004.032.26

composite materials, neural networks, artificial intelligence, Explainable AI, optimization, quantum computing, advanced materials.                                                                   

Modern industrial development demands the creation of new materials to enhance the durability and operational lifespan of machines while reducing metal and energy consumption. Composite materials, particularly those based on polymers (reactoplasts), play a key role in achieving these goals. Neural networks, including CNNs, RNNs, LSTMs, GANs, and transformers, outperform traditional algorithms in pattern recognition tasks and are effective tools for analyzing macro- and microstructures of composite materials with predefined properties. Despite challenges in training deep models, requiring significant computational resources and energy, optimization methods like quantization and distillation help reduce costs. Integrating quantum computing further accelerates optimization processes. The importance of Explainable AI is emphasized to address the «black-box» nature of neural networks, ensuring their reliability for critical applications. These technologies are essential for advancing intelligent systems and creating next-generation materials for high-tech industries.

1. Lingxi Xie, Xin Chen, Kaifeng Bi, Longhui Wei, Yuhui Xu, Lanfei Wang, Zhengsu Chen, An Xiao, Jianlong Chang, Xiaopeng Zhang, and Qi Tian. 2021. Weight-Sharing Neural Architecture Search: A Battle to Shrink the Optimization Gap. ACM Comput. Surv. 54, 9, Article 183 (December 2022), 37 pages. Available at: https://doi.org/10.1145/3473330.
2. Mazumder Rahinul & Govindaraj Premika & Mathews Lalson & Salim Nisa & Antiohos Dennis & Hameed Nishar. (2023). Modeling, Simulation, and Machine Learning in Thermally Conductive Epoxy Materials, Multifunctional Epoxy Resins, 295–326. Doi:10.1007/978-981-19-6038-3_11.
3. Stukhliak Petpo, Martsenyuk Vasyl, Totosko Oleg, Stukhlyak Danulo, Didych Iryna. The use of neural networks for modeling the thermophysical characteristics of epoxy composites treated with electric spark water hammer. CEUR Workshop Proceedings, 3742, 2nd International Workshop on Computer Information Technologies in Industry 4.0, CITI 2024, Ternopil, June 12–14, 2024, pp. 13–24.
4. Shoulong Dong, Hong Quan, Dongfang Zhao, Hansheng Li, Junming Geng, Helei Liu.Generic AI models for mass transfer coefficient prediction in amine-based CO2 absorber, Part I: BPNN model, Chemical Engineering Science, Volume 264, 2022, 118165, ISSN 0009-2509, Available at: https://doi.org/ 10.1016/j.ces.2022.118165.
5. Sian Jin, Chengming Zhang, Xintong Jiang, Yunhe Feng, Hui Guan, Guanpeng Li, Shuaiwen Leon Song, and Dingwen Tao. 2021. COMET: a novel memory-efficient deep learning training framework by using error-bounded lossy compression. Proc. VLDB Endow. 15, 4 (December 2021), 886–899. Available at: https://doi.org/10.14778/3503585.3503597
6. S. Lee and H. Park, “Effect of Optimization Techniques on Feedback Alignment Learning of Neural Networks,” 2023 International Conference on Artificial Intelligence in Information and Communication (ICAIIC), Bali, Indonesia, 2023, pp. 227–231. Doi: 10.1109/ICAIIC57133.2023.10067047.
7. Stukhliak P., Totosko O., Vynokurova O., Stukhlyak D. Investigation of tribotechnical characteristics of epoxy composites using neural networks (2024) CEUR Workshop Proceedings, 3842, 1st International Workshop on Bioinformatics and Applied Information Technologies, BAIT 2024, Zboriv, 2 October 2024, pp. 157–170.
8. Fialko N., Dinzhos R., Sherenkovskii J., Meranova N., Navrodska R., Izvorska D., Korzhyk V., Lazarenko M., & Koseva N. (2021) Establishing patterns in the effect of temperature regime when manufacturing nanocomposites on their heat-conducting properties . Eastern-European Journal of Enterprise Technologies, 4 (5(112), pp. 21–26. Available at: https://doi.org/10.15587/1729-4061.2021.236915.
