A comparison between the back-propagation and counter-propagation networks in the modeling of the TIG welding process

被引：88

作者：

Juang, SC

Tarng, YS ^{[1
]}

Lii, HR

机构：

[1] Natl Taiwan Univ Sci & Technol, Dept Engn Mech, Taipei 106, Taiwan

[2] Chung Shan Inst Sci & Technol, Aeronaut Ind Dev Ctr, Aeronaut Res Lab, Taichung, Taiwan

来源：

JOURNAL OF MATERIALS PROCESSING TECHNOLOGY | 1998年 / 75卷 / 1-3期

关键词：

back-propagation; counter-propagation; neural networks; modeling; tungsten inert gas welding;

D O I：

10.1016/S0924-0136(97)00292-6

中图分类号：

T [工业技术];

学科分类号：

08 ;

摘要：

The use of neural networks to model tungsten inert gas (TIG) welding is explored in this paper. Both the back-propagation and counter-propagation networks are used to associate the welding process parameters with the features of the weld-pool geometry. A comparison between the back-propagation and counter-propagation networks in the modeling of the TIG welding process is given. It is shown that both the back-propagation and counter-propagation networks can model the TIG welding process with reasonable accuracy. However, the counter-propagation network has better learning ability for the TIC welding process than the back-propagation network, although the back-propagation network has better generalization ability fur the TIG welding process than does the counter-propagation network. (C) 1998 Elsevier Science S.A.

引用

页码：54 / 62

页数：9