Paper Titles
Redesign of Low-Activation Vanadium Alloys Based on Impurity Control for Fusion Reactor Applications
p.21
CALPHAD-Based Modelling of Microstructural Evolution during D.C. Casting and Homogenization of AA3003 Aluminium Alloy
p.35
Atomistic Investigation of Stability and Segregation of Alphagenic and Betagenic Solutes in Hexagonal Titanium
p.43
Simulation-Driven Insights into Heat Transfer during Copper Mold Casting of Magnesium-Based Bulk Metallic Glasses
p.51
Verification of a Novel Mathematical Model for Determination of the Biomass Specific Growth Rate in Bioprocesses Using Relative Change in Biomass Measurements
p.57
Numerical Investigation of the Influence of Residual Stresses after Additive Manufacturing on the Fatigue Crack Propagation in 5xxx Aluminum Alloys
p.63
Application of Artificial Neural Networks for Microstructure Models ALFLOW and ALSOFT
p.71
Sintering Process Analysis of Aluminum Matrix Composites Using Machine Learning
p.77
Testing Theories and Simulations on Phase Coarsening by Experiments
p.83

Application of Artificial Neural Networks for Microstructure Models ALFLOW and ALSOFT

Article Preview

Abstract:

In the present work artificial neural networks (ANN) models have been implemented and trained as surrogate models to replicate two physics-based microstructure models for Al-alloys, i.e. the ALFLOW model, which predicts the sub-structure evolution and associated flow stress during plastic deformation and the softening model ALSOFT, which predicts the softening behavior after hot/cold deformation, in view of the combined effect of recovery and recrystallization. Input for both ANN models was limited to variables such as strain, strain rate, time, temperature and solute concentration, and the flow stress as the output. Accuracy and efficiency were tested for different ANN architectures. It is demonstrated that fully connected feed-forward neural network architectures with ∼3 hidden layers are suitable as surrogate models for both ALFLOW and ALSOFT, with a potential speed-up of ∼100x for ALFLOW and ∼10x for ALSOFT.

You might also be interested in these eBooks
Computational Materials Science and Materials Informatics View Preview

Info:

Periodical:

Defect and Diffusion Forum (Volume 446)

Pages:

71-76

DOI:

https://doi.org/10.4028/p-rzJlE7

Citation:

Cite this paper

Online since:

January 2026

Authors:

Daniel Aron Premiger, Knut Marthinsen*, Tomáš Mánik

Keywords:

Aluminium Alloy, Machine Learning, Mechanical Properties, Microstructure Modelling, Neural Networks, Recovery, Recrystallization, Sub-Structure Evolution

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

© 2026 Trans Tech Publications Ltd. All Rights Reserved

Share:

Citation:

* - Corresponding Author

References

[1] E. Nes, Modelling of work hardening and stress saturation in FCC metals, Prog. Mater Sci., 41 (1997) 129-193.

DOI: 10.1016/s0079-6425(97)00032-7

Google Scholar

[2] E. Nes, K. Marthinsen and B. Rønning, Modelling the evolution in microstructure and properties during processing of aluminium alloys, J. Mater. Process. Technol., 117 (2001) 333-340.

DOI: 10.1016/s0924-0136(01)00791-9

Google Scholar

[3] E. Nes and K. Marthinsen, Modeling the evolution in microstructure and properties during plastic deformation of f.c.c.-metals and alloys – an approach towards a unified model, Mater. Sci. Eng., A, 322 (2002) 176-193.

DOI: 10.1016/s0921-5093(01)01130-3

Google Scholar

[4] K. Marthinsen and E. Nes, Modelling strain hardening and steady state deformation of Al–Mg alloys, Mater. Sci. Technol., 17 (2001) 376-388.

DOI: 10.1179/026708301101510096

Google Scholar

[5] H.E. Vatne, T. Furu, R. Ørsund and E. Nes, Modelling recrystallization after hot deformation of aluminium, Acta Mater., 44 (1996) 4463-4473.

DOI: 10.1016/1359-6454(96)00078-x

Google Scholar

[6] H. Vatne, R. Ørsund, K. Marthinsen and E. Nes, Modeling recrystallization kinetics, grain sizes, and textures during multipass hot rolling, Metall and Mat Trans A, 27 (1996) 4133-4144.

DOI: 10.1007/bf02595661

Google Scholar

[7] J.A. Sæter JA, B. Forbord, H.E. Vatne, E. Nes. In: Sato T, Kumai S, Kobayashi T, Murakami Y, editors. Proc. ICAA 6, vol. 1. Tokyo: The Japan Inst. Light Metals; 1998. p.113.

Google Scholar

[8] L. Vu-Quoc and A. Humer. Deep learning applied to computational mechanics: A comprehensive review, state of the art, and the classics. Computer Modeling in Engineering & Sciences, 137(2) (2023) 1069–1343.

DOI: 10.32604/cmes.2023.028130

Google Scholar

[9] D.P. Kingma, and J.L. Ba, Adam: A Method for Stochastic Optimization. arXiv:1412.6980v9

Google Scholar