Paper Titles
Graph Neural Network for Draw-in Prediction in Sheet Metal Stamping
p.137
A Bayesian Data Assimilation Framework for Characterizing Recrystallization in Steels
p.145
Predicting Lateral Flow in Hot Sheet Metal Rolling Using Symbolic Regression
p.157
Physics-Informed Recurrent Neural Networks with Kinematic Constraints for Large Deformation Metal Forming
p.171
An Ai-Based Approach to Developing a Microstructural Model for Multi-Stage Hot Deformation Processes
p.183
Accelerating Microstructural Evolution Simulations in DIGIMU® through a Front-Tracking Lagrangian Solver: Implementation and Validation in AISI 304L Stainless Steel
p.193
Study on the Apparent Friction Coefficient between a Deformable and a Rough Rigid Body under Large Sliding
p.205
Using Kolmogorov-Arnold Networks for Discrepancy Modeling of Lateral Flow in Hot Rolling of Steel Slabs
p.215
Modelling Deformation Mechanisms Decomposition, Separation and Compaction in Mechanical Joining Processes of Fiber Reinforced Thermoplastics on Meso Scale
p.227

An Ai-Based Approach to Developing a Microstructural Model for Multi-Stage Hot Deformation Processes

Article Preview
View Pdf By email

Abstract:

Predicting the microstructural state during manufacturing is critical, as it directly governs the material's final mechanical properties. Accurate prediction of microstructure evolution in multi-stage industrial hot deformation processes, such as rolling, is limited by the lack of experimental data at intermediate stages, where direct measurement is impractical. To address this, an integrated methodology combining finite element (FE) simulation in QForm UK® software, physical simulation using the Thermo-Mechanical Treatment Simulator (TMTS), and artificial intelligence (AI) is proposed and investigated. The methodology is demonstrated for the 11-pass hot rolling of a 41Cr4 steel bar. Thermomechanical loading histories from an FE model of the industrial process were used to design and simulate a targeted TMTS experiment, generating a synthetic dataset via an analytical JMAK model that combines multiple recrystallisation mechanisms. This data was used to train a recurrent neural network (RNN) with an augmented physics-informed Long Short-Term Memory (LSTM) cell to predict the totally recrystallised fraction (RX) solely from loading history data. The AI model achieved high accuracy when validated within the TMTS simulation domain, successfully capturing different recrystallisation regimes. Implementation within commercial FE software enabled direct prediction in the rolling process simulation, yielding promising predictive capability, particularly in regions with thermal histories similar to the training data, highlighting the critical importance of training data diversity. This work establishes a proof of concept for a novel calibration methodology, where targeted physical simulation bridges the gap between industrial process complexity and data-driven AI model development, offering a practical solution for modelling scenarios where traditional experimental calibration is infeasible.

You have full access to the following eBook
Advanced Numerical and AI Strategies for Material Forming Read eBook

Info:

Periodical:

Key Engineering Materials (Volume 1050)

Pages:

183-192

DOI:

https://doi.org/10.4028/p-dWx8G5

Citation:

Cite this paper

Online since:

April 2026

Authors:

Denis Tretyakov, Nikolay Biba*, Vitaliy Belugin, Artur Gartvig, Andrei Shitikov, Sergei Stebunov

Keywords:

AI Models, Deep Learning, FEM, Forging, Metals, Microstructure, Recrystallization

Export:

RIS, BibTeX

Permissions:

Creative Commons CC BY 4.0

Share:

Citation:

* - Corresponding Author

References

[1] Reshetov, A. and Bylya, O., 2023, April. Benchmarking mean-field models available in commercial FE software in application to two-blow forging of IN718 alloy. Materials Research Forum LLC.

DOI: 10.21741/9781644902479-74

Google Scholar

[2] Bylya, O., Reshetov, A., Stefani, N., Rosochowska, M. and Blackwell, P., 2017. Applicability of JMAK-type model for predicting microstructural evolution in nickel-based superalloys. Procedia engineering, 207, pp.1105-1110.

DOI: 10.1016/j.proeng.2017.10.1067

Google Scholar

[3] Stebunov, S., Biba, N., Vlasov, A., et al, 2023. Integration of automated roll pass design and simulation for the development of shape rolling technology. Materials Research Proceedings, 32, p.655–662.

DOI: 10.21741/9781644903254-81

Google Scholar

[4] Gers, F., 2001. Long short-term memory in recurrent neural networks, Doctoral dissertation, Verlag nicht ermittelbar.

Google Scholar

[5] Tretyakov, D., Bylya, O., Shitikov, A., Gartvig, A., Stebunov, S. and Biba N., 2024. The prospects of implementation of artificial intelligence for modelling of microstructural parameters in metal forming processes. Materials Research Proceedings, 41, pp.2164-2173.

DOI: 10.21741/9781644903131-238

Google Scholar

[6] Gupta, N.K., 2021. Steel Rolling: Principle, Process & Application, London, UK.

Google Scholar

[7] Kim, J., Moon, Y.H., Kim, N.J. Multi-Scale Modeling of Microstructure Evolution during Multi-Pass Hot-Rolling and Cooling Process. Materials 2021, 14(11), p.2947.

DOI: 10.3390/ma14112947

Google Scholar

[8] Müller, C.-E. Application of Damage Models on Long Product Rolling Simulations in QForm UK. Presented at MEFORM 2025, Freiberg, Germany.

Google Scholar

[9] Timothy, S.P., Yiu, H.L., Fine, J.M. and Ricks, R.A., 1991. Simulation of single pass of hot rolling deformation of aluminium alloy by plane strain compression. Materials science and technology, 7(3), pp.255-263.

DOI: 10.1179/mst.1991.7.3.255

Google Scholar

[10] Johnson, W., Mehl, R., 1939. Reaction kinetics in process of nucleation and growth. Transactions of Transactions of the American Institute of Mining and Metallurgical Engineers, 135, pp.416-458.

Google Scholar

[11] Micas Simulation LTD, "QForm UK version 11, The software documentation: Description of Microstructure evolution model", 2023.

Google Scholar

[12] Stefani, N., Bylya, O., Reshetov, A. and Blackwell, P., 2017. On the applicability of JMAK-type models in predicting IN718 microstructural evolution. Computer Methods in Materials Science, 17(1), pp.59-68.

DOI: 10.7494/cmms.2017.1.0576

Google Scholar