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

Abstract:

Accurate prediction of quality-relevant material parameters, such as thickness and grain size, ensures product quality in hot forming processes. This task becomes especially complex in hot rolling, where the sequential and time-dependent nature of the process results in pass schedules with varying numbers of passes and grain size evolution that depends on the deformation history. To address this complexity, this study aims to develop and train deep learning models based on Long Short-Term Memory (LSTM) networks, which are well-suited for modelling sequential data. As input features for the model, real-time process parameters such as rolling force and rolling temperature are used, which can be captured by sensors during operation. Simulation data for both material and process parameters are acquired using Simulation as a Service (SaaS) through the Fast Rolling Model (FRM) called Rolling Calculation Tool (RoCaT), focusing on steel grade S355. The performance of the LSTM model is evaluated by analysing loss curves over training epochs and comparing predicted values to reference data. The maximum relative percentage error for thickness between the LSTM predicted value and the RoCaT value is 18.818% and 16.56259%, respectively, for pass schedules of 15 and 17 passes, with a starting thickness of 205mm. The percentage of relative error values for grain size is more pronounced during the initial passes as compared to later passes for both pass schedules. The statistical validation is performed on the denormalized data using metrics such as Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and R-Squared (R²), which demonstrate the model’s ability to predict key material properties in the hot rolling process reliably. The RMSE, MAE, and R² values for thickness are obtained as 45.2175mm, 18.7555mm, and 0.8115, respectively. For grain size, the corresponding values are 25.8287µm, 13.4319µm, and 0.9192.

• Periodical: Key Engineering Materials (Volume 1050)
• Pages: 81-91
• DOI: https://doi.org/10.4028/p-0V5rM0
• Online since: April 2026
• Authors: Tamoghna Majumder*, Nilesh Thakare, Holger Brüggemann, Emad Scharifi, Junhe Lian
• Keywords: Hot Rolling, Long Short-Term Memory, Quality-Relevant Material Parameters

References

[1] F. Tao, Q. Qi, A. Liu, and A. Kusiak, "Data-driven smart manufacturing," Journal of Manufacturing Systems, vol. 48, p.157–169, 2018.

DOI: 10.1016/j.jmsy.2018.01.006

[2] S. J. Plathottam, A. Rzonca, R. Lakhnori, and C. O. Iloeje, "A review of artificial intelligence applications in manufacturing operations," J Adv Manuf & Process, vol. 5, no. 3, 2023.

DOI: 10.1002/amp2.10159

[3] A. Sherstinsky, "Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) network," Physica D: Nonlinear Phenomena, vol. 404, p.132306, 2020.

DOI: 10.1016/j.physd.2019.132306

[4] T. Perumal, N. Mustapha, R. Mohamed, and F. M. Shiri, "A Comprehensive Overview and Comparative Analysis on Deep Learning Models," JAI, vol. 6, no. 1, p.301–360, 2024.

DOI: 10.32604/jai.2024.054314

[5] R. Jiao, K. Peng, and J. Dong, "Remaining Useful Life Prediction for a Roller in a Hot Strip Mill Based on Deep Recurrent Neural Networks," IEEE/CAA J. Autom. Sinica, vol. 8, no. 7, p.1345–1354, 2021.

DOI: 10.1109/JAS.2021.1004051

[6] A. G. Zinyagin, A. V. Muntin, V. S. Tynchenko, P. I. Zhikharev, N. R. Borisenko, and I. Malashin, "Recurrent Neural Network (RNN)-Based Approach to Predict Mean Flow Stress in Industrial Rolling," Metals, vol. 14, no. 12, p.1329, 2024.

DOI: 10.3390/met14121329

[7] G. Niu, M. Zhang, Y. Yang, and Z. Huang, "A Hot Rolling Full Process Rolling Force Prediction Method Based on Transfer Learning and Inception-LSTM Neural Network," ISIJ Int., vol. 65, no. 1, p.97–103, 2025.

DOI: 10.2355/isijinternational.ISIJINT-2023-446

[8] Z. Yang et al., "Online Prediction of Mechanical Properties of the Hot Rolled Steel Plate Using Time-series Deep Neural Network," ISIJ Int., vol. 63, no. 4, p.746–757, 2023.

DOI: 10.2355/isijinternational.ISIJINT-2022-383

[9] J. Lohmar, S. Seuren, M. Bambach, G. Hirt, "Design and application of an advanced fast rolling model with through thickness resolution for heavy plate rolling," 2014.

[10] S. Seuren, J. Willkomm, M. Buecker, M. Bambach, G. Hirt, "Sensitivity analysis of a force and microstructure model for plate rolling," 2012.

[11] Sims, R. B., & Wright, H., "Roll force and torque in hot rolling mills," 3(5), 261–269., 1963.

[12] Seuren, S., Bambach, M., Hirt, G., Heeg, R., & Philipp, M., "Geometric factors for fast calculation of roll force in plate rolling," 2010.

[13] Beynon, J. H., & Sellars, C. M., "Modelling microstructure and its effects during multipass hot rolling," 32(3), p.359–367, 1992.

DOI: 10.2355/isijinternational.32.359

[14] C. Idzik, A. Krämer, G. Hirt, and J. Lohmar, "Coupling of an analytical rolling model and reinforcement learning to design pass schedules: towards properties controlled hot rolling," J Intell Manuf, vol. 35, no. 4, p.1469–1490, 2024.

DOI: 10.1007/s10845-023-02115-2

[15] C. Scheiderer et al., "Simulation-as-a-Service for Reinforcement Learning Applications by Example of Heavy Plate Rolling Processes," Procedia Manufacturing, vol. 51, p.897–903, 2020.

DOI: 10.1016/j.promfg.2020.10.126

[16] S. Nosouhian, F. Nosouhian, and A. Kazemi Khoshouei, A Review of Recurrent Neural Network Architecture for Sequence Learning: Comparison between LSTM and GRU, 2021.

DOI: 10.20944/preprints202107.0252.v1

[17] P. Tang, H. Wang, and S. Kwong, "Deep sequential fusion LSTM network for image description," Neurocomputing, vol. 312, p.154–164, 2018, doi: 10.1016/j.neucom. 2018.05.086.

DOI: 10.1016/j.neucom.2018.05.086

[18] Y. Gao and Glowacka Dorota, "Deep Gate Recurrent Neural Network," p.350–365, 2016.

[19] Z. S. Kadhim, H. S. Abdullah, and K. I. Ghathwan, "Artificial Neural Network Hyperparameters Optimization: A Survey," Int. J. Onl. Eng., vol. 18, no. 15, p.59–87, 2022.

DOI: 10.3991/ijoe.v18i15.34399

[20] J. Almomani, G. Nasserddine, O.A. Khatib, R.R. Kala, M.Nasserddine, "Time Series Forecasting Approach for Power Demand Prediction Based on Feature Engineering, Optuna-Based Hyperparameter Tuning, and Ensemble Learning",2025 IEEE PES Conference on Innovative Smart Grid Technologies - Middle East (ISGT Middle East): IEEE, 2025.

DOI: 10.1109/ISGTMiddleEast65737.2025.11314432

[21] Haider Khalaf Jabbar, "Methods to avoid over-fitting and under-fittingin supervised machine learning(comparative study)," p.163–172.

DOI: 10.3850/978-981-09-5247-1_017

[22] Abhishek V Tatachar, "Comparative Assessment of Regression Models Based On Model Evaluation Metrics," 2021.