UDC 004.724
COMPARATIVE STUDY OF MACHINE LEARNING METHODS AND NEURAL NETWORKS FOR PREDICTING CHEMICAL COMPOSITION OF MATERIALS
V. P. Koryachko, Dr. Sc. (Tech.), full professor, Head of the Department, RSREU, Ryazan, Russia; orcid.org/0000-0000-0000-000X, 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, specialist, BMSTU, 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 methods for predicting the chemical composition of materials based on their physical properties using machine learning approaches is considered. The aim of this work is to study the relationships between physical and chemical properties of materials to develop an intelligent system in order to support new materials design. Machine learning algorithms such as linear regression, decision trees, and neural networks to predict the chemical composition of different materials were employed. The study high lights the effectiveness of the proposed methods for accurately predicting the chemical composition, which can optimize material development process and improve material properties.
Key words: : machine learning, multi-class regression, chemical composition, physical properties of ma terials, neural networks, linear regression, decision trees, material science.