An analytical predictor machine learning corrector scheme for modeling lateral flow in hot strip rolling

Publikation: Beiträge in SammelwerkenAufsätze in KonferenzbändenForschungbegutachtet

Standard

An analytical predictor machine learning corrector scheme for modeling lateral flow in hot strip rolling. / Hashemzadeh, Amirali; Bock, Frederic E.; Hol, Camile et al.
Material Forming, ESAFORM 2025: The 28th International ESAFORM Conference on Material Forming – ESAFORM 2025 – held in Paestum (Italy), 7-9 May, 2025. Hrsg. / Pierpaolo Carlone; Luigino Filice; Domenico Umbrello. Millersville: MaterialsResearchForum LLC, 2025. S. 2002-2011 (Materials Research Proceedings; Band 54).

Publikation: Beiträge in SammelwerkenAufsätze in KonferenzbändenForschungbegutachtet

Harvard

Hashemzadeh, A, Bock, FE, Hol, C, Schutte, K, Cometa, A, Soyarslan, C, Klusemann, B & Van Den Boogaard, T 2025, An analytical predictor machine learning corrector scheme for modeling lateral flow in hot strip rolling. in P Carlone, L Filice & D Umbrello (Hrsg.), Material Forming, ESAFORM 2025: The 28th International ESAFORM Conference on Material Forming – ESAFORM 2025 – held in Paestum (Italy), 7-9 May, 2025. Materials Research Proceedings, Bd. 54, MaterialsResearchForum LLC, Millersville, S. 2002-2011, 28th International ESAFORM Conference on Material Forming - ESAFORM 2025, Paestum, Italien, 07.05.25. https://doi.org/10.21741/9781644903599-215

APA

Hashemzadeh, A., Bock, F. E., Hol, C., Schutte, K., Cometa, A., Soyarslan, C., Klusemann, B., & Van Den Boogaard, T. (2025). An analytical predictor machine learning corrector scheme for modeling lateral flow in hot strip rolling. In P. Carlone, L. Filice, & D. Umbrello (Hrsg.), Material Forming, ESAFORM 2025: The 28th International ESAFORM Conference on Material Forming – ESAFORM 2025 – held in Paestum (Italy), 7-9 May, 2025 (S. 2002-2011). (Materials Research Proceedings; Band 54). MaterialsResearchForum LLC. https://doi.org/10.21741/9781644903599-215

Vancouver

Hashemzadeh A, Bock FE, Hol C, Schutte K, Cometa A, Soyarslan C et al. An analytical predictor machine learning corrector scheme for modeling lateral flow in hot strip rolling. in Carlone P, Filice L, Umbrello D, Hrsg., Material Forming, ESAFORM 2025: The 28th International ESAFORM Conference on Material Forming – ESAFORM 2025 – held in Paestum (Italy), 7-9 May, 2025. Millersville: MaterialsResearchForum LLC. 2025. S. 2002-2011. (Materials Research Proceedings). doi: 10.21741/9781644903599-215

Bibtex

@inbook{c49c089fcdf5495c846b726264ce1040,
title = "An analytical predictor machine learning corrector scheme for modeling lateral flow in hot strip rolling",
abstract = "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{\textquoteright}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{\textquoteright}s physics. To generate the ground truth (GT) space, an automated FE model for hot strip rolling is created. Moreover, the model{\textquoteright}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.",
keywords = "Finite Element Model, Hot rolling, Machine Learning, Predictor-corrector Modeling, Engineering",
author = "Amirali Hashemzadeh and Bock, {Frederic E.} and Camile Hol and Koen Schutte and Antonella Cometa and Celal Soyarslan and Benjamin Klusemann and {Van Den Boogaard}, Ton",
note = "Copyright {\textcopyright} 2025 by authors; 28th International ESAFORM Conference on Material Forming - ESAFORM 2025, ESAFORM 2025 ; Conference date: 07-05-2025 Through 09-05-2025",
year = "2025",
doi = "10.21741/9781644903599-215",
language = "English",
series = "Materials Research Proceedings",
publisher = "MaterialsResearchForum LLC",
pages = "2002--2011",
editor = "Pierpaolo Carlone and Luigino Filice and Domenico Umbrello",
booktitle = "Material Forming, ESAFORM 2025",
address = "United States",

}

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 -

DOI

Zuletzt angesehen

Publikationen

  1. The interplay between posture control and memory for spatial locations
  2. Do Specific Text Features Influence Click Probabilities in Paid Search Advertising?
  3. Interactive Media as Fields of Transduction
  4. Plant density modifies root system architecture in spring barley (Hordeum vulgare L.) through a change in nodal root number
  5. Development of an Active Aging Index for the Organizational Level
  6. Applying the Three Horizons approach in local and regional scenarios to support policy coherence in SDG implementation
  7. Digital twin support for laser-based assembly assistance
  8. "Doing" Sustainability Assessment in Different Consumption and Production Contexts-Lessons from Case Study Comparison
  9. Performance of process-based models for simulation of grain N in crop rotations across Europe
  10. Grazing effects on intraspecific trait variability vary with changing precipitation patterns in Mongolian rangelands
  11. A piezo servo hydraulic actuator for use in camless combustion engines and its control with MPC
  12. Baseflow recession and recharge as nonlinear storage processes
  13. Control of a two-thermoelectric-cooler system for ice-clamping application using Lyapunov based approach
  14. Second-order SMC with disturbance compensation for robust tracking control in PMSM applications
  15. Late developers and the inequity of "equitable utilization" and the harm of "do no harm"
  16. Influence of data clouds fusion from 3D real-time vision system on robotic group dead reckoning in unknown terrain
  17. Machine Learning and Data Mining for Sports Analytics
  18. Neural correlates of own name and own face processing in neurotypical adults scoring low versus high on symptomatology of autism spectrum disorder
  19. Planar Multipole Resonance Probe: A kinetic model based on a functional analytic description
  20. Accuracy and bias of methods used for root length measurements in functional root research
  21. Timing matters: Distinct effects of nitrogen and phosphorus fertilizer application timing on root system architecture responses
  22. Combining SMC and MTPA Using an EKF to estimate parameters and states of an interior PMSM
  23. Design of Reliable Remobilisation Finger Implants with Geometry Elements of a Triple Periodic Minimal Surface Structure via Additive Manufacturing of Silicon Nitride
  24. Enhanced Calculation Procedures for Material and Energy Flow Oriented EMIS
  25. Gamen
  26. The Application of Extended Producer Responsibility in Germany
  27. A Graphic Language for Business Application Systems to Improve Communication Concerning Requirements Specification with the User
  28. "Learning by doing"
  29. Pathways of Data-driven Business Model Design and Realization
  30. Simulation of SARS-CoV-2 pandemic in Germany with ordinary differential equations in MATLAB
  31. Local responses to global technological change.
  32. Finding the Best Match — a Case Study on the (Text‑) Feature and Model Choice in Digital Mental Health Interventions
  33. The role of supervisor support for dealing with customer verbal aggression. Differences between ethnic minority and ethnic majority workers