9. Totosko O. V., Levytskyi V. V., Stukhlyak P. D., Mykytyshyn A. H., Investigation of electrospark hydraulic shock influence on adhesive-cohesion characteristics of epoxy coatings, Functional materials, vol. 27, issue 4, 2020, pp. 760–766.
10. Shuai Li, Shu Li, Dongrong Liu, Jia Yang, Mingyu Zhang (2023) Hardness prediction of high entropy alloys with periodic table representation of composition, processing, structure and physical parameters, Journal of Alloys and Compounds, vol. 967, 171735, ISSN 0925-8388, Available at: https://doi.org/ 10.1016/j.jallcom.2023.171735.
11. Wang Y., Zhao Y. & Addepalli S. (2021).  Practical Options for Adopting Recurrent Neural Network and Its Variants on Remaining Useful Life Prediction. Chin. J. Mech. Eng. 34, 69 Available at: https://doi.org/ 10.1186/s10033-021-00588-x.
12. Li X.; Chen C. (2024) Temperature Prediction for Aerospace Thermal Tests Based on Physical and LSTM Hybrid Model. Aerospace, 11, 964. Available at: https://doi.org/10.3390/aerospace11120964.
13. Mienye I. D., Swart T. G. (2024) A Comprehensive Review of Deep Learning: Architectures, Recent Advances, and Applications. Information, 15, 755. Available at: https://doi.org/10.3390/info15120755.
14. Yechuri P. K., Ramadass S. (2021) Classification of image and text data using deep learning-based LSTM model. Traitement du Signal, vol. 38, no. 6, pp. 1809–1817. Available at: https://doi.org/10.18280/ts.380 625.
15. Feiyang Xue; Advancements and future directions in deep learning-based natural language processing. AIP Conf. Proc. 11 December 2024; 3194 (1): 050022. Available at: https://doi.org/10.1063/5.0224436.
16. Oralbekova D, Mamyrbayev O, Othman M, Kassymova D, Mukhsina K. (2023) Contemporary Approaches in Evolving Language Models. Applied Sciences, 13 (23):12901. Available at: https://doi.org/ 10.3390/app132312901.
17. Babu T., Nair R. R. & M., E. P. (2024). Foundations of Generative AI. In R. Kumar, S. Sahu, & S. Bhattacharya (Eds.), The Pioneering Applications of Generative AI (pp. 136–166). IGI Global Scientific Publishing.  Available at: ttps://doi.org/10.4018/979-8-3693-3278-8.ch007.
18. Qu P., Ji X. L., Chen J. J. et al. (2024) Research on General-Purpose Brain-Inspired Computing Systems. J. Comput. Sci. Technol. 39, 4–21. Available at: https://doi.org/10.1007/s11390-023-4002-3.
19. Manuel Lagunas, Ana Serrano, Diego Gutierrez, Belen Masia; The joint role of geometry and illumination on material recognition. Journal of Vision, 2021, 21 (2):2. Available at: https://doi.org/10.1167/jov.21.2.2.
20. J. Han, W. Wang, Y. Lin, X. LYU (2023) “MRU-Net: A remote sensing image segmentation network for enhanced edge contour Detection,” KSII Transactions on Internet and Information Systems, vol. 17, no. 12, pp. 3364–3382. Doi: 10.3837/tiis.2023.12.008.
21. Stukhljak P., Dobrotvor I., Mytnyk M., Мykytyshyn A. Investigation of the phenomena revealed on phase interface in epoxide-composites. Przetworstwo tworzyw. Polymer processing. 2017 N1 (175)/23, pp. 53–63.
22. Sapronov O., Zinchenko S., Nagovskyi D., Naumov V., Golotenko O., Sapronova A., Yakushchenko S., Sotsenko V. (2023) Anti-corrosion polymer coatings for vehicles protection. Scientific Journal of TNTU (Tern.), vol. 112, no. 4, pp. 127–137.
