Towards hybrid modelling of aluminium extrusion mechanical properties – A univariate representation of artificial aging
Christian Dalheim Øien, Ole Runar Myhr, Geir Ringen
Abstract. Hybrid modelling of mechanical properties in age-hardened aluminium extrusions presents challenges in numerically representing artificial aging. This study investigates a diffusion-based synthetic feature, the Scheil integral, to assess its effectiveness in capturing temperature history for model training and inference. A comprehensive dataset of mechanical properties from Al-Mg-Si (6xxx) extrusions was analysed, and machine learning models were trained using both the full aging cycle representation and the Scheil integral as a single aging descriptor. Results demonstrate that this approach significantly reduces input dimensionality, simplifying the aging process representation from nine variables to one, with minimal loss in predictive accuracy. This finding supports the use of the Scheil integral for efficient model training and process similarity assessments in hybrid modelling.
Keywords
Aluminium Extrusion, Hybrid Modelling, Precipitation Kinetics
Published online 5/7/2025, 10 pages
Copyright © 2025 by the author(s)
Published under license by Materials Research Forum LLC., Millersville PA, USA
Citation: Christian Dalheim Øien, Ole Runar Myhr, Geir Ringen, Towards hybrid modelling of aluminium extrusion mechanical properties – A univariate representation of artificial aging, Materials Research Proceedings, Vol. 54, pp 819-828, 2025
DOI: https://doi.org/10.21741/9781644903599-88
The article was published as article 88 of the book Material Forming
Content from this work may be used under the terms of the Creative Commons Attribution 3.0 license. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.
References
[1] D. Raabe, D. Ponge, P. J. Uggowitzer, M. Roscher, M. Paolantonio, C. Liu, H. Antrekowitsch, E. Kozeschnik, D. Seidmann, B. Gault, F. De Geuser, A. Deschamps, C. Hutchinson, C. Liu, Z. Li, P. Prangnell, J. Robson, P. Shanthraj, S. Vakili, C. Sinclair, L. Bourgeois, S. Pogatscher, Making sustainable aluminum by recycling scrap: The science of “dirty” alloys, Progress in Materials Science, vol. 128, 2022, https://doi.org/10.1016/j.pmatsci.2022.100947
[2] C. D. Øien, G. Ringen, Data-driven through-process modelling of aluminum extrusion: Predicting mechanical properties, Manufacturing Letters, vol. 41, 2024, https://doi.org/10.1016/j.mfglet.2024.09.154
[3] O. R. Myhr, Ø. Grong and S. J. Andersen: Modelling of the age hardening behaviour of Al-Mg-Si alloys. Acta Mater. Vol. 49, Jan. 2001, pp. 65-75. https://doi.org/10.1016/S1359-6454(00)00301-3
[4] O. R. Myhr, Ø. Grong, and K. O. Pedersen: A Combined Precipitation, Yield Strength and Work Hardening Model for Al-Mg-Si Alloys. Metall. Mater. Trans A, Vol. 41A, No. 9, 2010, pp. 2276-2289. https://doi.org/10.1007/s11661-010-0258-7
[5] O. R. Myhr, Ø. Grong and C. Schäfer: An Extended Age-Hardening Model for Al-Mg-Si Alloys Incorporating the Room-Temperature Storage and Cold Deformation Process Stages. Metall. Mater. Trans A, Vol. 46A, 2015, pp. 6018-6039. https://doi.org/10.1007/s11661-015-3175-y
[6] S. J. Andersen, H. W. Zandbergen, J. Jansen, C. Træholt, U. Tundal, O. Reiso,
The crystal structure of the β″ phase in Al–Mg–Si alloys, Acta Materialia, Volume 46, Issue 9, 1998, pp. 3283-3298, ISSN 1359-6454, https://doi.org/10.1016/S1359-6454(97)00493-X.
[7] A.K. Gupta, D.J. Lloyd, S.A. Court, Precipitation hardening in Al–Mg–Si alloys with and without excess Si, Materials Science and Engineering: A, Volume 316, Issues 1–2,
2001, Pages 11-17, ISSN 0921-5093. https://doi.org/10.1016/S0921-5093(01)01247-3.
[8] S. J. Andersen, C. D. Marioara, R. Vissers, A. Frøseth, H. W. Zandbergen, The structural relation between precipitates in Al–Mg–Si alloys, the Al-matrix and diamond silicon, with emphasis on the trigonal phase U1-MgAl2Si2, Materials Science and Engineering: A, Volume 444, Issues 1–2, 2007, Pages 157-169, ISSN 0921-5093. https://doi.org/10.1016/j.msea.2006.08.084.
[9] R. Holmestad, C. D. Marioara, F. J. H. Ehlers, M. Torsæter, R. Bjørge, J. Røyset, S. J. Andersen, Precipitation in 6xxx Aluminum Alloys, Proceedings of the 12th International Conference on Aluminium Alloys, 2010, pp. 30-39. ISBN: 978-4-905829-11-9
[10] S. Spigarelli and C. Paoletti (2017). A Unified Physical Model for Creep and Hot Working of Al-Mg Solid Solution Alloys. Metals. 8. 9. 10.3390/met8010009. http://dx.doi.org/10.3390/met8010009
[11] J.W. Christian, The Theory of Transformations in Metals and Alloys, Ch. 12 Formal Theory of Transformation Kinetics, Pergamon, 2002, ISBN 9780080440194. https://doi.org/10.1016/B978-008044019-4/50005-2
[12] E. Scheil, Anlaufzeit der Austenitumwandlung, Archiv für das Eisenhüttenwesen, vol. 8, issue 12, 1935, pp. 565-567. https://doi.org/10.1002/srin.193500186
[13] O. R. Myhr and Ø. Grong, Process modelling applied to 6082-T6 aluminium weldments—I. Reaction kinetics, In: Acta Metallurgica et Materialia, Volume 39, Issue 11, 1991, pp. 2693-2702.https://doi.org/10.1016/0956-7151(91)90086-G.
[14] T. Chen and C. Guestrin. XGBoost: A Scalable Tree Boosting System. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD ’16), 2016. https://doi.org/10.1145/2939672.2939785
[15] C. Bentéjac, A. Csörgő, G. Martínez-Muñoz. A Comparative Analysis of XGBoost. In: Artificial Intelligence Review, vol. 54, 2019. http://dx.doi.org/10.1007/s10462-020-09896-5
[16] O. R. Myhr, O. S. Hopperstad, and T. Børvik, A Combined Precipitation, Yield Stress, and Work Hardening Model for Al-Mg-Si Alloys Incorporating the Effects of Strain Rate and Temperature, Metallurgical and Materials Transactions, 2018, Volume 49, pages 3592–3609. http://dx.doi.org/10.1007/s11661-018-4675-3
