Paper Titles

Numerical Investigation of Deposition Efficiency Influencing Factors in the Friction Surfacing Process
p.1

Prediction of Strip Width Deviation in Hot Strip Roughing Mills Based on Machine Learning Regression
p.9

Multi-Objective Bayesian Optimization of Dual-Phase Steel Microstructures for Minimal Damage Initiation
p.21

Algebraic Hierarchical Graph Neural Networks for Forming Simulation of Thermoplastic Composite Materials
p.31

Explainable Machine Learning and 3D Visualization for Rotary Tube Bending: Expert Evaluation of a Web-Based Tool
p.43

Investigation of Code Optimization Strategies for Enhancing the Performance of Static Recrystallization Cellular Automata Models
p.59

Parameter Optimization and Data-Driven Soft-Sensor Framework for Torque Prediction in Bobbin-Tool Friction Stir Welding of AA2024
p.69

Long Short-Term Memory to Predict the Quality Parameters in the Hot Rolling Process
p.81

HomeKey Engineering MaterialsKey Engineering Materials Vol. 1050Prediction of Strip Width Deviation in Hot Strip...

Prediction of Strip Width Deviation in Hot Strip Roughing Mills Based on Machine Learning Regression

Article Preview

View Pdf By email

Abstract:

Previous research shows that predicting width deviation inherits a central importance in hot rolling processes, so that the pass planning in the hot strip mill (HSM) can be optimized. These predictions can be enabled using machine learning, complementing analytical formulations of width spread. For reliable production, it is important for the plant operator to be able to control the geometry with high accuracy across the entire plant. Therefore, the width must be accurately known throughout the entire HSM. This paper aims on the prediction of width deviation in early product stages during the roughing mill processes, where the major deformation takes place, and thus also has the most significant influence on the width spread. Therefore, this paper takes industrial data into account which is also used for the roll passing planning. To achieve a prediction during rough rolling for the width after exiting the mill (future state of the strip width), various machine learning algorithms were implemented and tested. The prediction results are evaluated against an inline width measurement, where the XGB model performs best with a Root Mean Squared Error (RMSE) of 1.11 mm. Subsequently, feature importance analyses are used to examine which features are relevant for the prediction result and to elaborate which significance process-and geometry data has on the same strip.

You have full access to the following eBook

Advanced Numerical and AI Strategies for Material Forming

Info:

Periodical:

Key Engineering Materials (Volume 1050)

Pages:

9-20

DOI:

https://doi.org/10.4028/p-GLpuV9

Citation:

Cite this paper

Online since:

April 2026

Authors:

Daniel Ewen*, Johannes Seitz, Sebastian Kallabis, Reinhold Franke, Joachim Denker, Lukas Lackmann, Bernd Kuhlenkötter

Keywords:

Hot Strip Rolling, Machine Learning, Prediction, Predictive Quality, Width Deviation

Export:

RIS, BibTeX

Permissions:

Creative Commons CC BY 4.0

Share:

Citation:

* - Corresponding Author

[1] Wirtschaftsvereinigung Stahl, "Statistisches Jahrbuch der Stahlindustrie: 2024 | 2025," [Online]. Available: https://www.wvstahl.de/publikationen/statistisches-jahrbuch-der-stahlindustrie-2024-2025/.

DOI: 10.5771/9783748949336-369

[2] H. Tiensuu, S. Tamminen, O. Haapala, and J. Röning, "Intelligent methods for root cause analysis behind the center line deviation of the steel strip," Open Engineering, vol. 10, no. 1, p.386–393, 2020.

DOI: 10.1515/eng-2020-0041

[3] LLM Group, Discussion on the production process and common quality problems of hot rolled strip steel. [Online]. Available: https://www.lmmgroupcn.com/discussion-on-the-production-process-and-common-quality-problems-of-hot-rolled-strip-steel/ (accessed: Oct. 22 2025).

DOI: 10.1520/a0634

[4] D. Weichert, P. Link, A. Stoll, S. Rüping, S. Ihlenfeldt, and S. Wrobel, "A review of machine learning for the optimization of production processes," International Journal of Advanced Manufacturing Technology, vol. 104, 5-8, p.1889–1902, 2019.

DOI: 10.1007/s00170-019-03988-5

[5] X. Shu and Y. Ye, "Knowledge Discovery: Methods from data mining and machine learning," Social science research, vol. 110, p.102817, 2023.

