Artificial intelligence as applied to classifying epoxy composites for aircraft
Abstract
The problem of classification of epoxy composites used for the manufacture of aircraft structures is solved by machine learning methods: neural network, reinforced trees and random forests. Classification metrics were obtained for each method used. Parameters such as precision, recall, F1 score and support were determined. The neural network classifier demonstrated the highest results. Boosted trees and random forests showed slightly lower results than the neural network method. At the same time, the classification metrics were high enough in each case. Therefore, machine learning methods effectively classify epoxy composites. The results obtained are in good agreement with the experimental ones. The prediction accuracy score obtained using each method was greater than 0.88.
Keyword : aircraft, aerospace applications, thermal conductivity coefficient, artificial intelligence, neural network, machine learning
How to Cite
Yasniy, O., Maruschak, P., Mykytyshyn, A., Didych, I., & Tymoshchuk, D. (2025). Artificial intelligence as applied to classifying epoxy composites for aircraft. Aviation, 29(1), 22–29. https://doi.org/10.3846/aviation.2025.23149
This work is licensed under a Creative Commons Attribution 4.0 International License.
References
Alpayndin, E. (2010). Introduction to machine learning. The Knowledge Engineering Review, 25(3), 353–353. https://doi.org/10.1017/S0269888910000056
Błażejewski, W., Barcikowski, M., Lubecki, M., Stabla, P., Bury, P., Stosiak, M., & Lesiuk, G. (2021). The mechanical investigation of filament-wound CFRP structures subjected to different cooling rates in terms of compressive loading and residual stresses – an experimental approach. Materials, 14(4), Article 1041. https://doi.org/10.3390/ma14041041
Das, M., Sahu, S., & Parhi, D. R. (2019). A review of application of composite materials for aerospace structures and its damage detection using artificial intelligence techniques. In International Conference on Artificial Intelligence in Manufacturing & Renewable Energy (ICAIMRE). SSRN. https://doi.org/10.2139/ssrn.3714181
Deng, F., He, Y., Zhou, S., Yu, Y., Cheng, H., & Wu, X. (2018). Compressive strength prediction of recycled concrete based on deep learning. Construction and Building Materials, 175, 562–569. https://doi.org/10.1016/j.conbuildmat.2018.04.169
Dobrotvor, I. G., Stukhlyak, P. D., Mykytyshyn, A. G., & Stukhlyak, D. P. (2021). Influence of thickness and dispersed impurities on residual stresses in epoxy composite coatings. Strength of Materials, 53, 283–290. https://doi.org/10.1007/s11223-021-00287-x
Gorunescu, F. (2011). Data mining: Concepts, models and techniques. Springer. https://doi.org/10.1007/978-3-642-19721-5
Guadagno, L., Pantelakis, S., Strohmayer, A., & Raimondo, M. (2022). High-performance properties of an aerospace epoxy resin loaded with carbon nanofibers and glycidyl polyhedral oligomeric silsesquioxane. Aerospace, 9(4), Article 222. https://doi.org/10.3390/aerospace9040222
Harris, C. E., Starnes Jr., J. H., & Shuart, M. J. (2001). An Assessment of the state-of-the-art in the design and manufacturing of large composite structures for aerospace vehicles (NASA Technical Memorandum TM-2001-210844). NASA Langley Research Center. https://ntrs.nasa.gov/api/citations/20010041346/downloads/20010041346.pdf
Harris, C. E., Starnes, J. H., & Shuart, M. J. (2002). Design and manufacturing of aerospace composite structures, state-of-the-art assessment. Journal of Aircraft, 39(4), 545–560. https://doi.org/10.2514/2.2992
Haykin, S. (2009). Neural networks and learning machines (3rd ed.). Pearson.
