Mechanical properties prediction of dual phase steels using machine learning

Abstract

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