首页 | 本学科首页   官方微博 | 高级检索  
     

焊接电弧光谱信息模式识别软件的开发
引用本文:云绍辉,张德勤,韩国明.焊接电弧光谱信息模式识别软件的开发[J].焊接学报,2006,27(9):21-24.
作者姓名:云绍辉  张德勤  韩国明
作者单位:1. 天津大学,系统工程研究所,天津,300072;九江学院,材料科学与工程学院,江西,九江,332005
2. 九江学院,材料科学与工程学院,江西,九江,332005
3. 天津大学,材料科学与工程学院,天津,300072
摘    要:采用模式识别方法,用Visual Basic开发了一套熔滴过渡光谱信号模式识别软件系统.根据熔滴过渡与光谱信号的对应关系,以及光谱信号波形的几何特征,抽取了多个关键性的特征参数.基于统计模式识别的Bayes决策理论,建立了相应的识别函数和最小距离法分类器.判别结果表明,利用该系统能够较好地对MIG,MAG和CO2焊熔滴过渡类型进行自动识别,为实现熔化极气体保护焊熔滴过渡自动控制奠定了基础.

关 键 词:熔滴过渡  光谱信号  Bayes决策  模式识别
文章编号:0253-360X(2006)09-021-04
收稿时间:10 17 2005 12:00AM
修稿时间:2005-10-17

Pattern recognition of spectrum information of metal transfer
YUN Shao-hui,ZHANG De-qin and HAN Guo-ming.Pattern recognition of spectrum information of metal transfer[J].Transactions of The China Welding Institution,2006,27(9):21-24.
Authors:YUN Shao-hui  ZHANG De-qin and HAN Guo-ming
Affiliation:Institute of Systems Engineering, Tianjin University, Tianjin 300072, China;Department of Materials Science and Engineering, Jiujiang University, Jiujiang 332005, Jiangxi, China,Department of Materials Science and Engineering, Jiujiang University, Jiujiang 332005, Jiangxi, China and School of Materials Science and Engineering, Tianjin University, Tianjin 300072, China
Abstract:A software system for pattern recognition of spectrum signal of metal transfer mode was developed using Visual Basic.Based on consistency of the spectrum and metal transfer and geometrical pattern features of the spectrum,several key characteristic parameters were extracted.Correspondent recognition function and a minimum-distance classifier were constructed based on Bayes decision theory.The results show that using this system,pattern recognition of metal transfer mode for metal inert-gas welding,metal active-gas welding,and CO_2 welding can be done automatically.This provides a basis for automatic control of metal transfer in metal gas arc welding.
Keywords:metal transfer  spectrum signal  Bayes decision  pattern recognition  
本文献已被 CNKI 维普 万方数据 等数据库收录!
点击此处可从《焊接学报》浏览原始摘要信息
点击此处可从《焊接学报》下载全文
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