Karpenko, M., Stosiak, M., Deptuła, A., Urbanowicz, K., Nugaras, J., Królczyk, G., & Żak, K. (2023). Performance evaluation of extruded polystyrene foam for aerospace engineering applications using frequency analyses. The International Journal of Advanced Manufacturing Technology, 126, 5515–5526. https://doi.org/10.1007/s00170-023-11503-0
Khozeimeh, F., Sharifrazi, D., Izadi, N. H., Joloudari, J. H., Shoeibi, A., Alizadehsani, R., Tartibi, M., Hussain, S., Sani, Z. A., Khodatars, M., Sadeghi, D., Khosravi, A., Nahavandi, S., Tan, R.-S., Acharya, U. R., & Islam, Sh. M. Sh. (2022). RF-CNN-F: Random forest with convolutional neural network features for coronary artery disease diagnosis based on cardiac magnetic resonance. Scientific Reports, 12, Article 11178. https://doi.org/10.1038/s41598-022-15374-5
Lee Sanchez, W. A., Huang, C.-Y., Chen, J.-X., Soong, Y.-C., Chan, Y.-N., Chiou, K.-C., Lee, T.-M., Cheng, C.-C., & Chiu, C.-W. (2021). Enhanced thermal conductivity of epoxy composites filled with Al2O3/Boron Nitride hybrids for underfill encapsulation materials. Polymers, 13(1), Article 147. https://doi.org/10.3390/polym13010147
Lin, Y., Huang, X., Chen, J., & Jiang, P. (2017). Epoxy thermoset resins with pristine high thermal conductivity. High Voltage, 2(3), 139–146. https://doi.org/10.1049/hve.2017.0120
Mohanty, J. R., Verma, B. B., Parhi, D. R. K., & Ray, D. R. (2009). Application of artificial neural network for predicting fatigue crack propagation life of aluminum alloys. Archives of Computational Materials Science and Surface Engineering, 1(3), 133–138.
Mykytyshyn, A. G. (2002). Development of technology and study of parameters of formation of products from epoxy-filled composites [CSc Dissertation, Lviv Polytechnic National University]. Lviv. (in Ukrainian).
Niccolai, A., Caputo, D., Chieco, L., Grimaccia, F., & Mussetta, M. (2021). Machine learning-based detection technique for NDT in industrial manufacturing. Mathematics, 9(11), Article 1251. https://doi.org/10.3390/math9111251
Pal, R. (2007). New models for thermal conductivity of particulate composites. Journal of Reinforced Plastics and Composites, 26(7), 643–651. https://doi.org/10.1177/0731684407075569
Pidaparti, R. M. V., & Palakal, M. (1995). Neural network approach to fatigue-crack-growth predictions under aircraft spectrum loadings. Journal of Aircraft, 32(4), 825–831. https://doi.org/10.2514/3.46797
Qing, S., & Li, C. (2024). Data-driven prediction on critical mechanical properties of engineered cementitious composites based on machine learning. Scientific Reports, 14, Article 15322. https://doi.org/10.1038/s41598-024-66123-9
Safavian, S. R., & Landgrebe, D. (1991). A survey of decision tree classifier methodology. IEEE Transactions on Systems, Man, and Cybernetics, 21(3), 660–674. https://doi.org/10.1109/21.97458
Stukhlyak, P. D., Mytnyk, M. M., & Mykytyshyn, A. H. (2000). Torsional pendulum for the investigation of dynamic characteristics of polymer materials. Materials Science, 36(3), 412–414. https://doi.org/10.1007/BF02769603
Stukhlyak, P. D. (1996). Rozrobka ta doslidzhennia kompozytnykh materialiv i pokryt na osnovi reaktoplastiv dlia vuzliv tertia i metalokonstruktsii [Disertacija doctora tekhnichnyh nauk, Fizyko-Mekhanichnyi Instytut im. G. V. Karpenka NAN Ukrainy]. Lviv. (in Ukrainian).
Tan, W. C. K., Kiew, J. C., Siow, K. Y., Sim, Z. R., Poh, H. S., & Taufiq, M. D. (2008). Self-healing of epoxy composite for aircraft’s structural applications. Solid State Phenomena, 136, 39–44. https://doi.org/10.4028/www.scientific.net/SSP.136.39
Towsyfyan, H., Biguri, A., Boardman, R., & Blumensath, T. (2020). Successes and challenges in non-destructive testing of aircraft composite structures. Chinese Journal of Aeronautics, 33(3), 771–791. https://doi.org/10.1016/j.cja.2019.09.017
Wasserman, P. D. (1989). Neural computing: Theory and practice. Coriolis Group (Sd).
