Prediction of Ms temperature based on alloying composition parameter assisted by machine learning

Abstract

The martensite start temperature (Ms) of steel plays an important guiding role in the formulation of heat treatment process. Because steel contains many alloying elements, it is very challenging to predict Ms from alloying elements. The rapid development of data-driven technology makes it convenient to accurately predict Ms. In this work, an Ms dataset of 1313 entries was collected and evaluated. By comparison, XGBoost algorithm is chosen to build a machine learning (ML) model for predicting the Ms of steel. The effects of atomic and thermal characterization on the performance of predictive models trained using machine learning algorithms are investigated. Pearson correlation coefficient and feature importance reveal the linear and nonlinear correlation of elements in the matrix. The model showed a good accuracy between predicted and actual values, and the R² on the test set is 0.94. Finally, R² of XGBoost model and JMatPro software on unknown data are 0.91 and 0.88 respectively. Successful validation shows that the model can accurately predict the Ms of various types of steel. These results indicate the potential of the model in the formulation of auxiliary heat treatment processes.