用神经网络方法探测机床运动误差通用建模方法  

A Study is Kinematic Error Model of NC Machine Center with Neural Network Method

作　　者：邬再新[1] 周伦才[1] 刘涛[1] 李娜[1] 李艳红[1] 

机构地区：[1]兰州理工大学机电学院,兰州730050

出　　处：《组合机床与自动化加工技术》2007年第12期23-25,共3页Modular Machine Tool & Automatic Manufacturing Technique

摘　　要：文章在分析了机床运动误差源的基础上,以典型误差源为对象,提出了基于人工神经网络技术的机床运动误差的通用建模方法,总结了基于神经网络方法的建模过程及建模方法;在此基础上建立了机床运动误差模型,通过对该模型的性能分析,用此通用方法建立的机床运动误差模型能达到精度要求,具有很好的通用性和预测性;同时该模型可以用于机床运动误差的智能补偿技术。This paper propose a universal modeling method based on neural network of the kinematic error of NC machine through analyzing the representative kinematic error source of the machine tools. The summary of modeling procedure and method is presented, Kinematic error model（KEM） of NC tools is established on this basis. The model has strong universality and prediction, The model meets accuracy demand of kinematic machine tools, The model can be used in intelligent error compensation technology.

关 键 词：运动误差 神经网络 误差模型 

分 类 号：TH161[机械工程—机械制造及自动化]