Wei, H., Zhao, S., Rong, Q., & Bao, H. (2018). Predicting the effective thermal conductivities of composite materials and porous media by machine learning methods. International Journal of Heat and Mass Transfer, 127, 908–916. https://doi.org/10.1016/j.ijheatmasstransfer.2018.08.082
Yasnii, О. P., Pastukh, O. А., Pyndus, Y. І., Lutsyk, N. S., & Didych, I. S. (2018). Prediction of the diagrams of fatigue fracture of D16T aluminum alloy by the methods of machine learning. Materials Science, 54, 333–338. https://doi.org/10.1007/s11003-018-0189-9
Yasniy, O., Mytnyk, M., Maruschak, P., Mykytyshyn, A., & Didych, I. (2024). Machine learning methods as applied to modelling thermal conductivity of epoxy-based composites with different fillers for aircraft. Aviation, 28(2), 64–71. https://doi.org/10.3846/aviation.2024.21472
Błażejewski, W., Barcikowski, M., Lubecki, M., Stabla, P., Bury, P., Stosiak, M., & Lesiuk, G. (2021). The mechanical investigation of filament-wound CFRP structures subjected to different cooling rates in terms of compressive loading and residual stresses – an experimental approach. Materials, 14(4), Article 1041. https://doi.org/10.3390/ma14041041
Das, M., Sahu, S., & Parhi, D. R. (2019). A review of application of composite materials for aerospace structures and its damage detection using artificial intelligence techniques. In International Conference on Artificial Intelligence in Manufacturing & Renewable Energy (ICAIMRE). SSRN. https://doi.org/10.2139/ssrn.3714181
Deng, F., He, Y., Zhou, S., Yu, Y., Cheng, H., & Wu, X. (2018). Compressive strength prediction of recycled concrete based on deep learning. Construction and Building Materials, 175, 562–569. https://doi.org/10.1016/j.conbuildmat.2018.04.169
Dobrotvor, I. G., Stukhlyak, P. D., Mykytyshyn, A. G., & Stukhlyak, D. P. (2021). Influence of thickness and dispersed impurities on residual stresses in epoxy composite coatings. Strength of Materials, 53, 283–290. https://doi.org/10.1007/s11223-021-00287-x
Gorunescu, F. (2011). Data mining: Concepts, models and techniques. Springer. https://doi.org/10.1007/978-3-642-19721-5
Guadagno, L., Pantelakis, S., Strohmayer, A., & Raimondo, M. (2022). High-performance properties of an aerospace epoxy resin loaded with carbon nanofibers and glycidyl polyhedral oligomeric silsesquioxane. Aerospace, 9(4), Article 222. https://doi.org/10.3390/aerospace9040222
Harris, C. E., Starnes Jr., J. H., & Shuart, M. J. (2001). An Assessment of the state-of-the-art in the design and manufacturing of large composite structures for aerospace vehicles (NASA Technical Memorandum TM-2001-210844). NASA Langley Research Center. https://ntrs.nasa.gov/api/citations/20010041346/downloads/20010041346.pdf
Harris, C. E., Starnes, J. H., & Shuart, M. J. (2002). Design and manufacturing of aerospace composite structures, state-of-the-art assessment. Journal of Aircraft, 39(4), 545–560. https://doi.org/10.2514/2.2992
Haykin, S. (2009). Neural networks and learning machines (3rd ed.). Pearson.
Karpenko, M., Stosiak, M., Deptuła, A., Urbanowicz, K., Nugaras, J., Królczyk, G., & Żak, K. (2023). Performance evaluation of extruded polystyrene foam for aerospace engineering applications using frequency analyses. The International Journal of Advanced Manufacturing Technology, 126, 5515–5526. https://doi.org/10.1007/s00170-023-11503-0
Khozeimeh, F., Sharifrazi, D., Izadi, N. H., Joloudari, J. H., Shoeibi, A., Alizadehsani, R., Tartibi, M., Hussain, S., Sani, Z. A., Khodatars, M., Sadeghi, D., Khosravi, A., Nahavandi, S., Tan, R.-S., Acharya, U. R., & Islam, Sh. M. Sh. (2022). RF-CNN-F: Random forest with convolutional neural network features for coronary artery disease diagnosis based on cardiac magnetic resonance. Scientific Reports, 12, Article 11178. https://doi.org/10.1038/s41598-022-15374-5
Lee Sanchez, W. A., Huang, C.-Y., Chen, J.-X., Soong, Y.-C., Chan, Y.-N., Chiou, K.-C., Lee, T.-M., Cheng, C.-C., & Chiu, C.-W. (2021). Enhanced thermal conductivity of epoxy composites filled with Al2O3/Boron Nitride hybrids for underfill encapsulation materials. Polymers, 13(1), Article 147. https://doi.org/10.3390/polym13010147
Lin, Y., Huang, X., Chen, J., & Jiang, P. (2017). Epoxy thermoset resins with pristine high thermal conductivity. High Voltage, 2(3), 139–146. https://doi.org/10.1049/hve.2017.0120
Mohanty, J. R., Verma, B. B., Parhi, D. R. K., & Ray, D. R. (2009). Application of artificial neural network for predicting fatigue crack propagation life of aluminum alloys. Archives of Computational Materials Science and Surface Engineering, 1(3), 133–138.
