材料科学
纳米晶材料
非晶态金属
合金
冶金
无定形固体
纳米技术
结晶学
化学
作者
Shengdong Tang,Rui Sun,Yifan He,Guichang Liu,Ruixuan Wang,Yuqin Liu,Chengying Tang
标识
DOI:10.1016/j.matdes.2024.113461
摘要
• Four ML models were proposed to predict the magnetic properties of Fe-based alloys. • XGBT model showed best predictive and generalization ability for predicting B s , H c . • An Fe 85 Si 2 B 8.5 P 3.5 C 1 alloy with high B s and low H c was designed and prepared. • The predicted results by XGBT are in very good agreement with measured ones. Four machine learning (ML) models including eXtreme Gradient boosting (XGBT), k -Nearest Neighbor ( k NN), 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 (R 2 ) of 0.992 and 0.967, respectively. Based on the feature importance analysis from the XGBT model, the Fe 85 Si 2 B 8.5 P 3.5 C 1 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 Fe 85 Si 2 B 8.5 P 3.5 C 1 alloy. It was found that the Fe 85 Si 2 B 8.5 P 3.5 C 1 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.
科研通智能强力驱动
Strongly Powered by AbleSci AI