未知环境下Elman网络X-Y平台力控制  

Force Control of X-Y Table Based on Elman Neural Network in Unknown Environment

作　　者：温淑焕[1] 强艳辉[1] 

机构地区：[1]燕山大学西校区电院工业计算机控制工程河北省重点实验室,秦皇岛066004

出　　处：《武汉理工大学学报》2009年第24期128-131,共4页Journal of Wuhan University of Technology

基　　金：河北省科技攻关项目(07213526);燕山大学博士基金(B168)

摘　　要：X-Y平台执行磨削、抛光等作业时,需要在位置跟踪的同时保持与工件一定的接触力。针对此种受限X-Y平台,提出了一种在不改变X-Y平台位置控制器的前提下实现力控制的方案,即系统的外环为力控制回路,根据力误差修正参考位置,使平台与环境的实际接触力跟踪期望力。在力控制回路中,利用改进Elman网络在线辨识未知环境,不需要环境位置和刚度的先验知识,这种方法有误差补偿作用,对干扰和环境等不确定因素具有鲁棒性,仿真结果表明了控制方案的有效性。The end elector of a X- Y table is required to keep precise position tracking and keep a contact force along the out-ward normal of the constraint surface in tasks such as sharpening and grind. In this paper, a kind of force control strategy for X-Y table is proposed on the premise that the robot position controller is not changed, namely, the outer loop is force control loop. It modifies the reference position according to the force error so that contact force between the X- Y table and the environment can track the reference force. In force control loop, an improved Elman neural network is used for identifying unknown environment online so that the prior knowledge of the environment is not required. This method can compensate the errors and has robusticity to the uncertainties and disturbance of the environment. Simulation results show that this control scheme is effective.

关 键 词：X-Y平台 力控制 改进ELMAN神经网络 未知环境 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]