Abstract:An adaptive control scheme for redundant variable geometry truss manipulators is proposed, based on fuzzy neural network in this paper. The fuzzy neural network model is used to identify inverse dynamic model of redundant variable geometry truss manipulators, and conventional feedback controller is applied to compensation of external interference and close-loop control. The simulation calculation for a four-celled tetrahedron based variable geometry truss manipulator is give. The method is proved to have good track accuracy and anti-interference characteristics.
[1] Ma Xiaomin. Inverse Identification and Closed-Loop Control of Dynamic Systems Using Neural Networks. ControlTheory and Application, 1997,14(6) [2] Xu Liju, Li Hong, Fan Shouwen. Analytical Model Method For Dynamics of N-Celled Tetrahedron-TetrahedronVariable Geometry Truss Manipulators. ASME Mechanisms Conference,Atlanta,USA, 1998 [3] 徐礼钜,高翔.冗余自由度变几何桁架机器人的轨迹规划.四川联合大学学报(自然科学版),1999,(5) [4] 陈卫田.施颂椒,张钟俊.基于神经网络的非线性自适应控制.控制理论和应用,1996,13(5) [5] Masao TANAKA. Configuration Control of the Truss-Type Parallel Manipulator by the Modular Neural NetworkModel. JSME International Journal Series C,1992 [6] 王士同.神经模糊系统及其应用.北京航空航天大学出版社