Genetic evolutionary approach for surface roughness prediction of laser sintered Ti–6Al–4V in EDM

Additive Manufacturing (AM) methods, in the field of production, are increasing rapidly. In particular, the use of Ti alloys has an important role in AM methods. The major disadvantage of AM methods is low surface quality of the manufactured parts. Therefore, parts produced using AM methods need subsequent surface treatment. Electro Discharge Machining (EDM) is one of the nontraditional machining methods, which can be used to improve the surface quality with appropriate parameters. In this study, EDM was investigated to improve the surface quality of sintered Ti–6Al–4V alloy by using 160 different finish parameters. It was observed that Current (I) has a notable effect on surface roughness showing that best surface quality is achieved with low current values, which is under R${}_a$ = 2 µm. To estimate the final result of EDM, roughness values obtained from the experiments were modeled by using the Genetic Expression Programming (GEP), and a mathematical relationship between the obtained roughness values and EDM parameters was proposed. As a result of 830,900 iterations, GEP model created can estimate the final surface roughness of the parts with 84% accuracy.