Sonlu Elemanlar Yöntemi ve Makine Öğrenme Algoritmaları Kullanılarak Silisyum Karbür Seramik Vücut Zırhının Balistik Performans Analizi

Öz

Bu çalışma, farklı kalınlıklardaki silisyum karbür (SiC) seramik vücut zırh plakalarına çarpan mermilerin artık hızını tahmin etmek için makine öğrenimine dayalı bir yaklaşım sunmaktadır. Yüksek hızlı darbe altında zırhın balistik tepkisini modellemek için ANSYS sonlu elemanlar yazılımı kullanılarak açık dinamik simülasyonlar gerçekleştirildi. Ana girdi parametreleri arasında mermi tipi, mermi namlu çıkış hızı, seramik kalınlığı ve gözenek boyutu yer almaktadır. Çıkış parametresi, darbeden sonra merminin ölçülen artık hızıdır. Simülasyon verileri, üç farklı makine öğrenimi modelini eğitmek ve değerlendirmek için kullanıldı: Doğrusal Regresyon, ElasticNet ve Çok Katmanlı Algılayıcı (MLP). Her modelin tahmini performansı, hem eğitim hem de test veri kümelerinde belirleme katsayısı (R), ortalama mutlak hata (MAE) ve kök ortalama kare hata (RMSE) ölçümleri kullanılarak değerlendirildi. Test edilen algoritmalar arasında, MLP modeli en yüksek doğruluk ve en düşük hata değerlerine ulaşarak balistik çarpma olaylarını yöneten karmaşık doğrusal olmayan ilişkileri yakalamada üstün bir yetenek gösterdi. Bulgular, yüksek doğruluklu simülasyon verileriyle eğitildiğinde makine öğrenimi tekniklerinin balistik koruma uygulamalarında artık hızı tahmin etmek için etkili tahmin araçları olarak hizmet edebileceğini göstermektedir. Bu yaklaşım, koruyucu zırh sistemlerinin ön tasarım aşamasında kapsamlı fiziksel testlere ve hesaplama açısından pahalı simülasyonlara olan ihtiyacı önemli ölçüde azaltabilir ve böylece malzeme seçimi ve optimizasyon sürecini hızlandırabilir.

Anahtar Kelimeler

• Balistik
• Silisyum karbür
• Vücut zırhı
• Makine öğrenmesi
• Simülasyon

Ballistic Performance Analysis of Silicon Carbide Ceramic Body Armor Using Finite Element Method and Machine Learning Algorithms

Öz

This study presents a machine learning-based approach for predicting the residual velocity of projectiles impacting silicon carbide (SiC) ceramic body armor plates of varying thicknesses. Explicit dynamic simulations were performed using the ANSYS finite element software to model the ballistic response of the armor under high-velocity impact. Key input parameters included projectile type, bullet muzzle velocity, ceramic thickness, and mesh size. The output parameter of interest was the residual velocity of the projectile after impact. Simulation data were used to train and evaluate three different machine learning models: Linear Regression, ElasticNet, and Multilayer Perceptron (MLP). The predictive performance of each model was assessed using the coefficient of determination (R), mean absolute error (MAE), and root mean square error (RMSE) metrics across both training and testing datasets. Among the tested algorithms, the MLP model achieved the highest accuracy and lowest error values, demonstrating superior capability in capturing the complex nonlinear relationships governing ballistic impact phenomena.The findings indicate that machine learning techniques, when trained with high-fidelity simulation data, can serve as efficient predictive tools for estimating residual velocity in ballistic protection applications. This approach can significantly reduce the need for extensive physical testing and computationally expensive simulations during the preliminary design phase of protective armor systems, thereby accelerating the material selection and optimization process.

