Sm-Co ALLOYS COERCIVITY PREDICTION USING STACKING HETEROGENEOUS ENSEMBLE MODEL

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.

Investigation of the phase transformation characteristics of Fe-Co elastrocalaric refrigeration alloy

Mechanical alloying (AM) and powder metallurgy(PM) have been widely used in many fields especially in the development of new alloy materials due to the advantages of simple process, high material utilization rate and accurate material ratio. In this investigation, experimental procedures were proposed to explore the phase transformation characteristics, elastrocalaric refrigeration effect of Fe-Co alloys synthesized by AM and PM. The samples of Fe-Co elastrocalaric refrigeration alloy with different phase transformation temperatures and different enthalpy changes have been successfully prepared by changing the initial ratio of Co element. The results show that the phase transformation characteristics have changed with the increase of Co content and showed different changing trends.

Formability and Magnetic Properties of the Binary Nd-Co Amorphous Alloys

In this paper, binary Nd-Co alloys with compositional range from Nd72.5Co27.5 to Nd50Co50 were successfully vitrified into glassy state by a melt-spinning method. The glass formability of the metallic glasses (MGs) was studied and the best glass former in the binary Nd-Co alloys was obtained. Magnetic properties of the MGs were measured. The compositional dependence of Curie temperature of the MGs was observed. The mechanism for the spin-glass-like behaviors and high coercivity at low temperature, and their influence on the magnetic entropy change of the MGs, were investigated.

Catalytic Decomposition of Methane to Hydrogen over Al2O3 Supported Mono- and Bimetallic Catalysts

This article discusses the decomposition of methane in the temperature range 550–800 °C on low-percentage monometallic (Ni/g-Al2O3, Co/g-Al2O3) and bimetallic (Ni-Co/g-Al2O3) catalysts. It is shown that the bimetallic catalyst is more active in the decomposition of methane to hydrogen than monometallic ones. At a reaction temperature of 600 °C, the highest methane conversion is 81%, and the highest hydrogen yield of 51% is formed on Ni-Co/g-Al2O3. A complex of physicochemical methods (Scanning Electron Microscope (SEM), X-ray Diffraction (XRD), Temperature Programmed Reduction (TPR-H2), etc.) established that the addition of cobalt oxide to the composition of Ni/g-Al2O3 leads to the formation of surface bimetallic Ni-Co alloys, while the dispersion of particles increases and the reducibility of the catalyst is facilitated, which provides an increase in the concentration of metal particles - active centers, which can be the reason for an increase in the catalytic properties of a bimetallic catalyst in comparison with monometallic ones. Copyright © 2021 by Authors, Published by BCREC Group. This is an open access article under the CC BY-SA License (https://creativecommons.org/licenses/by-sa/4.0).