Abstract
During the process of deep drawing of cylindrical thin-walled products from aluminum sheets, the occurrence of product defects in the form of breaking the material continuity is observed. This has a very large impact on the efficiency of production lines and the number of generated scraps. The number of defects depends on many factors, including the material and the process properties. Because the problem appears after changing one material to another, while the process parameters do not change, it was assumed that the material has the main influence on the number of defects. To reduce the number of defects, a tool is needed to predict threats to the process. Decision tree models were used for this purpose. Using the tree interaction algorithms, the influence of the chemical composition and strength parameters of the 3xxx series aluminum alloy on the number of generated defects was investigated. Increased Silicon (Si) and Iron (Fe) values generated a higher number of defects. Increased yield strength (YS) and decreased elongation (E) also generated a higher number of defects. Based on the results, a defect prediction tool was created, where after entering the parameters of the material, it is possible to predict production hazards.