Analysis of Prediction Mechanisms and Feature Importance of Martensite Start Temperature of Alloy Steel via Explainable Artificial Intelligence

Abstract

This study proposes a machine learning model to predict the martensite start temperature (M_s) of alloy steels. We collected 219 usable data from the literature, and adjusted the hyperparameters to propose an accurate machine learning model. Artificial neural networks (ANN) exhibited the best performance compared with existing empirical equation. The prediction mechanisms and feature importance of the ANN with regards to the whole system were discussed via the Shapley additive explanation (SHAP).