UDC 004.724
APPLICATION OF CLASSTERIZATION METHODS TO ANALYZE THE PROPERTIES OF MATERIALS
V. P. Koryachko, Dr. Sc. (Tech.), full professor, CAD department, Head of the Department, RSREU, Ryazan, Russia;
orcid.org/0000-0003-0272-673X, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
S. D. Vikulin, post-graduate student, RSREU, Ryazan, Russia;
orcid.org/0009-0002-9932-1113, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
A. V. Volkov, key project engineer, Huawei Technologies Co., Moscow, Russia;
orcid.org/0009-0008-1162-3816, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
The problem of developing cluster analysis methods to study basic characteristics of materials for the purpose of further development and implementation of intelligent search system in the field of materials science is considered. The aim of this work is to develop cluster analysis methods to study the basic characteristics of materials for further development and implementation of intelligent search system in the field of materials science. Clustering is carried out using the k-means algorithm, and validation of the results is carried out using intra-cluster and inter-cluster analysis. The determination of optimal initial parameters of cluster analysis method was carried out using elbow and silhouette methods. A collection of materials was successfully decomposed into clusters, and data hierarchical structure was visualized using a dendrogram, which confirmed the effectiveness of the method proposed.
Key words: : machine learning, cluster analysis, material science, k-means, elbow method, silhouette method, dendrogram.