FCMAC在六自由度并联机构轨迹跟踪中的应用  

Application of fuzzy cerebellar model articulation controller on 6-DOF parallel mechanism tracking

作　　者：胡陟[1] 高国琴[1] 江道根[1] 

机构地区：[1]江苏大学,镇江212013

出　　处：《机械设计与制造》2010年第9期52-54,共3页Machinery Design & Manufacture

基　　金：江苏省自然科学基金项目(BK2009202)

摘　　要：六自由度并联机构控制系统中存在不确定性和非线性因素,使得对其轨迹跟踪的过程中会不断有误差产生。神经网络控制器以其在线自学习的功能,能实时反应并消除误差。用模糊理论对结构简单的小脑模型关节控制器(CMAC)的空间划分方式进行模糊化处理,并通过BP学习算法对CMAC的空间划分方式进行在线调整,所得到模糊小脑模型关节控制器(FCMAC)有更高的自适应能力。仿真实验结果表明,FCMAC的在线学习功能优于传统的CMAC;用FCMAC对六自由度并联构进行轨迹跟踪,能较好地消除误差,有较高的控制精度。6-DOF parallel mechanism has its nonlinearities and uncertainties ,which cause continuous error in the process of trajectory tracking. ＂Neural network controllers have an ability of online self-learning, thus it can response and eliminate error in real-time. By using fuzzy theory to fuzzily the space division way of CMAC and adapting it on line through BP learning algorithm,the achieving fuzzy cerebellar model articulation controller （FCMAC） has a better self-adaptive ability. Simulation results show that FCMAC has a better online learning quality than traditional CMAC; and FCMAC can do well in eliminating error on 6-DOF parallel mechanism trajectory tracking,which is of high accuracy.

关 键 词：六自由度并联机构 轨迹跟踪 小脑模型关节控制器 模糊小脑模型关节控制器 

分 类 号：TH12[机械工程—机械设计及理论] TP242.2[自动化与计算机技术—检测技术与自动化装置]