Designing Laves-phase RFe2-type alloy with excellent magnetostrictive performance by physics-informed interpretable machine learning

作者：Pengqiang Hu, Chao Zhou, Ruisheng Zhang, Sidan Ding, Yuanjun Guo, Bo Wang, Dezhen Xue, Yizhe Ma, Zhiyong Dai, Yin Zhang, Fanghua Tian, Sen Yang · 发表于：Materials & Design · 年份：2025 · DOI：10.1016/j.matdes.2025.113799 · 被引用次数：7 · 研究领域：Magnetic Properties and Applications、Microstructure and Mechanical Properties of Steels、Non-Destructive Testing Techniques

• A physics-informed explainable ML-based strategy is used to design RFe 2 -type alloys. • A magnetostriction heatmap of Tb-Dy-Fe-V is obtained by XGB model. • Determining composition range of alloy with giant magnetostriction by ML. • Uncovering nonlinear impact of each feature on magnetostriction. Laves-phase RFe 2 -type (R = rare earth) magnetostrictive materials have tremendous application potential in smart devices. However, efficiently unearthing novel RFe 2 -type compounds with huge magnetostriction in experiments remains challenge due to the vast compositional space. Herein, we employ a physics-informed interpretable machine learning-based strategy to facilitate the design of targeted alloys. A home-built dataset is obtained through constructing composition-physical parameters-magnetostriction relationship. By comparing different models, the XGBoost (XGB) regression model is selected to predict magnetostriction of quaternary Tb x Dy 1- x Fe y V 2- y alloys. The results demonstrate that the optimal performance occurs in the composition range of 0.23–0.38 for Tb content and 0.01–0.08 for V content. The predicted properties are then verified by the measured results of a series of synthesized samples. Additionally, a model interpretability based on SHapley Additive exPlanations (SHAP) values manifests that volume magnetic susceptibility and bulk modulus exert the greatest impact on magnetostriction. This work offers a recipe to swiftly designing RFe 2 -type materials with...