Data-driven glass-forming ability for Fe-based amorphous alloys

被引：1

作者：

Wu, Yi-Cheng ^{[1
]}

Yan, Lei ^{[1
]}

Liu, Jin-Feng ^{[1
]}

Qiu, Hai ^{[1
]}

Deng, Bo ^{[1
]}

Wang, Dong-Peng ^{[3
]}

Shi, Rong-Hao ^{[4
]}

Chen, Yong ^{[5
]}

Guan, Peng-Fei ^{[2
]}

机构：

[1] Jiangsu Univ Sci & Technol, Sch Mech Engn, Zhenjiang 212100, Peoples R China

[2] Beijing Computat Sci Res Ctr, Beijing 100193, Peoples R China

[3] Jiangsu Univ Sci & Technol, Sch Mat Sci & Engn, Zhenjiang 212100, Jiangsu, Peoples R China

[4] Henan Acad Sci, Inst Mat, Zhengzhou 450046, Peoples R China

[5] Yancheng Inst Technol, Sch Automot Engn, Yancheng 224051, Peoples R China

来源：

MATERIALS TODAY COMMUNICATIONS | 2024年 / 40卷

基金：

中国国家自然科学基金;

关键词：

Amorphous alloys; Glass forming ability; Machine learning; Data augmentation; Model interpretation; METALLIC GLASSES; PREDICTION;

D O I：

10.1016/j.mtcomm.2024.109440

中图分类号：

T [工业技术];

学科分类号：

08 ;

摘要：

Fe-based amorphous alloys have garnered significant academic interest due to their distinctive properties and promising application prospects. However, their limited glass forming ability (GFA) presents a significant challenge in engineering applications. This study utilizes three machine learning techniques, namely artificial neural networks (ANN), Random Forest (RF), and eXtreme Gradient Boosting (XGB) to predict the maximum amorphous diameter (Dmax) of Fe-based amorphous alloys based solely on chemical composition. Three oversampling techniques were implemented to tackle the uneven distribution in the original dataset, significantly enhancing model performance. Additionally, Shapley Additive Explanation (SHAP) was employed to interpret the constructed models, revealing pertinent rules regarding GFA. The applied techniques and revealed rules contribute to a statistical comprehension of GFA, potentially aiding in the discovery of novel Fe-based amorphous alloys.

引用

页数：7