An online self-gain tuning method using neural networks for nonlinear PD computed torque controller of a 2-dof parallel manipulator

详细信息    查看全文

• 作者：Tien Dung Le ^{dung.letien@gmail.com}Author Vitae ; Hee-Jun Kang ; ^{hjkang@ulsan.ac.kr}Author Vitae ; Young-Soo Suh ^{yssuh@ulsan.ac.kr}Author Vitae ; Young-Shick Ro ^{ysro@uou2.ulsan.ac.kr}Author Vitae
• 关键词：Parallel manipulator ; Nonlinear PD computed torque controller ; Online self gain tuning ; Neural networks.
• 刊名：Neurocomputing
• 出版年：2013
• 出版时间：20 September, 2013
• 年：2013
• 卷：116
• 期：Complete
• 页码：53-61
• 全文大小：785 K

文摘

Parallel manipulators have advantages like high accuracy, high stiffness, high payload capability, low moving inertia, and so on. In this paper, a detailed study to apply an online self gain tuning method using neural networks for nonlinear PD computed torque controller to a 2-dof parallel manipulator is presented. A novel nonlinear PD computed torque controller is achieved by combining conventional computed torque controller and auto tuning method using neural networks which has advantages such as flexibility, adaptation and learning ability. The proposed controller has a simple structure and little computation time while securing good performance in tracking trajectories of parallel manipulators. To verify the control performance, various simulations of a 2-dof parallel manipulator are conducted. Simulation results show the effectiveness of the proposed method in comparison with the conventional computed torque controller.