Next Article in Journal
Numerical Investigation of Fracture Behavior and Current-Carrying Capability Degradation in Bi2212/Ag Composite Superconducting Wires Subjected to Mechanical Loads Using Phase Field Method
Previous Article in Journal
Aerodynamic Lift Modeling and Analysis of a Bat-like Flexible Flapping-Wing Robot
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Modelling
Volume 6
Issue 4
10.3390/modelling6040118
modelling-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

Machine Learning Approaches for Classification of Composite Materials

by
Dmytro Tymoshchuk
1,
Iryna Didych
2,*,
Pavlo Maruschak
3,*,
Oleh Yasniy
1,
Andrii Mykytyshyn
2 and
Mykola Mytnyk
2
1
Department of Artificial Intelligence Systems and Data Analysis, Ternopil Ivan Puluj National Technical University, 46001 Ternopil, Ukraine
2
Department of Computer-Integrated Technologies, Ternopil Ivan Puluj National Technical University, 46001 Ternopil, Ukraine
3
Department of Automation of Technological Processes and Production, Ternopil Ivan Puluj National Technical University, 46001 Ternopil, Ukraine
*
Authors to whom correspondence should be addressed.
Modelling 2025, 6(4), 118; https://doi.org/10.3390/modelling6040118
Submission received: 9 August 2025 / Revised: 4 September 2025 / Accepted: 29 September 2025 / Published: 1 October 2025
(This article belongs to the Special Issue Machine Learning and Artificial Intelligence in Modelling)
Versions Notes

Abstract

The paper presents a comparative analysis of various machine learning algorithms for the classification of epoxy composites reinforced with basalt fiber and modified with inorganic fillers. The classification is based on key thermophysical characteristics, in particular, the mass fraction of the filler, temperature, and thermal conductivity coefficient. A dataset of 16,056 interpolated samples was used to train and evaluate more than a dozen models. Among the tested algorithms, the MLP neural network model showed the highest accuracy of 99.7% and balanced classification metrics F1-measure and G-Mean. Ensemble methods, including XGBoost, CatBoost, ExtraTrees, and HistGradientBoosting, also showed high classification accuracy. To interpret the results of the MLP model, SHAP analysis was applied, which confirmed the predominant influence of the mass fraction of the filler on decision-making for all classes. The results of the study confirm the high effectiveness of machine learning methods for recognizing filler type in composite materials, as well as the potential of interpretable AI in materials science tasks.
Keywords: epoxy compositions; artificial intelligence; machine learning; neural networks; MLP; naive Bayes classifiers; linear classifiers; gradient boosting; SVM; kNN epoxy compositions; artificial intelligence; machine learning; neural networks; MLP; naive Bayes classifiers; linear classifiers; gradient boosting; SVM; kNN

Share and Cite

MDPI and ACS Style

Tymoshchuk, D.; Didych, I.; Maruschak, P.; Yasniy, O.; Mykytyshyn, A.; Mytnyk, M. Machine Learning Approaches for Classification of Composite Materials. Modelling 2025, 6, 118. https://doi.org/10.3390/modelling6040118

AMA Style

Tymoshchuk D, Didych I, Maruschak P, Yasniy O, Mykytyshyn A, Mytnyk M. Machine Learning Approaches for Classification of Composite Materials. Modelling. 2025; 6(4):118. https://doi.org/10.3390/modelling6040118

Chicago/Turabian Style

Tymoshchuk, Dmytro, Iryna Didych, Pavlo Maruschak, Oleh Yasniy, Andrii Mykytyshyn, and Mykola Mytnyk. 2025. "Machine Learning Approaches for Classification of Composite Materials" Modelling 6, no. 4: 118. https://doi.org/10.3390/modelling6040118

APA Style

Tymoshchuk, D., Didych, I., Maruschak, P., Yasniy, O., Mykytyshyn, A., & Mytnyk, M. (2025). Machine Learning Approaches for Classification of Composite Materials. Modelling, 6(4), 118. https://doi.org/10.3390/modelling6040118

Article Metrics

Back to TopTop