Industry 4.0
Vol. 11 (2026), Issue 1, pg(s) 12-14

DOMINANT TECHNOLOGIES IN “INDUSTRY 4.0”

Machine Learning Prediction of Mechanical Properties for Al-Mg-Si Alloys Using a Hybrid Data Synthesis Approach

  • 1 Institute of Metal Science, Equipment and Technologies with Hydro- and Aerodynamics Centre ―Acad. A. Balevski‖, Bulgarian Academy of Sciences, Sofia, 1574, 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

Abstract

This study develops a machine learning framework for predicting the mechanical properties of 6xxx series Al-Mg-Si alloys (6061, 6063, 6082) across seven temper conditions. A hybrid dataset of 860 real measurement-based and 4,200 Monte Carlo augmented samples was generated from a literature-mined dataset. Random Forest (RF), Gradient Boosting (GBR), and Multilayer Perceptron (MLP) models were evaluated via 5-fold cross-validation (CV). RF achieved the best or comparable accuracy: coefficient of determination R² = 0.80 (ultimate tensile strength), 0.92 (yield strength), and 0.83 (elongation). Feature importance analysis showed that alloy type and temper encodings dominated predictions (>90% combined), while individual compositional features contributed <3% a result partly attributable to the augmentation strategy, which decoupled measured compositions from their corresponding property values. Learning curve analysis confirmed model convergence above 2,000 samples.

References

  1. Chauhan, K.P.S.; FUTURE INSTITUTE OF ENGINEERING AND TECHNOLOGY, BAREILLY (U.P.) Influence of Heat Treatment on the Mechanical Properties of Aluminium Alloys (6xxx Series): A Literature Review. Int. J. Eng. Res. Technol. (Ahmedabad) 2017, V6, doi:10.17577/ijertv6is030301.
  2. Gao, Y.-H.; Zhang, X.-X.; Zhou, J.-Z.; Xu, P.; Xin, Z.-J.; Gao, J.-H.; Shi, Y.-H.; Lü, Y.; Zhao, Y.-F.; Li, J.-Y. Engineering Heterogeneous Microstructures for Enhanced Strength and Ductility in Air-Cooled Al−Mg−Si Alloys. Trans. Nonferrous Met. Soc. China 2025, 35, 1017–1031, doi:10.1016/s1003-6326(24)66731-2.
  3. Hagen, A.B.; Wenner, S.; Bjørge, R.; Wan, D.; Marioara, C.; Holmestad, R.; Ringdalen, I.G. Local Mechanical Properties and Precipitation Inhomogeneity in Large-Grained Al-Mg-Si Alloys. SSRN Electron. J. 2022, doi:10.2139/ssrn.4216356.
  4. Effect of Copper/Alumina Hybrid Reinforcement on the Microstructure and Mechanical Properties of Stir Cast Aluminum Alloy AA6063;
  5. Wang, H.; Zheng, H.; Hu, M.; Ma, Z.; Liu, H. Synergistic Effect of Al2O3-Decorated Reduced Graphene Oxide on Microstructure and Mechanical Properties of 6061 Aluminium Alloy. Sci. Rep. 2024, 14, 16213, doi:10.1038/s41598-024-67004-x.
  6. Jiang, W.; Zhu, J.; Li, G.; Guan, F.; Yu, Y.; Fan, Z. Enhanced Mechanical Properties of 6082 Aluminum Alloy via SiC Addition Combined with Squeeze Casting. J. Mater. Sci. Technol. 2021, 88, 119–131, doi:10.1016/j.jmst.2021.01.077.
  7. Qian, X.; Parson, N.; Chen, X.-G. Effect of Post- Homogenisation Cooling Rate and Mn Addition on Mg2Si Precipitation and Hot Workability of AA6060 Alloys. Can. Metall. Q. 2020, 59, 189–200, doi:10.1080/00084433.2020.1719332.
  8. 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.
  9. Li, J.; Zhang, Y.; Cao, X.; Zeng, Q.; Zhuang, Y.; Qian, X.; Chen, H. Accelerated Discovery of High-Strength Aluminum Alloys by Machine Learning. Commun. Mater. 2020, 1, doi:10.1038/s43246-020-00074-2.
  10. 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.
  11. 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.
  12. Silva, M.S.; Barbosa, C.; Acselrad, O.; Pereira, L.C. Effect of Chemical Composition Variation on Microstructure and Mechanical Properties of a 6060 Aluminum Alloy. J. Mater. Eng. Perform. 2004, 13, 129–134, doi:10.1361/10599490418307.
  13. Trindade, W.G.; Padovezzi, R.O.; Pinto, E.P.G.; Marques, G.A.; Amorese, R.A.; Silva, M.C.; Damasio, T.S.; Andrade, G.O. de; Luca, R. de; Nascimento, P.H.T. do Influence of Alloying Elements on the Mechanical Properties and Electrical Conductivity of 6000 Series Aluminum Alloy. A Review. CONTRIBUCIONES A LAS CIENCIAS SOCIALES 2025, 18, e18763, doi:10.55905/revconv.18n.6-193.

Article full text

Download PDF