Mechanical properties prediction of dual phase steels using machine learning

The use of artificial intelligence techniques, with the increase data generation capacity and advancement computational resources, has enabled industries to develop improve products without compromising laboratory industrial resources. In this paper, a supervised machine learning (ML) based technique was used predict yield strength (YS), ultimate tensile (UTS), elongation (EL) dual phase steels minimum strengths 590 780 MPa. analysis done from information containing chemical composition thermomechanical processing parameters referred materials. proposed ML model reached values coefficient determination above 0.94, an accuracy ±30 MPa for YS UTS, ±3% EL. These results demonstrated rationality reliability tested method, allowing its application in future research works decision making that aim optimize parameters.