Machines. Technologies. Materials.
Vol. 20 (2026), Issue 3, pg(s) 111-113

TECHNOLOGIES

Machine Learning Prediction of Mechanical Properties for Al-Cu Alloys Using Monte Carlo Data Augmentation

  • 1 Institute of Metal Science, Equipment and Technologies with Hydro- and Aerodynamics Centre “Acad. A. Balevski”, Bulgarian Academy of Sciences, Sofia, 1574, Bulgaria; National Center for Mechatronics and Clean Technologies, 8 “Kliment Ohridski” Blvd., Building 8, 1756 Sofia, Bulgaria
  • 2 Institute of Metal Science, Equipment and Technologies with Hydro- and Aerodynamics Centre “Acad. A. Balevski”, Bulgarian Academy of Sciences, Sofia, 1574, Bulgaria; Institute of Mechanics, Bulgarian Academy of Sciences, Sofia, 1113, Bulgaria; National Center for Mechatronics and Clean Technologies, 8 “Kliment Ohridski” Blvd., Building 8, 1756 Sofia, Bulgaria
  • 3 Department of Inorganic Chemistry, Faculty of Chemistry and Pharmacy, Sofia University “St. Kliment Ohridski”, Sofia, Bulgaria
  • 4 University of Chemical Technology and Metallurgy Sofia, Bulgaria

Abstract

This study presents a machine learning framework for predicting the mechanical properties of 2xxx series Al-Cu alloys (2024, 2219, 2524) across 11 temper conditions. Monte Carlo augmentation generated 8,800 synthetic samples from compositional specification ranges of a literature-mined dataset. Three regression models, Random Forest, Gradient Boosting, and SVR-RBF were evaluated via 5-fold cross-validation (CV) to predict ultimate tensile strength (UTS), yield strength (YS), and elongation. All models achieved coefficient of determination R² > 0.991, with Mean Absolute Error MAE ≤ 7.4 MPa for UTS, ≤ 5.4 MPa for YS, and ≤ 0.51% for elongation. Feature importance analysis revealed that temper condition encoding dominated predictions (>75% importance), while individual compositional features contributed <5% each. The high predictive accuracy reflects the effectiveness of the augmentation scheme in capturing withingroup property–composition–temper relationships, though generalization to unseen alloy–temper conditions remains to be validated. The results illustrate the potential of combining corpus-mined data with Monte Carlo augmentation for rapid alloy property screening.

Keywords

References

  1. Li, S.-S.; Yue, X.; Li, Q.-Y.; Peng, H.-L.; Dong, B.-X.; Liu, T.-S.; Yang, H.-Y.; Fan, J.; Shu, S.-L.; Qiu, F.; et al. Development and Applications of Aluminum Alloys for Aerospace Industry. J. Mater. Res. Technol. 2023, 27, 944–983, doi:10.1016/j.jmrt.2023.09.274.
  2. García-Aguirre, K.A.; Holguín-Momaca, J.T.; Ruiz- Esparza-Rodriguez, M.A.; Guía-Tello, J.C.; Garay-Reyes, C.G.; Estrada-Guel, I.; Martínez-Sánchez, R. Microstructural Evolution and Strengthening Mechanisms in a 2xxx Series Modified Al Alloy. Microsc. Microanal. 2022, 28, 2854–2856, doi:10.1017/s1431927622010753.
  3. Elkatatny, S.; Alsharekh, M.F.; Alateyah, A.I.; El- Sanabary, S.; Nassef, A.; Kamel, M.; Alawad, M.O.; BaQais, A.; El-Garaihy, W.H.; Kouta, H. Optimizing the Powder Metallurgy Parameters to Enhance the Mechanical Properties of Al- 4Cu/XAl2O3 Composites Using Machine Learning and Response Surface Approaches. Appl. Sci. (Basel) 2023, 13, 7483, doi:10.3390/app13137483.
  4. Hu, H.; Zhao, F.; Yong, W.; Jiang, L.; Zhang, Z.; Xie, J. A Machine Learning Strategy to Achieve Dual-Synchronous Property Improvement of Aviation Al-Cu-Mg Alloy. J. Mater. Sci. Technol. 2026, 244, 208–230, doi:10.1016/j.jmst.2025.04.036.
  5. Fu, C.; Lin, X.; Huang, H.; Yue, C.; Zuo, X.; Zheng, B.; Du, K.; Zheng, W. Synergistic Enhancement of Strength and Plasticity in Al-Cu Alloys Using Interpretable Machine Learning Algorithms. Mater. Sci. Eng. A Struct. Mater. 2025, 942, 148702, doi:10.1016/j.msea.2025.148702.
  6. Shawon, A.R.; Ghosh, R.; Islam, M.A. Analysis of Thermal Conductivity of Aluminum Alloys by Compositions and Tempering Process Using Machine Learning. Sci. Rep. 2025, 15, 33352, doi:10.1038/s41598-025-15868-y.
  7. J. Soofi, Y.; Rahman, M.A.; Gu, Y.; Liu, J. A Feasibility Study of Machine Learning-Assisted Alloy Design Using Wrought Aluminum Alloys as an Example. Comput. Mater. Sci. 2022, 215, 111783, doi:10.1016/j.commatsci.2022.111783.
  8. Park, J.; Yoon, H.-K. Methodology for Generating Diverse Geotechnical Datasets Using Monte Carlo Simulation and Genetic Algorithms. Comput.-aided Civ. Infrastruct. Eng. 2025, 40, 5494–5511, doi:10.1111/mice.70106.
  9. Pfeiffer, O.P.; Liu, H.; Montanelli, L.; Latypov, M.I.; Sen, F.G.; Hegadekatte, V.; Olivetti, E.A.; Homer, E.R. Aluminum Alloy Compositions and Properties Extracted from a Corpus of Scientific Manuscripts and US Patents 2021.
  10. Zhou, Y.; Lin, X.; Kang, N.; Huang, W.; Wang, Z. Mechanical Properties and Precipitation Behavior of the Heat- Treated Wire + Arc Additively Manufactured 2219 Aluminum Alloy. Mater. Charact. 2021, 171, 110735, doi:10.1016/j.matchar.2020.110735.
  11. Zhang, L.; Huang, G.; Wang, L.; Lu, G.; Guan, S. Microstructure-Strengthening Correlation of 2219 Al Alloy Subjected to Ultrasonic Melt Treatment, Hot Rolling and Heat Treatment. J. Mater. Res. Technol. 2023, 27, 7470–7481, doi:10.1016/j.jmrt.2023.11.167.

Article full text

Download PDF