Determinants of saturation magnetic flux density in Fe-based metallic glasses:insights from machine-learning models  

作　　者：Jie Xiong Bo-Wen Bai Hao-Ran Jiang Angeles Faus-Golfe 

机构地区：[1]Materials Genome Institute,Shanghai University,Shanghai 200444,China [2]Institute of Special Environments Physical Sciences,Harbin Institute of Technology,Shenzhen 518055,China [3]Laboratoire de Physique des 2 Infinis Irene Joliot-Curie(IJCLab),CNRS-IN2P3,Universite Paris-Saclay,91405 Orsay,France

出　　处：《Rare Metals》2024年第10期5256-5267,共12页稀有金属（英文版）

基　　金：financially supported by Shanghai Pujiang Program(No.23PJ1403500);GuangDong Basic and Applied Basic Research Foundation(No.2023A1515110901);Shenzhen Pengcheng Peacock Project(No.NA11409004);the National Natural Science Foundation of China(Nos.U22B2064 and 51105102);and Shanghai Rising-Star Program Yangfan Project(No.23YF1411900)。

摘　　要：Fe-based metallic glasses have garnered significant attention due to their low coercivity force and core loss.Enhancing the saturation magnetic flux density(Bs)of Fe-based metallic glasses is crucial for their industry applications.This work constructed a dataset comprising330 training data and 157 test data.The support vector regression model surpassed the tree-based ensemble models in the test set and demonstrated comparable accuracy to the tree-based ensemble models in the training set.Additionally,we proposed an indicator for Bsbased on symbolic regression.This newly proposed indicator exhibits a Pearson correlation coefficient exceeding 0.92 with Bs.The present work provides a simple and accurate formula for predicting the Bsof Fe-based amorphous alloys,demonstrating the effectiveness of machine learning approaches in discovering novel soft magnetic materials.

关 键 词：Saturation magnetic flux density Fe-based metallic glasses Machine learning Symbolic regression 

分 类 号：TG139.8[一般工业技术—材料科学与工程] TP181[金属学及工艺—合金]