23. Berdnikova O., Kushnarova O., Bernatskyi A., Polovetskyi Y., Kostin V., Khokhlov M. Structure Features of Surface Layers in Structural Steel after Laser-Plasma Alloying with 48(WC–WC) + 48Cr + 4Al Powder. Proceedings of the 2021 IEEE 11th International Conference “Nanomaterials: Applications and Properties”, NAP2021, 2021. https://doi.org/10.1109/NAP51885.2021.9568516
24. Dolgov, N., Stukhlyak, P., Totosko, O., Melnychenko, O., Stukhlyak, D., & Chykhira, I. (2023). Analytical stress analysis of the furan epoxy composite coatings subjected to tensile test. Mechanics of Advanced Materials and Structures, 31(25), 6874–6884. Available at: https://doi.org/10.1080/15376494.2023. 2239811.
25. Stukhlyak P., Totosko O. (2021) The molecular mobility of the epoxy binder in a modified composites by electric-hammer. Scientific Journal of TNTU (Tern.), vol. 103, no. 3, pp. 70–78.
26. Mehrdad Shafiei Dizaji, Zhu Mao “Machine-learning to see defects: a hybrid attention-ConvLSTM-based convolutional neural network deep learning architecture for structural damage detection,” Proc. SPIE 12046, Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2022, 120460L (18 April 2022). Available at: https://doi.org/10.1117/12.2615542.
27. Yasniy O., Demchyk V., Lutsyk N. (2022) Modelling of functional properties of shape-memory alloys by machine learning methods. Scientific Journal of TNTU (Tern.), vol. 108, no. 4, pp. 74–78.
28. Murgod T. R., Reddy P. S., Gaddam S. et al. A Survey on Graph Neural Networks and its Applications in Various Domains. SN COMPUT. SCI. 6, 26 (2025). Available at: https://doi.org/10.1007/s42979-024-03543-4.
29. B. Cunha, C. Droz, A. Zine, S. Foulard and M. Ichchou, “A review of machine learning methods applied to structural dynamics and vibroacoustic,” Mechanical Systems and Signal Processing, vol. 200, pp. 110535, Jun. 2023. Doi:10.1016/j.ymssp.2023.110535.
30. O. Khatib, S. Ren, J. Malof and W. Padilla (2021) “Deep Learning the Electromagnetic Properties of Metamaterials – A Comprehensive Review,” Adv. Funct. Mater, vol. 31, no. 2101748, May. Doi:10.1002/adfm.202101748.

1. Lingxi Xie, Xin Chen, Kaifeng Bi, Longhui Wei, Yuhui Xu, Lanfei Wang, Zhengsu Chen, An Xiao, Jianlong Chang, Xiaopeng Zhang, and Qi Tian. 2021. Weight-Sharing Neural Architecture Search: A Battle to Shrink the Optimization Gap. ACM Comput. Surv. 54, 9, Article 183 (December 2022), 37 pages. Available at: https://doi.org/10.1145/3473330.
2. Mazumder Rahinul & Govindaraj Premika & Mathews Lalson & Salim Nisa & Antiohos Dennis & Hameed Nishar. (2023). Modeling, Simulation, and Machine Learning in Thermally Conductive Epoxy Materials, Multifunctional Epoxy Resins, 295–326. Doi:10.1007/978-981-19-6038-3_11.
3. Stukhliak Petpo, Martsenyuk Vasyl, Totosko Oleg, Stukhlyak Danulo, Didych Iryna. The use of neural networks for modeling the thermophysical characteristics of epoxy composites treated with electric spark water hammer. CEUR Workshop Proceedings, 3742, 2nd International Workshop on Computer Information Technologies in Industry 4.0, CITI 2024, Ternopil, June 12–14, 2024, pp. 13–24.
4. Shoulong Dong, Hong Quan, Dongfang Zhao, Hansheng Li, Junming Geng, Helei Liu.Generic AI models for mass transfer coefficient prediction in amine-based CO2 absorber, Part I: BPNN model, Chemical Engineering Science, Volume 264, 2022, 118165, ISSN 0009-2509, Available at: https://doi.org/ 10.1016/j.ces.2022.118165.
