Welding Gap Detecting and Monitoring using Neural Networks

Generally, welding gap is a serious factor of a falling-off in weld quality among various kind of weld defect. Welding gap is created between two work piece in GMAW(Gas Metal Arc Welding) of horizontal fillet weld because surface of workpiece is not flat by cutting process. In these days, there were many attempts to detect welding gap. though we prevalently use the vision sensor or arc sensor in welding process, it is difficult to detect welding gap for improvement of welding quality. But we have a trouble to find relationship between welding gap and many welding parameters due to non-linearity of welding process. As mentioned about the various difficult problem, we can detect welding gap precisely using neural networks which are able to model non-linear function. Also, this paper was proposed real-time monitoring of weld bead shape to find effect of welding gap and to estimate weld quality. Monitoring of weld bead shape examined the correlation of welding parameters with bead eometry using learning ability of neural networks. Finally, the developed system, welding gap detecting system and bead shape monitoring system, is expected to the successful capability of automation of welding process by result of simulation.