Neural network approach to weld quality monitoring

Supervision of welding processes is one of the most important and complicated tasks in production lines. Artificial neural networks have been applied for modeling and physical control processes. In this paper, the authors propose the use of a neural network classifier for online non-destructive testing. This system has been developed and installed in a welding station of General Motors in Cadiz (Spain). Results confirm the validity of this novel approach.<<ETX>>