Adaptive control of parallel manipulators via fuzzy-neural network algorithm

作     者：Dachang ZHU Yuefa FANG 

作者机构：College of Mechanical and Electrical Control Engineering Beijing Jiaotong University Beijing 100044 China 

出 版 物：《控制理论与应用（英文版）》 (JOURNAL OF CONTROL THEORY AND APPLICATIONS)

年 卷 期：2007年第5卷第3期

页      面：295-300页

学科分类：08[工学] 0835[工学-软件工程] 0802[工学-机械工程] 080201[工学-机械制造及其自动化] 

基　　金：This work was supported by the National Natural Science Foundation of China (No. 50375001) 

主　　题：Parallel manipulator Adaptive control Fuzzy neural network algorithm Simulation 

摘      要：This paper considers adaptive control of parallel manipulators combined with fuzzy-neural network algorithms （FNNA）. With this algorithm, the robustness is guaranteed by the adaptive control law and the parametric uncertainties are eliminated. FNNA is used to handle model uncertainties and external disturbances. In the proposed control scheme, we consider modifying the weight of fuzzy rules and present these rules to a MIMO system of parallel manipulators with more than three degrees-of-freedom （DoF）. The algorithm has the advantage of not requiring the inverse of the Jacobian matrix especially for the low DoF parallel manipulators. The validity of the control scheme is shown through numerical simulations of a 6-RPS parallel manipulator with three DoF.