journal article·2026-02

Boosting machine learning algorithms for predicting the macroscopic material behavior of continuous fiber reinforced composite

Aiman Tariq, Ayşe Polat, Babür Deliktaş

Publisher page

Abstract

Macroscopic mechanical properties of fibrous materials are often characterized by modeling their microscale behavior using micromechanical techniques. This process typically involves using a Representative Volume Element (RVE) and finite element simulations to obtain the macroscopic behavior through homogenization. However, these micromechanical simulations can be computationally demanding, especially for 3D models with discrete material microstructures. This paper uses boosting machine learning algorithms to predict the homogenized macroscopic material behavior of heterogeneous composites. These models are trained on the micromechanical simulation results generated by varying the constitutive parameters of local phases and microscopic parameters such as fiber volume fraction. The Bayesian optimization is used to determine the best hyperparameters of the considered boosting models, which include adaptive boosting (AdaB), gradient boosting (GBR), light gradient boosting (LGB), and extreme gradient boosting (XGB). The performances of trained models are assessed using various metrics such as R 2 , MAE, MAPE, and RMSE and using various plots such as scatter plots, Taylor plots, radar plots, and bar plots. The comparative assessment showed that all the models predicted the homogenized stiffness matrix of the RVE successfully, with R 2 values between 0.94 and 0.99. The XGB model presented the best overall performance. This work contributes to the field of composites by presenting a new and computationally efficient approach to predict the macroscopic behavior of RVEs using boosting models.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Composite Material Mechanics · Mechanical Behavior of Composites · Innovations in Concrete and Construction Materials

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Bursa Uludag University

Funding

Bursa Uludag Universitesi · Scientific and Technological Research Council of Turkey

References (57)

