稀土
人工智能
磁铁
计算机科学
机器学习
工程类
机械工程
工作(物理)
支持向量机
材料科学
作者
Dan Liu,Yuan Li,Xinqi Zheng,Xin Ming,Ruoshui Liu,Jiazheng Hao,Yinong Yin,Jianfeng Xi,Tongyun Zhao,Fengxia Hu,Baogen Shen
标识
DOI:10.1038/s41524-026-02299-0
摘要
Rare earth permanent magnets are key functional materials for strategic emerging fields such as energy engineering and intelligent manufacturing. Misch metal (MM)‑based alloys help boost rare‑earth resource utilization, yet traditional trial‑and‑error experiments suffer from long cycles and cumbersome variable control. In this work, we established 18 model-optimization combinations by coupling six machine learning models with three hyperparameter optimization algorithms. A systematic test was conducted on datasets with different target properties, including Curie temperature T c , residual magnetization B r , saturation magnetization M s , coercivity H c and maximum energy product ( BH ) max . For T c prediction, 14 combinations achieved the coefficient of determination R 2 > 0.9. For the small-sample datasets B r and M s , 8 combinations maintained R 2 > 0.79 with satisfying generalization capacity. The optimal combination, Extreme Gradient Boosting coupled with Grey Wolf Optimizer, was further applied to predict H c and ( BH ) max of MM x Fe y B 100- x - y . The high-performance regions for H c and ( BH ) max are x = 0.14 – 0.16, y = 0.79 – 0.80 and x = 0.125 – 0.13, y = 0.79 – 0.795. Its predictions closely matched experimental data, with average errors of merely 0.317 kOe and 0.016 MGOe. These findings provide guidance on the machine learning driven material design and performance optimization for permanent magnets.
科研通智能强力驱动
Strongly Powered by AbleSci AI