Data-driven metallurgical design for high strength low alloy (HSLA) steel

This thesis presents a data-driven approach to the design of high strength low alloy (HSLA) steel, focusing on metallurgical properties and modeling techniques. The objective is to enhance HSLA steel's performance by employing advanced data mining and modeling strategies. A comprehensive methodology is developed, incorporating linear regression models, artificial neural networks, and recursive partitioning techniques to evaluate various properties of HSLA steel. The results indicate significant improvements in yield strength and overall material performance through the application of these methods. This study contributes to the field of materials science by demonstrating the potential of data-driven approaches in optimizing steel design, thereby providing valuable insights for future research and industrial applications.