accurate dynamic model. View of the above, the method internal model control based on GA-SVM and inverse system is presen- ted. To simplify the controller, inverse system method is used for decoupling. Inverse system is identified based on SVM identification to overcome the complex parsing process. In order to further improve the accuracy of model, its parameters are optimized by Genetic al- gorithm （GA）. Meanwhile, the internal model controller is introduced to guarantee the robustness while there is modeling error or dis- turbance. The tracking performance shows that the method has good robustness without knowing the mathetnatical model, and it is easy accomplishment in engineering.

关 键 词：机械臂 支持向量机 逆系统 遗传算法 内模控制 

分 类 号：TP241.2[自动化与计算机技术—检测技术与自动化装置]