Abstract:
A method for automatic detection of burning through of short
circuit CO2 arc welding is presented. It is based on the
extraction of arc signal features as well as classification of
the obtained features using self-organize feature map (SOM)
neural networks in order to get the weld quality information,
for example, to determine if there is defect in the product.
This is important for the on-line monitoring of weld quality
especially in robotic welding and lay the foundation for the
further real-time control of weld quality.
Key words: Weld Quality D efect SOM Neural networks CO2 arc welding
*
This project
is supported by National Natural Science Foundation of Guangdong (No.990550).
Manuscript received on December 15, 1999; revised manuscript March
15, 2000 |