Show source-provided references
1. 10.47852/bonviewAAES3202172310.47852/bonviewAAES32021723 ↗
2. 10.1016/j.compstruct.2023.11772610.1016/j.compstruct.2023.117726 ↗
3. 10.1016/j.compstruct.2023.11774010.1016/j.compstruct.2023.117740 ↗
4. Renard J, Marmonier MF. Etude de l’initiation de l’endommagement dans la matrice d’un matériau composite par une méthode d’homogénéisation. La Recherche aérospatiale. 1987; 6: 43–51.
5. 10.1016/0045-7825(90)90148-F10.1016/0045-7825(90)90148-F ↗
6. 10.1016/S0045-7825(03)00348-710.1016/S0045-7825(03)00348-7 ↗
7. 10.1016/j.ijmecsci.2011.06.00210.1016/j.ijmecsci.2011.06.002 ↗
8. 10.1177/073168441877944110.1177/0731684418779441 ↗
9. 10.1016/S0020-7683(03)00346-910.1016/S0020-7683(03)00346-9 ↗
10. 10.1016/j.jcp.2006.09.01910.1016/j.jcp.2006.09.019 ↗
11. 10.1016/j.cma.2016.04.00410.1016/j.cma.2016.04.004 ↗
12. 10.1016/j.compositesa.2023.10792910.1016/j.compositesa.2023.107929 ↗
13. 10.1016/j.tafmec.2024.10448710.1016/j.tafmec.2024.104487 ↗
14. 10.1098/rspa.1957.013310.1098/rspa.1957.0133 ↗
15. 10.1016/0022-5096(65)90010-410.1016/0022-5096(65)90010-4 ↗
16. 10.1016/0001-6160(73)90064-310.1016/0001-6160(73)90064-3 ↗
17. 10.1016/0167-6636(87)90005-610.1016/0167-6636(87)90005-6 ↗
18. 10.1007/BF0037268910.1007/BF00372689 ↗
19. 10.1016/j.cma.2016.02.00110.1016/j.cma.2016.02.001 ↗
20. 10.1016/j.ijsolstr.2023.11245210.1016/j.ijsolstr.2023.112452 ↗
21. 10.1016/j.cma.2018.01.03610.1016/j.cma.2018.01.036 ↗
22. 10.1002/nme.495310.1002/nme.4953 ↗
23. 10.1016/j.compstruct.2014.11.05210.1016/j.compstruct.2014.11.052 ↗
24. Tariq A, Uzun B, Deliktaş B, et al. Assessment of machine learning methods predicting the axial vibration frequencies of microbars. ZAMM‐Journal of Applied Mathematics and Mechanics/Zeitschrift Für Angewandte Mathematik Und Mechanik. 2024; 104(3): e202300916.
25. 10.1080/15376494.2024.232080910.1080/15376494.2024.2320809 ↗
26. 10.1007/s40430-024-05093-510.1007/s40430-024-05093-5 ↗
27. 10.1088/2631-6331/abf8f810.1088/2631-6331/abf8f8 ↗
28. 10.1016/j.ijmecsci.2023.10895210.1016/j.ijmecsci.2023.108952 ↗
29. 10.1016/j.rineng.2023.10158710.1016/j.rineng.2023.101587 ↗
30. 10.1016/j.mseb.2023.11677010.1016/j.mseb.2023.116770 ↗
31. 10.1016/j.ijsolstr.2021.11109510.1016/j.ijsolstr.2021.111095 ↗
32. 10.1016/j.ijsolstr.2023.11233410.1016/j.ijsolstr.2023.112334 ↗
33. 10.1016/j.ijsolstr.2023.11252110.1016/j.ijsolstr.2023.112521 ↗
34. 10.1016/j.ijsolstr.2021.11131110.1016/j.ijsolstr.2021.111311 ↗
35. 10.1016/j.compositesb.2021.10915210.1016/j.compositesb.2021.109152 ↗
36. 10.1016/j.cemconcomp.2021.10429510.1016/j.cemconcomp.2021.104295 ↗
37. 10.1007/s00366-021-01398-410.1007/s00366-021-01398-4 ↗
38. 10.1016/j.compscitech.2022.10941410.1016/j.compscitech.2022.109414 ↗
39. 10.1109/TKDE.2004.2910.1109/TKDE.2004.29 ↗
40. Tariq A, Uzun B, Deliktaş B, et al. A machine learning approach for buckling analysis of a bi-directional FG microbeam. Microsyst Technol. 2024; 1–22.
41. 10.3390/polym1319338910.3390/polym13193389 ↗
42. 10.1016/0167-6636(93)90066-Z10.1016/0167-6636(93)90066-Z ↗
43. 10.1016/j.jeurceramsoc.2017.11.03810.1016/j.jeurceramsoc.2017.11.038 ↗
44. 10.1016/j.compscitech.2003.11.00910.1016/j.compscitech.2003.11.009 ↗
45. 10.1201/978143989413210.1201/9781439894132 ↗
46. Kucherenko S, Albrecht D, Saltelli A. Exploring multi-dimensional spaces: a comparison of Latin hypercube and quasi-Monte Carlo sampling techniques. arXiv preprint arXiv:1505.02350. 2015.
47. 10.1016/j.mbs.2021.10859310.1016/j.mbs.2021.108593 ↗
48. 10.1098/rsta.2015.020210.1098/rsta.2015.0202 ↗
49. Grimm LG, Nesselroade Jr KP. Statistical applications for the behavioral and social sciences. Hoboken, NJ: John Wiley & Sons, 2019.
50. 10.1006/jcss.1997.150410.1006/jcss.1997.1504 ↗
51. 10.1214/aos/101320345110.1214/aos/1013203451 ↗
52. 10.1016/j.asoc.2019.03.01710.1016/j.asoc.2019.03.017 ↗
53. Chen T Guestrin C. Xgboost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining San Francisco CA 13–17 August 2016 pp. 785–794.10.1145/2939672.2939785 ↗
54. Ke G, Meng Q, Finley T, et al. Lightgbm: a highly efficient gradient boosting decision tree. Adv Neural Inf Process Syst. 2017; 30.
55. Snoek J, Larochelle H, Adams RP. Practical bayesian optimization of machine learning algorithms. Adv Neural Inf Process Syst. 2012; 25: 2951–2959.
56. Wu J, Chen XY, Zhang H et al. Hyperparameter optimization for machine learning models based on Bayesian optimization. Journal of Electronic Science and Technology 2019; 17(1): 26–40.
57. Van der Maaten L, Hinton G. Visualizing data using t-SNE. J Mach Learn Res 2008; 9(11): 2579.