Mykytyshyn, A. G. (2002). Development of technology and study of parameters of formation of products from epoxy-filled composites [CSc Dissertation, Lviv Polytechnic National University]. Lviv. (in Ukrainian).
Niccolai, A., Caputo, D., Chieco, L., Grimaccia, F., & Mussetta, M. (2021). Machine learning-based detection technique for NDT in industrial manufacturing. Mathematics, 9(11), Article 1251. https://doi.org/10.3390/math9111251
Pal, R. (2007). New models for thermal conductivity of particulate composites. Journal of Reinforced Plastics and Composites, 26(7), 643–651. https://doi.org/10.1177/0731684407075569
Pidaparti, R. M. V., & Palakal, M. (1995). Neural network approach to fatigue-crack-growth predictions under aircraft spectrum loadings. Journal of Aircraft, 32(4), 825–831. https://doi.org/10.2514/3.46797
Qing, S., & Li, C. (2024). Data-driven prediction on critical mechanical properties of engineered cementitious composites based on machine learning. Scientific Reports, 14, Article 15322. https://doi.org/10.1038/s41598-024-66123-9
Safavian, S. R., & Landgrebe, D. (1991). A survey of decision tree classifier methodology. IEEE Transactions on Systems, Man, and Cybernetics, 21(3), 660–674. https://doi.org/10.1109/21.97458
Stukhlyak, P. D., Mytnyk, M. M., & Mykytyshyn, A. H. (2000). Torsional pendulum for the investigation of dynamic characteristics of polymer materials. Materials Science, 36(3), 412–414. https://doi.org/10.1007/BF02769603
Stukhlyak, P. D. (1996). Rozrobka ta doslidzhennia kompozytnykh materialiv i pokryt na osnovi reaktoplastiv dlia vuzliv tertia i metalokonstruktsii [Disertacija doctora tekhnichnyh nauk, Fizyko-Mekhanichnyi Instytut im. G. V. Karpenka NAN Ukrainy]. Lviv. (in Ukrainian).
Tan, W. C. K., Kiew, J. C., Siow, K. Y., Sim, Z. R., Poh, H. S., & Taufiq, M. D. (2008). Self-healing of epoxy composite for aircraft’s structural applications. Solid State Phenomena, 136, 39–44. https://doi.org/10.4028/www.scientific.net/SSP.136.39
Towsyfyan, H., Biguri, A., Boardman, R., & Blumensath, T. (2020). Successes and challenges in non-destructive testing of aircraft composite structures. Chinese Journal of Aeronautics, 33(3), 771–791. https://doi.org/10.1016/j.cja.2019.09.017
Wasserman, P. D. (1989). Neural computing: Theory and practice. Coriolis Group (Sd).
Wei, H., Zhao, S., Rong, Q., & Bao, H. (2018). Predicting the effective thermal conductivities of composite materials and porous media by machine learning methods. International Journal of Heat and Mass Transfer, 127, 908–916. https://doi.org/10.1016/j.ijheatmasstransfer.2018.08.082
Yasnii, О. P., Pastukh, O. А., Pyndus, Y. І., Lutsyk, N. S., & Didych, I. S. (2018). Prediction of the diagrams of fatigue fracture of D16T aluminum alloy by the methods of machine learning. Materials Science, 54, 333–338. https://doi.org/10.1007/s11003-018-0189-9
Yasniy, O., Mytnyk, M., Maruschak, P., Mykytyshyn, A., & Didych, I. (2024). Machine learning methods as applied to modelling thermal conductivity of epoxy-based composites with different fillers for aircraft. Aviation, 28(2), 64–71. https://doi.org/10.3846/aviation.2024.21472