Anahtar Kelimeler

• Ballistic
• Silicon carbide
• Body armor
• Machine learning
• Simulation

Kaynakça

1. [1] A. R. Williams, The Knight and the Blast Furnace: A History of the Metallurgy of Armour in the Middle Ages & the Early Modern Period, Brill, Leiden, 2003.
2. [2] T. A. Otitoju, P. U. Okoye, G. Chen, Y. Li, M. O. Okoye, S. Li, "Advanced ceramic components: Materials, fabrication, and applications," Journal of Industrial and Engineering Chemistry, 85, 34-65, 2020.
3. [3] X. Guo, X. Sun, X. Tian, G. J. Weng, Q. D. Ouyang, L. L. Zhu, "Simulation of ballistic performance of a two-layered structure of nanostructured metal and ceramic," Composite Structures, 157, 163-173, 2016.
4. [4] J. Pittari III, G. Subhash, J. Zheng, V. Halls, P. Jannotti, "The rate-dependent fracture toughness of silicon carbide- and boron carbide-based ceramics," Journal of the European Ceramic Society, 35, 4411-4422, 2015.
5. [5] G. J. Appleby-Thomas, D. C. Wood, A. Hameed, J. Painter, B. Fitzmaurice, "On the effects of powder morphology on the post-comminution ballistic strength of ceramics," International Journal of Impact Engineering, 100, 46-55, 2017.
6. [6] P. Chabera, A. Boczkowska, A. Morka, P. Kędzierski, T. Niezgoda, A. Oziębło, A. Witek, "Comparison of numerical and experimental study of armour system based on alumina and silicon carbide ceramics," Bulletin of the Polish Academy of Sciences. Technical Sciences, 63, 2, 363-367, 2015.
7. [7] F. Cui, G. Wu, T. Ma, W. Li, "Effect of ceramic properties and depth-of-penetration test parameters on the ballistic performance of armour ceramics," Defence Science Journal, 67, 3, 2017.
8. [8] S. G. Savio, V. Madhu, "Ballistic performance evaluation of ceramic tiles with respect to projectile velocity against hard steel projectile using DOP test," International Journal of Impact Engineering, 113, 161-167, 2018.

