Weld modeling and control using artificial neural networks
- 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, Journal Name: IEEE Transactions on Industry Applications Journal Issue: 6 Vol. 31; ISSN ITIACR; ISSN 0093-9994
- Country of Publication:
- United States
- Language:
- English
Similar Records
The use of an advanced design of power supply control system for wet shielded metal arc welding
AUTOMATED DEFECT CLASSIFICATION USING AN ARTIFICIAL NEURAL NETWORK