| ACQUIRING AND PATTERN RECOGNITION OF SPECTRUM INFORMATION OF WELDING METAL TRANSFER |
| |
| 作者姓名： | Han Guoming
He Yu
Yun Shaohui
Li Junyue
School of Materials Sdence
and Engineering Tianjin University Tranjin China |
| |
| 作者单位： | Han Guoming
He Yu
Yun Shaohui
Li Junyue
School of Materials Sdence
and Engineering，Tianjin University，Tranjin 300072，China |
| |
| 基金项目： | This project is supported by National Natural Science Foundation of China (No.59990470). |
| |
| 摘 要： | In order to recognize various metal transfer modes, by the creation of a pattern recognition system for metal transfer mode, five kinds of spectrum signal in gas metal arc welding (MIG, MAG and CO2) are collected and taken as training samples. These samples are pretreated by computer. Several key characteristic parameters of the spectrum signal are creatively extracted, and a corresponding recognition function and a minimum-distance-classifier are constructed. The results show that using this method, the pattern recognition of several kinds of metal transfer mode for the metal gas arc welding can be done successfully. It has good accuracy and recognition precision, basis for controlling the metal gas arc welding metal transfer automatically, and relative important parameters in welding process, such as the frequency of droplet transfer and the approximate diameter of each droplet, can also be obtained.
|
ACQUIRING AND PATTERN RECOGNITION OF SPECTRUM INFORMATION OF WELDING METAL TRANSFER |
| |
| Han Guoming
He Yu
Yun Shaohui
Li Junyue
School of Materials Sdence
and Engineering,Tianjin University,Tranjin ,China.ACQUIRING AND PATTERN RECOGNITION OF SPECTRUM INFORMATION OF WELDING METAL TRANSFER[J].Chinese Journal of Mechanical Engineering,2004,17(3):319-322. |
| |
| Authors: | HanGuoming HeYu YunShaohui LiJunyue |
| |
| Affiliation: | SchoolofMaterialsScienceandEngineering,TianjinUniversity,Tianjin300072,China |
| |
| Abstract: | In order to recognize various metal transfer modes, by the creation of a pattern recognition system for metal transfer mode, five kinds of spectrum signal in gas metal arc welding (MIG, MAG and CO2) are collected and taken as training samples. These samples are pretreated by computer. Several key characteristic parameters of the spectrum signal are creatively extracted, and a corresponding recognition function and a minimum-distance-classifier are constructed. The results show that using this method, the pattern recognition of several kinds of metal transfer mode for the metal gas arc welding can be done successfully. It has good accuracy and recognition precision, basis for controlling the metal gas arc welding metal transfer automatically, and relative important parameters in welding process, such as the frequency of droplet transfer and the approximate diameter of each droplet, can also be obtained. |
| |
| Keywords: | Gas metal arc welding Metal transfer Spectrum Acquiring Pattern recognition |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
