Proceedings of the KWS Conference (대한용접접합학회:학술대회논문집)
- 2002.10a
- /
- Pages.301-306
- /
- 2002
THE USE OF NEURAL NETWORK TECHNOLOGIES TO DETERMINE WELDING
- Kim, Ill-Soo (Department of Mechanical Engineering, Mokpo National University) ;
- Jeong, Young-Jae (Department of Mechanical Engineering, Mokpo National University) ;
- Park, Chang-Eun (Department of Mechanical Engineering, Mokpo National University) ;
- Sung, Back-Sub (Department of Mechanical Engineering, Mokpo National University) ;
- Kim, In-Ju (Department of Mechanical Engineering, Mokpo National University) ;
- Son, Jon-Sik (Department of Mechanical Engineering, Mokpo National University) ;
- Yarlagadda, Prasad K.D.V. (School of Mech. Mfg.&Med. Engineering, Queensland Univ.)
- Published : 2002.10.01
Abstract
This paper presents the use of the neural network technology to establish a mathematical model for predicting bead geometry (top-bead width, top-bead height, back-bead width and back-bead height) for multi-pass welding, and understand relationships between process parameters and bead geometry for robotic GMA welding process. Using a series of robotic arc welding, additional multi-pass butt welds were carried out in order to verify the performance of the developed neural network model. The results show that not only the proposed model can predict the bead geometry with reasonable accuracy and guarantee the uniform weld quality, but also the neural network model could be better than the linear and curvilin ear equations developed from Lee [8].