Al2O3 takviyeli cam elyaf kompozitlerde aşınma davranışının deneysel incelenmesi ve yapay sinir ağları ile makine öğrenmesi modellerinin karşılaştırmalı analizi

Abstract

Bu çalışmada, cam elyaf takviyeli epoksi kompozitlerin tribolojik performanslarını iyileştirmek amacıyla farklı miktarlarda (%1-5 ağırlıkça) eklenen Al2O3 partiküllerinin aşınma davranışları üzerindeki etkileri deneysel olarak araştırılmıştır. Elle yatırma yöntemiyle üretilen kompozit laminantlar, ball-on-disc bilye test düzeneği kullanılarak aşınma testlerine tabi tutulmuştur. Test edilen tüm numuneler arasında, %3 ağırlıkça Al2O3 içeren kompozit en yüksek aşınma direncini göstermiştir. Saf kompozitle karşılaştırıldığında, özgül aşınma oranı %70'e kadar azalmıştır. Buna karşılık, %4 ve %5 Al2O3 ilavesi, partikül aglomerasyonu nedeniyle aşınma direncinde bir azalmaya neden olmuştur. En yüksek özgül aşınma oranı 260x10⁻⁶ mm³/Nm iken, %3 eklenen numunede bu değer 80x10⁻⁶ mm³/Nm'ye düşmüştür. Ayrıca, yapay sinir ağı ve farklı makine öğrenimi regresörleri kullanılarak aşınma oranı tahminleri gerçekleştirilmiştir. En düşük MAPE değerlerine Random Forest (%17.62), Ridge regresörü (%18.46) ve ANN (%19.92) ulaşmış olup, bu da Al2O3 takviyeli cam elyaf kompozitler için güçlü tahmin performansına işaret etmektedir. Grid search metodu ile optimize edilen yapay sinir ağı modeli 0.9'lık bir ortalama karesel hata ve 0.92'lik bir belirlilik katsayısı değeri elde ederken, rastgele orman regresörü 0.91'lik bir belirlilik katsayısı değeriyle güçlü bir genelleme göstermiştir. Sonuçlar, aşınma performansı analizinde hem parçacık oranının hem de veri odaklı modellerin kritik rollerini ortaya koymuştur.

Keywords

• GFRP
• Aşınma
• Al2O3
• Makine öğrenmesi
• Yapay sinir ağları

Experimental investigation of wear behavior in Al2O3-reinforced glass fiber composites and comparative analysis of artificial neural network and machine learning models

Abstract

This study experimentally investigates the effects of adding different amounts (1-5 wt.%) of Al2O3 particles on the wear behavior of glass fiber-reinforced epoxy composites to improve their tribological performance. Composite laminates produced using the hand-lay up method were subjected to wear tests using a ball-on-disc test setup under dry sliding conditions. Among all tested compositions, the composite containing 3 wt.% Al2O3 exhibited the highest wear resistance. Compared to the neat composite, the specific wear rate was reduced by up to 70%. In contrast, 4% and 5% Al2O3 additions resulted in a decrease in wear resistance due to particle agglomeration. While the highest specific wear rate was 260×10⁻⁶ mm³/Nm, this value decreased to 80×10⁻⁶ mm³/Nm in the 3% added sample. Furthermore, wear rate predictions were performed using models such as artificial neural network and different machine learning regressors. Random Forest (17.62%), Ridge regressor (18.46) and artificial neural network (19.92%) achieved the lowest MAPE values, indicating strong predictive performance for Al2O3-reinforced glass fiber composites. The artificial neural network model optimized with grid search achieved a mean squared error of 0.90 and a coefficient of determination of 0.92, while the random forest regressor demonstrated strong generalization with a coefficient of determination of 0.91. The results demonstrated the critical roles of both particle ratio and data-driven models in wear performance analysis.

Keywords

• GFRP
• Wear
• Al2O3
• Machine learning
• ANN

References

1. P. K. Mallick, Fiber-Reinforced Composites: Materials, Manufacturing, and Design, Third Edition. 2007. https://doi.org/10.1201/9781420005981.
2. Z. Cao, T. Hao, P. Wang, Y. Zhang, B. Cheng, T. Yuan, and J. Meng, Surface modified glass fiber membranes with superior chemical and thermal resistance for O/W separation. Chemical Engineering Journal, 309, 30-40, 2017. https://doi.org/10.1016/j.cej.2016.10.013.
3. A. Kumre, R. S. Rana, and R. Purohit, A Review on mechanical property of sisal glass fiber reinforced polymer composites. Materials Today: Proceedings, 4, 2, Part A, 3466-3476, 2017. https://doi.org/10.1016/ j.matpr.2017.02.236.
4. A. C. Detomi, R. M. D. Santos, S. L. M. R. Filho, C. C. Martuscelli, T. H. Panzera, and F. Scarpa, Statistical effects of using ceramic particles in glass fibre reinforced composites. Materials & Design, 55, 463-470, 2014. https://doi.org/10.1016/ j.matdes.201 3.09.026.
5. A. Mohanty, V. K. Srivastava, and P. U. Sastry, Investigation of mechanical properties of alumina nanoparticle-loaded hybrid glass/carbon-fiber-reinforced epoxy composites. Journal of Applied Polymer Science, 131, 1, 2014. https://doi.org/10.1002/ app.39749.
6. S. A. B. Lins, M. C. G. Rocha, and J. R. M. d’Almeida, Mechanical and thermal properties of high-density polyethylene/alumina/glass fiber hybrid composites. Journal of Thermoplastic Composite Materials, 32, 11, 1566-1581, 2019. https://doi.org/10.1177/ 0892705718 797391.
7. A. Fathy, A. Shaker, M. A. Hamid, and A. Megahed, The effects of nano-silica/nano-alumina on fatigue behavior of glass fiber-reinforced epoxy composites. Journal of Composite Materials, 51, 12, 1667-1679, 2017. https://doi.org/10.1177/0021998316661870.
8. A. Mohanty and V. K. Srivastava, Effect of alumina nanoparticles on the enhancement of impact and flexural properties of the short glass/carbon fiber reinforced epoxy based composites. Fibers and Polymers, 16, 1, 188-195, 2015. https://doi.org/ 10.1007/s12221-015-0188-5.

