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

Publikation: Beiträge in SammelwerkenAufsätze in KonferenzbändenForschungbegutachtet

Authors

  • Amirali Hashemzadeh
  • Frederic E. Bock
  • Camile Hol
  • Koen Schutte
  • Antonella Cometa
  • Celal Soyarslan
  • Benjamin Klusemann
  • Ton Van Den Boogaard

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.

OriginalspracheEnglisch
TitelMaterial Forming, ESAFORM 2025 : The 28th International ESAFORM Conference on Material Forming – ESAFORM 2025 – held in Paestum (Italy), 7-9 May, 2025
HerausgeberPierpaolo Carlone, Luigino Filice, Domenico Umbrello
Anzahl der Seiten10
ErscheinungsortMillersville
VerlagMaterialsResearchForum LLC
Erscheinungsdatum2025
Seiten2002-2011
ISBN (elektronisch)978-1-64490-359-9
DOIs
PublikationsstatusErschienen - 2025
Veranstaltung28th International ESAFORM Conference on Material Forming - ESAFORM 2025 - Paestum, Italien
Dauer: 07.05.202509.05.2025
Konferenznummer: 28

Bibliographische Notiz

Publisher Copyright:
© 2025, Association of American Publishers. All rights reserved.

DOI

Zuletzt angesehen

Publikationen

  1. The Practical Significance of History: When and How History Can Be Used for Institutional Change
  2. Low working memory reduces the use of mental contrasting
  3. Thanking and responding to thanks in American English: Language patterning and contextual appropriateness
  4. Understanding Innovation
  5. NNARX networks on didactic level system identification
  6. Does modality play a role? Visual-verbal cognitive style and multimedia learning
  7. Landscape models for use in studies of landscape change and habitat fragmentation
  8. A four-component classification of uncertainties in biological invasions: implications for management
  9. Cobalt in end-of-life products in the EU, where does it end up? - The MaTrace approach
  10. Long-term population dynamics of Dactylorhiza incarnata (L.) Soo after abandonment and re-introduction of mowing
  11. Creative spaces in computer science
  12. Leveraging the macro-level environment to balance work and life
  13. Was fehlt in der EVS?
  14. Managing Multiple Logics: The Role of Performance Measurement Systems in Social Enterprises
  15. Anisotropy and mechanical properties of dissimilar Al additive manufactured structures generated by multi-layer friction surfacing
  16. Comparing preference-based quality-of-life measures
  17. Approaches and Lessons in Political Career Research
  18. Case study meta-analysis in the social sciences. Insights on data quality and reliability from a large-N case survey
  19. Continous preventive diagnosis for cardiovascular diseases based on stochastic modeling
  20. Doing statistics, enacting the nation
  21. “Making Sense”
  22. Lizard distribution patterns in the Tumut Fragmentation "Natural Experiment" in south-eastern Australia
  23. Broad values as the basis for understanding deliberation about protected area management
  24. Adaptation strategies for reducing vulnerability to future environmental change
  25. Selecting methods for ecosystem service assessment
  26. Exports, firm size, and firm dynamics