Optimization With Artificial Intelligence Of The Machinability Of Hardox Steel, Which Is Exposed To Different Processes

This study examined the changes in properties such as microstructure, microhardness and conductivity that occur in the structure of Hardox 400 steel when exposed to different processes such as heat treatment, cold forging, plasma welding, mig-mag welding and commercial sample. The samples affected by these changes were processed in WEDM with the box-behnken experimental design. Deep Learning (DL) and Extreme Learning Machine (ELM) were used to create prediction models for Ra, Kerf, MRR and WWR. The best Ra (surface roughness) value of 1.92 µm was obtained in the heat treated sample and in the experiment with a time off of 250 µs. The best kerf value of 200 µ was obtained in the heat treated sample and in the experiment with a time off of 200 µs. The best mrr value of 200 g min-1 was obtained in the mig-mag welded sample and in the experiment.