Machine learning assisted design and preparation of Fe85Si2B8.5P3.5C1 amorphous/nanocrystalline alloy with high Bs and low Hc

Abstract

Four machine learning (ML) models including eXtreme Gradient boosting (XGBT), k-Nearest Neighbor (kNN), Gradient Boosting Decision Tree (GBDT) and Artificial Neural Network (ANN) were employed to predict saturation flux density (B_s), coercivity (H_c), grain size, magnetostriction (λ), and Curie temperature (T_c) of Fe-based amorphous/nanocrystalline alloys. To maximize predictive ability of ML models, grid-search and normalization were used to search the most proper parameters of ML and pre-process raw data, respectively. XGBT had best predictive and generalization ability for predicting B_s and H_c with coefficient of determination (R²) of 0.992 and 0.967, respectively. Based on the feature importance analysis from the XGBT model, the Fe₈₅Si₂B_8.5P_3.5C₁ amorphous alloy ribbon with good magnetic properties, such as high B_s, low H_c, was designed and prepared by melt spinning. X-ray diffraction (XRD), differential scanning calorimetry (DSC), transmission electron microscopy (TEM), vibrating sample magnetometer (VSM), B–H loop tracer, and magnetostriction instrument were used to identify the phase structure and physical properties of the Fe₈₅Si₂B_8.5P_3.5C₁ alloy. It was found that the Fe₈₅Si₂B_8.5P_3.5C₁ alloy had good magnetic properties with B_s of 1.82 T and the H_c of 2.02 A/m after annealing at 723 K for 180 s, in good agreement with the designed results by machine learning.