A Study on the Cluster-wise Regression Model for Bead Width in the Automatic GMA Welding

Abstract

The automatic welding system is presently made use of high volume production industries even if the cost of the related equipment is justified by the large number of pieces to be made. Also, the detailed devices with the predetermined sequences of welding parameters and the use of timers to form the weld joints were required. A new mathematical model that predicts the optimal welding parameters on a given bead geometry and accomplishes the desired mechanical properties of the weldment to make the automatic GMA(Gas Metal Arc) welding process should be needed. Therefore, the purpose of this study is to investigate the effect on the bead width of mild steel welded by the GMA welding method through a full factorial design. A cluster-wise regression analysis model that derives the optimal bead width according to welding voltage, arc current, welding speed, welding angle, and Contact Tip-to-Work Distance(CTWD) has been developed. Not only the fitting of these models have been checked and compared by using a variance test, but also the developed regression models have been carried out based on the additional experiments.