ANN Assisted Prediction of Weld Bead Geometry in Gas Tungsten Arc Welding of HSLA Steels

Abstract

Weld bead geometry (front bead width and height, and back bead width and height) is a significant physical characteristic of a weldment. Several welding parameters such as welding speed, weld current, voltage, and shielding gas flow rate affect the weld bead geometry. Traditionally, an expert welder from his experience of trial and error selects a set of parameters that may yield fairly good results. However, the trial and error can be avoided, if a suitable automation tool can be developed, which could forecast the output from a set of desired parameters. Artificial neural net (ANN) was applied to predict the weld bead geometry in gas tungsten arc (GTA) welding of high strength low alloy (HSLA) steel. Back-propagation neural network algorithm has been followed to associate the welding process parameters with the weld bead geometry.