9. [9] D. Hu, Y. Zhang, Z. Shen, Q. Cai, "Investigation on the ballistic behavior of mosaic SiC/UHMWPE composite armor systems," Ceramics International, 43, 13, 10368-10376, 2017.
10. [10] Z. Shen, D. Hu, G. Yang, X. Han, "Ballistic reliability study on SiC/UHMWPE composite armor against armor-piercing bullet," Composite Structures, 213, 209-219, 2019.
11. [11] S. Ryan, N. M. Sushma, A. K. A. V., J. Berk, T. Hashem, S. Rana, S. Venkatesh, "Machine learning for predicting the outcome of terminal ballistics events," Defence Technology, 31, 14-26, 2024.
12. [12] J. A. Artero-Guerrero, J. Pernas-Sánchez, J. Martín-Montal, D. Varas, J. López-Puente, "The influence of laminate stacking sequence on ballistic limit using a combined Experimental/FEM/Artificial Neural Networks (ANN) methodology," Composite Structures, 183, 299-308, 2018.
13. [13] Y. Wang, W. Sun, "Machine learning-based real-time velocity prediction of projectile penetration to carbon/aramid hybrid fiber laminates," Thin-Walled Structures, 197, 111600, 2024.
14. [14] M. Khan, M. F. Javed, N. A. Othman, S. K. U. Rehman, F. Ahmad, "Predicting penetration depth in ultra-high-performance concrete targets under ballistic impact: an interpretable machine learning approach augmented by deep generative adversarial network," Results in Engineering, 25, 103909, 2025.
15. [15] Z. Zhu, X. Kong, H. Zhou, C. Zheng, W. Wu, "A hybrid data-driven machine learning framework for predicting the impact resistance of composite armor," International Journal of Impact Engineering, 195, 105125, 2025.
16. [16] H. B. Mutu, "Machine learning-based approach for ballistic performance prediction of hybrid armors," Materials Today Communications, 113226, 2025.
17. [17] X. D. Lei, X. Q. Wu, Z. Zhang, K. L. Xiao, Y. W. Wang, C. G. Huang, "A machine learning model for predicting the ballistic impact resistance of unidirectional fiber-reinforced composite plate," Scientific Reports, 11, 6503, 2021.
18. [18] N. Kazarinov, A. Khvorov, "Predicting impact strength of perforated targets using artificial neural networks trained on FEM-generated datasets," Defence Technology, 32, 32-44, 2024.
19. [19] R. Andreotti, V. Leggeri, A. Casaroli, M. Quercia, C. Bettin, M. Zanella, M. V. Boniardi, "A simplified constitutive model for a SEBS gel muscle simulant-development and experimental validation for finite elements simulations of handgun and rifle ballistic impacts," Frattura e Integrità Strutturale, 16, 61, 176-197, 2022.
20. [20] X. Quan, R. A. Clegg, M. S. Cowler, N. K. Birnbaum, C. J. Hayhurst, "Numerical simulation of long rods impacting silicon carbide targets using JH-1 model," International Journal of Impact Engineering, 33, 1-12, 634-644, 2006.
21. [21] Autodyn, A.N.S.Y.S., "Theory Manual Revision 4.3," Century Dynamics, Concord, CA, 2005.
22. [22] T. J. Holmquist, G. R. Johnson, "Response of silicon carbide to high velocity impact," Journal of Applied Physics, 91, 9, 5858-5866, 2002.
23. [23] A. Araslı, "Grafen kaplı silisyum karbür seramiklerin mekanik ve balistik özelliklerinin incelenmesi," Yüksek Lisans Tezi, Fen Bilimleri Enstitüsü, [Üniversite Adı], [Şehir], Türkiye, 2022.
24. [24] M. Wagner, R. Adamczak, A. Porollo, J. Meller, "Linear regression models for solvent accessibility prediction in proteins," Journal of Computational Biology, 12, 355-369, 2005.
25. [25] J. Friedman, T. Hastie, R. Tibshirani, "Regularization paths for generalized linear models via coordinate descent," Journal of Statistical Software, 33, 1-22, 2010.
26. [26] H. Zou, T. Hastie, "Regularization and variable selection via the elastic net," Journal of the Royal Statistical Society B, 67, 301-320, 2005.
27. [27] S. Haykin, Neural Networks: A Comprehensive Foundation, Prentice Hall PTR, New Jersey, 1994.
28. [28] I. Goodfellow, Y. Bengio, A. Courville, Deep Learning, MIT Press, Cambridge, 2016.
29. [29] C. M. Bishop, N. M. Nasrabadi, Pattern Recognition and Machine Learning, Springer, New York, 2006.
30. [30] K. Gurney, An Introduction to Neural Networks, CRC Press, Boca Raton, 2018.
31. [31] Y. LeCun, Y. Bengio, G. Hinton, "Deep learning," Nature, 521, 7553, 436-444, 2015.
32. [32] G. P. Zhang, "Time series forecasting using a hybrid ARIMA and neural network model," Neurocomputing, 50, 159-175, 2003.
33. [33] H. B. Mutu, A. Özer, "Experimental and finite element analysis of ballistic properties of composite armor made of alumina, carbon and UHMWPE," Polymer Composites, 45, 15, 13844-13860, 2024.
34. [34] S. N. Monteiro, L. H. L. Louro, W. Trindade, C. N. Elias, C. L. Ferreira, E. de Sousa Lima, E. P. Lima Jr., "Natural curaua fiber-reinforced composites in multilayered ballistic armor," Metallurgical and Materials Transactions A, 46, 10, 4567-4577, 2015.
35. [35] A. Tasdemirci, G. Tunusoglu, M. Güden, "The effect of the interlayer on the ballistic performance of ceramic/composite armors: Experimental and numerical study," International Journal of Impact Engineering, 44, 1-9, 2012.
36. [36] P. Hu, Y. Cheng, P. Zhang, J. Liu, H. Yang, J. Chen, "A metal/UHMWPE/SiC multi-layered composite armor against ballistic impact of flat-nosed projectile," Ceramics International, 47, 16, 22497-22513, 2021.
37. [37] G. Crouch, G. Appleby-Thomas, P. J. Hazell, "A study of the penetration behaviour of mild-steel-cored ammunition against boron carbide ceramic armours," International Journal of Impact Engineering, 80, 203-211, 2015.