基于领域知识辅助的机器学习方法对软磁金属玻璃性能的预测  

Domain knowledge aided machine learning method for properties prediction of soft magnetic metallic glasses

作　　者：李鑫 单光存 赵鸿滨[3] 石燦鴻 Xin LI;Guang-cun SHAN;Hong-bin ZHAO;Chan Hung SHEK(School of Instrumentation Science and Opto-electronics Engineering,Beihang University,Beijing 100191,China;Department of Materials Science and Engineering,City University of Hong Kong,Kowloon Tong,Hong Kong SAR,China;State Key Laboratory of Advanced Materials for Smart Sensing,GRINM Group Co.,Ltd.,Beijing 100088,China)

机构地区：[1]北京航空航天大学仪器科学与光电工程学院,北京100191 [2]香港城市大学材料科学与工程系,香港特别行政区 [3]有研科技集团有限公司智能传感功能材料国家重点实验室,北京100088

出　　处：《Transactions of Nonferrous Metals Society of China》2023年第1期209-219,共11页中国有色金属学报（英文版）

基　　金：financially supported by the National Key R&D Program of China(No.022YFB4703400);the Fundamental Research Funds for the Central Universities,China。

摘　　要：提出一种领域知识辅助的机器学习方法,实现对软磁金属玻璃饱和磁化强度(B_(s))和临界尺寸(D_(max))的预测。基于公开的实验数据,建立软磁合金数据库。提出一个通用的特征空间,适用于面向不同预测任务的机器学习模型训练。结果表明,机器学习模型的预测能力比基于物理知识的估计方法精度更高。此外,领域知识辅助的特征选择可在有效减少特征数量的同时,不显著降低模型的预测精度。最后,对软磁金属玻璃临界尺寸的二分类预测进行讨论。A machine learning(ML)method aided by domain knowledge was proposed to predict saturated magnetization(B_(s))and critical diameter(D_(max))of soft magnetic metallic glasses(MGs).Two datasets were established based on published experimental works about soft magnetic MGs.A general feature space was proposed and proven to be adaptive for ML model training for different prediction tasks.It was demonstrated that the predictive performance of ML models was better than that of traditional knowledge-based estimation methods.In addition,domain knowledge aided feature design can greatly reduce the number of features without significantly reducing the prediction accuracy.Finally,the binary classification of Dmaxof soft magnetic MGs was studied.

关 键 词：金属玻璃 软磁性 玻璃形成能力 机器学习 材料描述符 

分 类 号：TB331[一般工业技术—材料科学与工程]