Machine Learning Steel Ms Temperature. (June 2021)

• Record Type: Journal Article
• Authors: Zhang, Yun; Xu, Xiaojie
• Is Part Of: Simulation. Volume 97:Number 6(2021)
• Page Start: 383
• Page End: 425
• Publication Date: 2021-06
• Subjects: Martensite -- Steel -- Gaussian process regression -- machine learning -- phase transformation; Computer simulation -- Periodicals; 003.3
• DOI: 10.1177/0037549721995574
• Languages: English
• ISSNs: 0037-5497

Abstract

Empirical equations, thermodynamics frameworks, and neural network modeling have been developed to predict steel martensite start temperature, M s, but they might not tend to generalize well when composition includes a wide range of alloying elements. In this study, we develop the Gaussian process regression (GPR) model to shed light on the relationship between alloying elements andM s temperature for steels. A total of 1119 steels withM s ranging from 153 K to 938 K are examined. The model has a high degree of accuracy and stability, contributing to fast low-costM s temperature estimations.