Open AccessSm-Co ALLOYS COERCIVITY PREDICTION USING STACKING HETEROGENEOUS ENSEMBLE MODEL
Author(s) -
А.М. Trostianchyn,
Zoia Duriagina,
Ivan Izonin,
Roman Tkachenko,
V. V. Kulyk,
Olena Pavliuk
Publication year - 2021
Publication title -
acta metallurgica slovaca
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.277
H-Index - 13
eISSN - 1338-1156
pISSN - 1335-1532
DOI - 10.36547/ams.27.4.1173
Subject(s) - coercivity , adaboost , stacking , boosting (machine learning) , random forest , ensemble learning , machine learning , gradient boosting , artificial intelligence , computer science , materials science , magnet , microstructure , algorithm , condensed matter physics , metallurgy , physics , nuclear magnetic resonance , engineering , mechanical engineering , support vector machine
The use of machine learning tools in modern materials science can significantly reduce the duration and cost of developing new materials and improving the properties of existing ones. This is especially true in studying expensive and strategic importance materials like alloys of rare earth metals, which are used to manufacture high-energy permanent magnets. At the same time, single machine learning algorithms do not always provide the accuracy required to solve a particular applied task. Therefore, the current paper aimed to develop an ensemble model for predicting the magnetic properties of Sm-Co system alloys with high accuracy. Based on literature data, we have collected the dataset of the relationship between phase composition, sample state, crystallographic orientation, microstructure, and magnetic properties. We have compared different machine learning algorithms. A stacking ensemble model was designed based on high-precision machine learning algorithms: Neural Networks, AdaBoost, Gradient Boosting, and Random Forest algorithm. The proposed ensemble scheme showed a significant increase in the accuracy for predicting the magnetic properties of Sm-Co alloys on the example of coercivity.