A Neural Network Approach for GMA Butt Joint Welding

Kim Hardam Christensen, Torben Sørensen, Osama Al-Erhayem (Editor)

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review


This paper describes the application of the neural network technology for gas metal arc welding (GMAW) control. A system has been developed for modeling and online adjustment of welding parameters, appropriate to guarantee a certain degree of quality in the field of butt joint welding with full penetration, when the gap width is varying during the welding process. The process modeling to facilitate the mapping from joint geometry and reference weld quality to significant welding parameters has been based on a multi-layer feed-forward network. The Levenberg-Marquardt algorithm for non-linear least squares has been used with the back-propagation algorithm for training the network, while a Bayesian regularization technique has been successfully applied for minimizing the risk of inexpedient over-training. Finally, a predictive closed-loop control strategy based on a so-called single-neuron self-learning PSD control algorithm has been proposed.
Original languageEnglish
Title of host publicationProc. 11th Int. Conf. on Joining of Materials
Place of PublicationGilleleje, Denmark
PublisherJOM Institute for the Joining of Materials
Publication date2003
Publication statusPublished - 2003
Event11th Int. Conf. on Joining of Materials - Helsingør, Denmark
Duration: 1 Jan 2003 → …


Conference11th Int. Conf. on Joining of Materials
CityHelsingør, Denmark
Period01/01/2003 → …


Dive into the research topics of 'A Neural Network Approach for GMA Butt Joint Welding'. Together they form a unique fingerprint.

Cite this