首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于神经网络的六维力传感器静态标定方法研究
引用本文:李海滨,段志信,高理富,康补晓.基于神经网络的六维力传感器静态标定方法研究[J].内蒙古工业大学学报,2006,25(2):85-89.
作者姓名:李海滨  段志信  高理富  康补晓
作者单位:内蒙古工业大学理学院,内蒙古工业大学理学院,中科院沈阳自动化研究所机器人重点实验室,内蒙古工业大学理学院 呼和浩特010051,中科院沈阳自动化研究所机器人重点实验室,沈阳110016,呼和浩特010051,沈阳110016,呼和浩特010051
摘    要:利用BP神经网络研究了六维力传感器的静态标定方法.良好的泛化能力是基于神经网络标定方法的关键,而现有基于神经网络的传感器标定方法对网络的泛化能力鲜有考虑.针对上述问题,以提高神经网络泛化能力为目的,对神经网络的训练样本、训练期望误差值和网络隐层单元数等的选取进行了研究.实验及计算机仿真表明,当选取样本数据具有遍历性时,利用神经网络标定后进行补偿计算可提高六维力传感器的测量精度.

关 键 词:六维力传感器  静态标定  神经网络  泛化能力
文章编号:1001-5167(2006)02-0085-05
收稿时间:2005-10-14
修稿时间:2005年10月14

AN APPROACH TO STATIC CALIBRATION FOR 6-DIMENSIONAL FORCE SENSOR BASED ON NEURAL NETWORK
LI Hai-bin,DUAN Zhi-xin,GAO Li-fu,KANG Bu-xiao.AN APPROACH TO STATIC CALIBRATION FOR 6-DIMENSIONAL FORCE SENSOR BASED ON NEURAL NETWORK[J].Journal of Inner Mongolia Polytechnic University(Social Sciences Edition),2006,25(2):85-89.
Authors:LI Hai-bin  DUAN Zhi-xin  GAO Li-fu  KANG Bu-xiao
Institution:1. School of Science, Inner Mongolia University of Technology, Hohhot 010051, China; 2. Robotics Laboratory of Shenyang Institute of Automation, Shenyang 110016, China
Abstract:By use of neural network,the method of static demarcation of six-dimensional force sensor has been studied.The good capability of generalization is the key to the best use of the demarcation method based on neural network.Yet it is seldom taken into consideration.Thus,in order to develop the capability of generalization,the selection of network sample,expected training error and number of units in hidden layers of network is studied.Experiments and computer simulation show that,when the selected data of sample has ergodicity,.the measuring precision of six-dimensional force sensor can be improved if compensating calculation is made after calibration by means of neural network
Keywords:six-dimensional force sensor  static calibration  neural network  generalization ability
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号