DOI: 10.1016/j.ssresearch.2022.102817

[6] T. Shibahara, Y. Misaka, T. Kono, M. Koriki, and H. Takemoto, "Edger Set-up Model at Roughing Train in Hot Strip Mill," Tetsu-to-Hagane, vol. 67, no. 15, p.2509–2515, 1981.

DOI: 10.2355/tetsutohagane1955.67.15_2509

[7] A. Hashemzadeh, F. E. Bock, C. Hol, K. Schutte, A. Cometa, C. Soyarslan, B. Klusemann, and T. van den Boogaard, "An analytical predictor machine learning corrector scheme for modeling lateral flow in hot strip rolling," in Materials Research Proceedings, 2025, p.2002–2011.

DOI: 10.21741/9781644903599-215

[8] W. Wu, W. Peng, Y. Liu, J. Liu, X. Li, D. Zhang, and J. Sun, "Predictive modeling of strip width based on incremental learning and adaptive-weight fusion during the hot rolling process," Journal of Manufacturing Processes, vol. 142, p.157–176, 2025.

DOI: 10.1016/j.jmapro.2025.03.091

[9] S. Latham and C. Giannetti, "A Tool to Combine Expert Knowledge and Machine Learning for Defect Detection and Root Cause Analysis in a Hot Strip Mill," SN Computer Science, vol. 4, no. 5, 2023.

DOI: 10.1007/s42979-023-02104-5

[10] Y. Xin, Z. Zhang, Z. Zhong, and Y. Li, "Lateral spread prediction based on hybrid CNN-LSTM model for hot strip finishing mill," Materials Letters, vol. 378, p.137594, 2025.

DOI: 10.1016/j.matlet.2024.137594

[11] H. Gao, Y. Qin, H. Yuan, X. Li, J. Cao, F. Luan, and D. Zhang, "Temporal online self-learning stochastic configuration networks: A study on strip deviation prediction," Information Sciences, vol. 689, p.121446, 2025.

DOI: 10.1016/j.ins.2024.121446

[12] Z. Dong, X. Li, F. Luan, C. Cui, J. Ding, and D. Zhang, "Rolling theory-guided prediction of hot-rolled plate width based on parameter transfer strategy," ISA transactions, vol. 146, p.352–365, 2024.

DOI: 10.1016/j.isatra.2024.01.013

[13] Y. Zhong, J. Wang, J. Xu, and J. Rao, "Strip width spread prediction in rough rolling process based on mechanism modeling and optimization," Journal of Iron and Steel Research International, vol. 30, no. 12, p.2416–2424, 2023.

DOI: 10.1007/s42243-023-01085-2

[14] Y. Zhong, J. Wang, J. Xu, J. Rao, and K. Dang, "Data-driven width spread prediction model improvement and parameters optimization in hot strip rolling process," Applied Intelligence, vol. 53, no. 21, p.25752–25770, 2023.

DOI: 10.1007/s10489-023-04818-8

[15] Y. Ji, S. Liu, M. Zhou, Z. Zhao, X. Guo, and L. Qi, "A machine learning and genetic algorithm-based method for predicting width deviation of hot-rolled strip in steel production systems," Information Sciences, vol. 589, p.360–375, 2022.

DOI: 10.1016/j.ins.2021.12.063

[16] G. Louppe, L. Wehenkel, A. Sutera, and P. Geurts, "Understanding variable importances in forests of randomized trees," Advances in neural information processing systems, vol. 26, 2013. [Online]. Available: https://proceedings.neurips.cc/paper_files/paper/2013/file/e3796ae838835da0b6f6ea37bcf8bcb7-Paper.pdf.

[17] P. Roßbach, Neural Networks vs. Random Forests – Does it always have to be Deep Learning? [Online]. Available: https://blog.frankfurt-school.de/de/neural-networks-vs-random-forests-does-it-always-have-to-be-deep-learning/ (accessed: Nov. 5 2025).

DOI: 10.3390/su151813898

[18] T. Akiba, S. Sano, T. Yanase, T. Ohta, and M. Koyama, "Optuna," in Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Anchorage AK USA, 2019, p.2623–2631.

DOI: 10.1145/3292500.3330701

[19] DIN EN 10051:2024-07, Continuously hot-rolled strip and plate/sheet cut from wide strip of non-alloy and alloy steels - Tolerances on dimensions and shape, Berlin.

DOI: 10.3403/30200093