5. Sian Jin, Chengming Zhang, Xintong Jiang, Yunhe Feng, Hui Guan, Guanpeng Li, Shuaiwen Leon Song, and Dingwen Tao. 2021. COMET: a novel memory-efficient deep learning training framework by using error-bounded lossy compression. Proc. VLDB Endow. 15, 4 (December 2021), 886–899. Available at: https://doi.org/10.14778/3503585.3503597
6. S. Lee and H. Park, “Effect of Optimization Techniques on Feedback Alignment Learning of Neural Networks,” 2023 International Conference on Artificial Intelligence in Information and Communication (ICAIIC), Bali, Indonesia, 2023, pp. 227–231. Doi: 10.1109/ICAIIC57133.2023.10067047.
7. Stukhliak P., Totosko O., Vynokurova O., Stukhlyak D. Investigation of tribotechnical characteristics of epoxy composites using neural networks (2024) CEUR Workshop Proceedings, 3842, 1st International Workshop on Bioinformatics and Applied Information Technologies, BAIT 2024, Zboriv, 2 October 2024, pp. 157–170.
8. Fialko N., Dinzhos R., Sherenkovskii J., Meranova N., Navrodska R., Izvorska D., Korzhyk V., Lazarenko M., & Koseva N. (2021) Establishing patterns in the effect of temperature regime when manufacturing nanocomposites on their heat-conducting properties . Eastern-European Journal of Enterprise Technologies, 4 (5(112), pp. 21–26. Available at: https://doi.org/10.15587/1729-4061.2021.236915.
9. Totosko O. V., Levytskyi V. V., Stukhlyak P. D., Mykytyshyn A. H., Investigation of electrospark hydraulic shock influence on adhesive-cohesion characteristics of epoxy coatings, Functional materials, vol. 27, issue 4, 2020, pp. 760–766.
10. Shuai Li, Shu Li, Dongrong Liu, Jia Yang, Mingyu Zhang (2023) Hardness prediction of high entropy alloys with periodic table representation of composition, processing, structure and physical parameters, Journal of Alloys and Compounds, vol. 967, 171735, ISSN 0925-8388, Available at: https://doi.org/ 10.1016/j.jallcom.2023.171735.
11. Wang Y., Zhao Y. & Addepalli S. (2021).  Practical Options for Adopting Recurrent Neural Network and Its Variants on Remaining Useful Life Prediction. Chin. J. Mech. Eng. 34, 69 Available at: https://doi.org/ 10.1186/s10033-021-00588-x.
12. Li X.; Chen C. (2024) Temperature Prediction for Aerospace Thermal Tests Based on Physical and LSTM Hybrid Model. Aerospace, 11, 964. Available at: https://doi.org/10.3390/aerospace11120964.
13. Mienye I. D., Swart T. G. (2024) A Comprehensive Review of Deep Learning: Architectures, Recent Advances, and Applications. Information, 15, 755. Available at: https://doi.org/10.3390/info15120755.
14. Yechuri P. K., Ramadass S. (2021) Classification of image and text data using deep learning-based LSTM model. Traitement du Signal, vol. 38, no. 6, pp. 1809–1817. Available at: https://doi.org/10.18280/ts.380 625.
15. Feiyang Xue; Advancements and future directions in deep learning-based natural language processing. AIP Conf. Proc. 11 December 2024; 3194 (1): 050022. Available at: https://doi.org/10.1063/5.0224436.
16. Oralbekova D, Mamyrbayev O, Othman M, Kassymova D, Mukhsina K. (2023) Contemporary Approaches in Evolving Language Models. Applied Sciences, 13 (23):12901. Available at: https://doi.org/ 10.3390/app132312901.
17. Babu T., Nair R. R. & M., E. P. (2024). Foundations of Generative AI. In R. Kumar, S. Sahu, & S. Bhattacharya (Eds.), The Pioneering Applications of Generative AI (pp. 136–166). IGI Global Scientific Publishing.  Available at: ttps://doi.org/10.4018/979-8-3693-3278-8.ch007.
