Physics-Informed Machine Learning for Steel Development: A Computational Framework and CCT Diagram Modelling
This work addresses the problem of accurately predicting steel microstructure and properties for materials scientists and engineers, representing an incremental advance by combining physical insights with existing ML methods.
The paper tackles the challenge of applying machine learning to complex industrial materials like steel by introducing a physics-informed computational framework for modeling continuous cooling transformation (CCT) diagrams, achieving high computational efficiency (generating diagrams in under 5 seconds) and strong generalizability with F1 scores above 88% for phase classification and MAEs below 20°C for most phase transition temperatures.
Machine learning (ML) has emerged as a powerful tool for accelerating the computational design and production of materials. In materials science, ML has primarily supported large-scale discovery of novel compounds using first-principles data and digital twin applications for optimizing manufacturing processes. However, applying general-purpose ML frameworks to complex industrial materials such as steel remains a challenge. A key obstacle is accurately capturing the intricate relationship between chemical composition, processing parameters, and the resulting microstructure and properties. To address this, we introduce a computational framework that combines physical insights with ML to develop a physics-informed continuous cooling transformation (CCT) model for steels. Our model, trained on a dataset of 4,100 diagrams, is validated against literature and experimental data. It demonstrates high computational efficiency, generating complete CCT diagrams with 100 cooling curves in under 5 seconds. It also shows strong generalizability across alloy steels, achieving phase classification F1 scores above 88% for all phases. For phase transition temperature regression, it attains mean absolute errors (MAE) below 20 °C across all phases except bainite, which shows a slightly higher MAE of 27 °C. This framework can be extended with additional generic and customized ML models to establish a universal digital twin platform for heat treatment. Integration with complementary simulation tools and targeted experiments will further support accelerated materials design workflows.