Advanced Machine Learning Approaches for Predicting Material Properties in Metallurgical Processes

• Advanced ML models (DNN, RF, SVR) outperform traditional regression in predicting material properties, with DNN achieving R² = 0.95. • Cooling rate and alloying element concentrations are the most critical factors influencing material properties. • The developed models enable real-time property prediction, facilitating process optimization and quality control. • The methodology is transferable to other materials systems and industrial applications.