18. Qu P., Ji X. L., Chen J. J. et al. (2024) Research on General-Purpose Brain-Inspired Computing Systems. J. Comput. Sci. Technol. 39, 4–21. Available at: https://doi.org/10.1007/s11390-023-4002-3.
19. Manuel Lagunas, Ana Serrano, Diego Gutierrez, Belen Masia; The joint role of geometry and illumination on material recognition. Journal of Vision, 2021, 21 (2):2. Available at: https://doi.org/10.1167/jov.21.2.2.
20. J. Han, W. Wang, Y. Lin, X. LYU (2023) “MRU-Net: A remote sensing image segmentation network for enhanced edge contour Detection,” KSII Transactions on Internet and Information Systems, vol. 17, no. 12, pp. 3364–3382. Doi: 10.3837/tiis.2023.12.008.
21. Stukhljak P., Dobrotvor I., Mytnyk M., Мykytyshyn A. Investigation of the phenomena revealed on phase interface in epoxide-composites. Przetworstwo tworzyw. Polymer processing. 2017 N1 (175)/23, pp. 53–63.
22. Sapronov O., Zinchenko S., Nagovskyi D., Naumov V., Golotenko O., Sapronova A., Yakushchenko S., Sotsenko V. (2023) Anti-corrosion polymer coatings for vehicles protection. Scientific Journal of TNTU (Tern.), vol. 112, no. 4, pp. 127–137.
23. Berdnikova O., Kushnarova O., Bernatskyi A., Polovetskyi Y., Kostin V., Khokhlov M. Structure Features of Surface Layers in Structural Steel after Laser-Plasma Alloying with 48(WC–WC) + 48Cr + 4Al Powder. Proceedings of the 2021 IEEE 11th International Conference “Nanomaterials: Applications and Properties”, NAP2021, 2021. https://doi.org/10.1109/NAP51885.2021.9568516
24. Dolgov, N., Stukhlyak, P., Totosko, O., Melnychenko, O., Stukhlyak, D., & Chykhira, I. (2023). Analytical stress analysis of the furan epoxy composite coatings subjected to tensile test. Mechanics of Advanced Materials and Structures, 31(25), 6874–6884. Available at: https://doi.org/10.1080/15376494.2023. 2239811.
25. Stukhlyak P., Totosko O. (2021) The molecular mobility of the epoxy binder in a modified composites by electric-hammer. Scientific Journal of TNTU (Tern.), vol. 103, no. 3, pp. 70–78.
26. Mehrdad Shafiei Dizaji, Zhu Mao “Machine-learning to see defects: a hybrid attention-ConvLSTM-based convolutional neural network deep learning architecture for structural damage detection,” Proc. SPIE 12046, Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2022, 120460L (18 April 2022). Available at: https://doi.org/10.1117/12.2615542.
27. Yasniy O., Demchyk V., Lutsyk N. (2022) Modelling of functional properties of shape-memory alloys by machine learning methods. Scientific Journal of TNTU (Tern.), vol. 108, no. 4, pp. 74–78.
28. Murgod T. R., Reddy P. S., Gaddam S. et al. A Survey on Graph Neural Networks and its Applications in Various Domains. SN COMPUT. SCI. 6, 26 (2025). Available at: https://doi.org/10.1007/s42979-024-03543-4.
29. B. Cunha, C. Droz, A. Zine, S. Foulard and M. Ichchou, “A review of machine learning methods applied to structural dynamics and vibroacoustic,” Mechanical Systems and Signal Processing, vol. 200, pp. 110535, Jun. 2023. Doi:10.1016/j.ymssp.2023.110535.
30. O. Khatib, S. Ren, J. Malof and W. Padilla (2021) “Deep Learning the Electromagnetic Properties of Metamaterials – A Comprehensive Review,” Adv. Funct. Mater, vol. 31, no. 2101748, May. Doi:10.1002/adfm.202101748.