Weld modeling and control using artificial neural networks

Journal Article · Wed Nov 01 00:00:00 EST 1995 · IEEE Transactions on Industry Applications

DOI:https://doi.org/10.1109/28.475745· OSTI ID:186878

Cook, G E; Barnett, R J; Andersen, K; Strauss, A M ^[1]

---

1. Vanderbilt Univ., Nashville, TN (United States). Engineering School

The arc welding processes play an important role in modern manufacturing. Despite the widespread use of arc welding for joining metals, controlling most welding processes still requires considerable skills and experience on behalf of the human welder. Total automation of welding has not yet been achieved, largely because the physics which determine the success of any welding task, are not yet fully understood and quantified. Artificial neural networks were evaluated for monitoring and control of the variable polarity plasma arc welding process. Three areas of welding application were investigated: weld process modeling, weld process control, and weld bead profile analysis for quality control.

• OSTI ID: 186878
• Journal Information: IEEE Transactions on Industry Applications, Vol. 31, Issue 6; Other Information: DN: Paper presented at the 1993 Industry Applications Society Annual Meeting, Toronto, Ontario (CA), October 3--8, 1993; PBD: Nov-Dec 1995
• Country of Publication: United States
• Language: English

Related Subjects

36 MATERIALS SCIENCE
METALS
PLASMA ARC WELDING
MATHEMATICAL MODELS
PROCESS CONTROL
NEURAL NETWORKS
TANKS
MANUFACTURING