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. As the strip’s thick-
ness decreases, it undergoes lateral expansion known as spread. Modeling spread is crucial for sustain-
ability 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. For example, Bock et
al. [1] proposed a predictive framework to correct a fast but inaccurate analytical model towards the
solutions of a high-fidelity FE model via machine learning to foresee the residual stresses induced
by the laser shock peening process. The present work aims to develop a fast and accurate model for
predicting spread in hot rolling. Within the developed framework, machine learning plays a key role
in narrowing the gap between ground truth (GT) and analytical models by addressing the inherent un-
certainties and limitations of these models. 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 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 the 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.
