Modelling gas metal arc weld geometry using artificial neural network technology

A backpropagation network system for predicting gas metal are (GMA) bead-on-plate weld geometry from current, voltage and wire travel speed is reported in this study. Moreover, workpiece thickness is a variable that is taken into consideration because its effect on weld shape is to this point unknown in practice. The database consists of some ninety six welds (cross-sectional weld shapes and corresponding welding parameters). DCEP polarity, C-25 shielding and electrode diameter and extension of 0.9 and 19 mm respectively are assumed fixed for this study-consistent with the experimental database used to train and test the technology. For the purposes of this investigation, weld bead size and shape are defined by bead width, bead height, penetration and a new parameter, bay length at 22.5 degrees, introduced to model the underbead recession that occurs in deeper penetration welds. For pictorial representation, the upper bead is modelled by fitting a parabola to the bead width and reinforcement height while a combination of parabolas is suggested for the bead shape below the plate surface given the width, penetration and bay length. Deposit and plate fusion areas are also included. Finally, the reverse problem-predicting the welding parameters (current, voltage and travel speed) to achieve a given weld shape-is discussed in terms of the study. (C) 1999 Canadian Institute of Mining and Metallurgy. Published by Elsevier Science Ltd. All rights reserved.