Prediction of weld porosity (pit) in gas metal arc welds

Abstract

Recently, in the automobile industry, the use of zinc-plated high-strength steels has been increasing to lighten vehicles and improve safety. In this scenario, gas metal arc welding (GMAW) processes are applied to automobile bodies and chassis parts. However, porosity defects occur in the welds because of the zinc vapor formed in the zinc coating layer during the GMAW process. This causes a decrease in the strength of the welded portion. These porosity defects have internal porosity and external pits, but in the actual production line, the quality of the welds is assessed by the occurrence of defects in external pits. In this study, using arc voltage and a system based on the waveform of the welding current, feature variables were extracted to characterize the sizes of external pits formed in high tensile strength galvanized steel during the GMAW process. Subsequently, a size prediction model was applied to predict the sizes of the external defects in the pits, and the results were verified using a multiple linear regression model and an artificial neural network.