An analytical predictor machine learning corrector scheme for modeling lateral flow in hot strip rolling
Research output: Contributions to collected editions/works › Article in conference proceedings › Research › peer-review
Standard
Material Forming, ESAFORM 2025: The 28th International ESAFORM Conference on Material Forming – ESAFORM 2025 – held in Paestum (Italy), 7-9 May, 2025. ed. / Pierpaolo Carlone; Luigino Filice; Domenico Umbrello. Millersville: MaterialsResearchForum LLC, 2025. p. 2002-2011 (Materials Research Proceedings; Vol. 54).
Research output: Contributions to collected editions/works › Article in conference proceedings › Research › peer-review
Harvard
APA
Vancouver
Bibtex
}
RIS
TY - CHAP
T1 - An analytical predictor machine learning corrector scheme for modeling lateral flow in hot strip rolling
AU - Hashemzadeh, Amirali
AU - Bock, Frederic E.
AU - Hol, Camile
AU - Schutte, Koen
AU - Cometa, Antonella
AU - Soyarslan, Celal
AU - Klusemann, Benjamin
AU - Van Den Boogaard, Ton
N1 - Conference code: 28
PY - 2025
Y1 - 2025
N2 - Rolling is a metal forming process where slabs are passed through rollers to produce strips with specific dimensions and mechanical properties. This process is performed in hot or cold formats. In hot rolling, the workpiece is initially heated above its recrystallization temperature. During the hot rolling process, plastic deformation occurs as the material’s thickness decreases and elongation takes place along the longitudinal axis of the workpiece. Due to the incompressibility of plastic deformation, the material also expands in the transverse direction, a phenomenon known as spread or lateral flow. Modeling spread is crucial for sustainability considerations and meeting customer expectations regarding the quality of the final product. Current prediction methodologies, such as the accurate but slow Finite Element (FE) method or the fast but inaccurate analytical metal forming analysis, are impractical for optimal control. To tackle these challenges, hybrid frameworks have emerged as a promising alternative. The present work aims to develop a fast and accurate model for predicting spread in hot rolling. Specifically, machine learning improves analytical models by leveraging data from a high-fidelity FE model. Initially, we review analytical models for spread, which address key aspects of the problem’s physics. To generate the ground truth (GT) space, an automated FE model for hot strip rolling is created. Moreover, the model’s sensitivity to both process and material parameters is investigated. In the Analytical Predictor Machine Learning Corrector scheme, the analytical models generate initial predictions of GT. In the correction step, a data-driven machine learning model is used to refine these predictions by compensating for deviations from high-fidelity FE simulations. The proposed hybrid framework improves the accuracy of the existing analytical models while preserving their computational efficiency.
AB - Rolling is a metal forming process where slabs are passed through rollers to produce strips with specific dimensions and mechanical properties. This process is performed in hot or cold formats. In hot rolling, the workpiece is initially heated above its recrystallization temperature. During the hot rolling process, plastic deformation occurs as the material’s thickness decreases and elongation takes place along the longitudinal axis of the workpiece. Due to the incompressibility of plastic deformation, the material also expands in the transverse direction, a phenomenon known as spread or lateral flow. Modeling spread is crucial for sustainability considerations and meeting customer expectations regarding the quality of the final product. Current prediction methodologies, such as the accurate but slow Finite Element (FE) method or the fast but inaccurate analytical metal forming analysis, are impractical for optimal control. To tackle these challenges, hybrid frameworks have emerged as a promising alternative. The present work aims to develop a fast and accurate model for predicting spread in hot rolling. Specifically, machine learning improves analytical models by leveraging data from a high-fidelity FE model. Initially, we review analytical models for spread, which address key aspects of the problem’s physics. To generate the ground truth (GT) space, an automated FE model for hot strip rolling is created. Moreover, the model’s sensitivity to both process and material parameters is investigated. In the Analytical Predictor Machine Learning Corrector scheme, the analytical models generate initial predictions of GT. In the correction step, a data-driven machine learning model is used to refine these predictions by compensating for deviations from high-fidelity FE simulations. The proposed hybrid framework improves the accuracy of the existing analytical models while preserving their computational efficiency.
KW - Finite Element Model
KW - Hot rolling
KW - Machine Learning
KW - Predictor-corrector Modeling
KW - Engineering
UR - http://www.scopus.com/inward/record.url?scp=105008073113&partnerID=8YFLogxK
U2 - 10.21741/9781644903599-215
DO - 10.21741/9781644903599-215
M3 - Article in conference proceedings
AN - SCOPUS:105008073113
T3 - Materials Research Proceedings
SP - 2002
EP - 2011
BT - Material Forming, ESAFORM 2025
A2 - Carlone, Pierpaolo
A2 - Filice, Luigino
A2 - Umbrello, Domenico
PB - MaterialsResearchForum LLC
CY - Millersville
T2 - 28th International ESAFORM Conference on Material Forming - ESAFORM 2025
Y2 - 7 May 2025 through 9 May 2025
ER -