Welding quality analysis based on defect class using design of experiment method

In the manufacture industry, welding is one of important role in the field of metal engineering and repair. Welding has played a significant role in man’s ability to create and build since the Bronze Age. It remains a critical aspect of metal fabrication and manufacturing. In this experiment, Design of Experiment (DOE) technique, overall evaluation criteria (OEC), and ANOVA used to analyse the results. The aim of this study is to determine the best welding quality using DOE method and ANOVA analysis. Control and noise factors used to conduct the experiment. The specification of weld defect used such as crack, slag, holes, welding line, porous, over spatter, and pin hole. The result shows that sample no 7 is the best quality with average value is 0.22. The control factor that significantly influence the quality are plate thickness, amperage, electrode, and welding method.