9. M. Abu-Okail, N. A. Alsaleh, W. M. Farouk, A. Elsheikh, A. Abu-Oqail, Y. A. Abdelraouf, and M. A. Ghafaar, Effect of dispersion of alumina nanoparticles and graphene nanoplatelets on microstructural and mechanical characteristics of hybrid carbon/glass fibers reinforced polymer composite. Journal of Materials Research and Technology, 14, 2624-2637, 2021. https://doi.org/10.1016/j.jmrt.2021.07.158.
10. K. Sourabh K Singh, S. Kumar, and K. K. Singh, Computational data-driven based optimization of tribological performance of graphene filled glass fiber reinforced polymer composite using machine learning approach. Materials Today: Proceedings, 66, 3838-3846, 2022. https://doi.org/10.1016/ j.matpr.2022.06 .253.
11. Z. Li, X. Qi, C. Liu, B. Fan, and X. Yang, Particle size effect of PTFE on friction and wear properties of glass fiber reinforced epoxy resin composites. Wear, 532-533, 205104, 2023. https://doi.org/10.1016/ j.wear.2023.205104.
12. S. Kumar, K. S. K. Singh, and K. K. Singh, Data-driven modeling for predicting tribo-performance of graphene-incorporated glass-fabric reinforced epoxy composites using machine learning algorithms. Polymer Composites, 43, 9, 6599-6610, 2022. https://doi.org/10.1002/pc.26974.
13. H. H. Parikh and P. P. Gohil, Experimental investigation and prediction of wear behavior of cotton fiber polyester composites. Friction, 5, 2, 183-193, 2017. https://doi.org/10.1007/s40544-017-0145-y.
14. P. K. Padhi, A. Satapathy, and A. M. Nakka, Processing, characterization, and wear analysis of short glass fiber-reinforced polypropylene composites filled with blast furnace slag. Journal of Thermoplastic Composite Materials, 28, 5, 656-671, 2015. https://doi.org/10.117 7/0892705713486142.
15. R. Yadav, H.-H. Lee, A. Meena, and Y. K. Sharma, Effect of alumina particulate and E-glass fiber reinforced epoxy composite on erosion wear behavior using Taguchi orthogonal array. Tribology International, 175, 107860, 2022. https://doi. org/10.1016/j.triboint.2022.107860.
16. K. P. Srinivasa Perumal, L. Selvarajan, K. P. Manikandan, and C. Velmurugan, Mechanical, tribological, and surface morphological studies on the effects of hybrid ilmenite and silicon dioxide fillers on glass fibre reinforced epoxy composites. Journal of the Mechanical Behavior of Biomedical Materials, 146, 106095, 2023. https://doi.org/10.1016/ j.jmbbm. 2023.106095.
17. P. Singh, S. Singh, R. Ojha, P. Tiwari, S. Khan, R. Kumar, and A. Gupta, Characterization of wear of FRP composites: A review. Materials Today: Proceedings, 64, 1357-1361, 2022. https://doi.org/10.1016/ j.matpr.2022.04.236.
18. K. A. Sheikh and M. M. Khan, Predictive modeling of abrasive wear in in-situ TiC reinforced ZA37 alloy: A machine learning approach. Tribology International, 202, 110291, 2025. https://doi.org/10.1016/ j.triboint.2024.110291.
19. M. D. Kiran, L. Y. B R, A. Babbar, R. Kumar, S. C. H S, R. P. Shetty, S. K B, S.K. L, R. Kaur, M. Q. Alkahtani, S. Islam, and R. Kumar, Tribological properties of CNT-filled epoxy-carbon fabric composites: Optimization and modelling by machine learning. Journal of Materials Research and Technology, 28, 2582-2601, 2024. https://doi.org/10.1016/j.jmrt.2023. 12.175.
20. F. Aydın, K.M. Karaoğlan, H. Y. Pektürk, B. Demir, V. Karakurt, and H. Ahlatçı, The comparative evaluation of the wear behavior of epoxy matrix hybrid nano-composites via experiments and machine learning models. Tribology International, 204, 110451, 2025. https://doi.org/10.1016/j.triboint.2024.110451.