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

Abstract

A machine learning (ML) method aided by domain knowledge was proposed to predict saturated magnetization (Bs) and critical diameter (Dmax) of soft magnetic metallic glass (MGs). Two datasets were established based on published experimental works about soft magnetic MGs. A general feature space was proposed and proved to be adaptive for ML model training for different prediction tasks. It was found that the predictive performance of ML models was better than traditional physical knowledge-based estimation methods. In addition, domain knowledge aided feature selection can greatly reduce the number of features without significantly reducing the prediction accuracy. Finally, binary classification of the critical size of soft magnetic metallic glass was studied.