10.14489/td.2025.04.pp.062-068

2025, 04 April

DOI: 10.14489/td.2025.04.pp.062-068

Gushina E. A.
STUDY OF THE POSSIBILITY OF APPLYING CLUSTER ANALYSIS FOR PREDICTING THE PROPERTIES OF POLYMER COMPOSITE MATERIALS
(pp. 62-68)

Abstract. This paper presents a study of the application of cluster analysis for predicting the properties of polymer composite materials. Clustering methods are considered, which allow efficient grouping of a variety of polymer composites based on specific properties such as mechanical strength, thermal conductivity, electrical conductivity and others. The use of cluster analysis opens up opportunities to reveal hidden patterns and relationships between the components of composites, which in turn helps to optimize their compositions and significantly improve their performance characteristics. The study utilized linear regression method to predict the properties of composite materials based on their composition and process parameters. The results obtained highlight the high efficiency of cluster analysis as an important tool for optimizing the composition of polymer composites and improving their performance characteristics, which may have potential applications in various branches of industry and science.

Keywords: cluster algorithms, cluster analysis, database structure, polymer composite materials, prediction of properties, optimization of properties.

+ - About the Authors Click to collapse

E. A. Gushina (Saint Petersburg University of Aerospace Instrumentation, Saint Petersburg, Russia) E-mail: Данный адрес e-mail защищен от спам-ботов, Вам необходимо включить Javascript для его просмотра.

+ - References Click to collapse

1. Gurenko A. V. (2024). Polymer composite materials in the aerospace industry. Nauchniy aspekt, (6). [in Russian language]
2. Polymer composites. Test methods. General requirements. (2017). Ru Standard GOST 57921‒2017. Moscow: Standartinform. [in Russian language]
3. Cheng Z. Q., Liu H., Tan W. (2024). Advanced Computational Modelling of Composite Materials. Engineering Fracture Mechanics, 305(2).
4. Rammerstorfer F. G., Dorninger K., Starlinger A., Skrna-Jakl I. C. (1994). Computational Methods in Composite Analysis and Design. Engineering Mechanics of Fibre Reinforced Polymers and Composite Structures. Chapter 8, 209 ‒ 231. Wien: Springer. (International Centre for Mechanical Sciences (CISM). 348).
5. Morgan D., Jacobs R. (2020). Opportunities and Challenges for Machine Learning in Materials Science. Annual Review of Materials Research, 50(1), 71 ‒ 103.
6. Mason R. D., Lind D. A. (1999). Statistical Techniques in Business and Economics. Irwin/McGraw Hill.
7. Parker A. J., Barnard A. S. (2019). Selecting Appropriate Clustering Methods for Materials Science Applications of Machine Learning. Advanced Theory and Simulations, 2(12).
8. Zhao J., Ramos N. M. M., Simoes M. L. et al. (2015). Application of Clustering Technique for Definition of Generic Objects in a Material Databas. Journal of Building Physics, vol. 39, (2), 124 ‒ 146.
9. Jiang Z., Zhang Z., Friedrich K. (2007). Prediction on Wear Properties of Polymer Composites with Artificial Neural Networks. Composites Science and Technology, 67(2), 168 ‒ 176.
10. Hamidi Y. K., Berrado A., Altan M. C. (2020). Machine Learning Applications in Polymer Composites. AIP Conference Proceedings. AIP Publishing, 2205(1).
11. Tao L., Chen G., Li Y. (2021). Machine Learning Discovery of High-Temperature Polymers. Patterns, 2(4).
12. Gushchina E. A. (2024). Design of a database of polymer composite materials. Vestnik Kazanskogo gosudarstvennogo tekhnicheskogo universiteta im. A. N. Tupoleva, (2), 46 ‒ 49. [in Russian language]
13. Ayatollahi M. R., Shadlou S., Shokrieh M., Chitsazzadeh M. (2011). Effect of Multi-Walled Carbon Nanotube Aspect Ratio on Mechanical and Electrical Properties of Epoxy-based Nanocomposites. Polymer Testing, 30(5), 548 ‒ 556.
14. Hawkins S. A., Yao H., Wang H., Sue H.-J. (2017). Tensile Properties and Electrical Conductivity of Epoxy Composite thin Films Containing Zinc Oxide Quantum Dots and Multi-Walled Carbon Nanotubes. Carbon, 115, 18 ‒ 27.
15. Verma P., Saini P., Choudhary V. (2015). Designing of Carbon Nanotube/Polymer Composites using Melt Recirculation Approach: Effect of Aspect RAtio on Mechancal, Electrical and EMI Shielding Response. Materials & Design, 88, 269 ‒ 277.
16. Selukov D. A., Shilov V. S. (2016). Finding the optimal number of clusters using the elbow method. Innovatsionnye tekhnologii: teoriya, instrumenty, praktika, (1), 107 ‒ 111. [in Russian language]
17. Gel'man E., Hill Dzh., Vekhtari A. (2022). Regression: theory and practice. Cambridge: Cambridge University Press. [in Russian language]

+ - Purchase digital version of a single article Click to collapse

This article is available in electronic format (PDF).

DOI: 10.14489/td.2025.04.pp.062-068

Copy the article DOI and follow the link https://id-spektr.ru/product/pokupka-elektronnoy-stati-iz-zhurnala-kontrol-diagnostika

Please specify the article DOI in the order comments.