Deep applications of machine learning in cold strip rolling industry: opportunities and challenges

ZONG Nanfu; QI Zhen; JING Tao; SHEN Houfa; JEAN-CHRISTOPHE Gebelin; MARYAM Khaksar Ghalati

doi:10.7513/j.issn.1004-7638.2025.05.011

Volume 46 Issue 5

Oct. 2025

Turn off MathJax

Article Contents

Article Navigation > IRON STEEL VANADIUM TITANIUM > 2025 > 46(5): 102-110

ZONG Nanfu, QI Zhen, JING Tao, SHEN Houfa, JEAN-CHRISTOPHE Gebelin, MARYAM Khaksar Ghalati. Deep applications of machine learning in cold strip rolling industry: opportunities and challenges[J]. IRON STEEL VANADIUM TITANIUM, 2025, 46(5): 102-110. doi: 10.7513/j.issn.1004-7638.2025.05.011

Citation:

ZONG Nanfu, QI Zhen, JING Tao, SHEN Houfa, JEAN-CHRISTOPHE Gebelin, MARYAM Khaksar Ghalati. Deep applications of machine learning in cold strip rolling industry: opportunities and challenges[J]. IRON STEEL VANADIUM TITANIUM, 2025, 46(5): 102-110. doi: 10.7513/j.issn.1004-7638.2025.05.011

Citation:

ZONG Nanfu, QI Zhen, JING Tao, SHEN Houfa, JEAN-CHRISTOPHE Gebelin, MARYAM Khaksar Ghalati. Deep applications of machine learning in cold strip rolling industry: opportunities and challenges[J]. IRON STEEL VANADIUM TITANIUM, 2025, 46(5): 102-110. doi: 10.7513/j.issn.1004-7638.2025.05.011

PDF( 1750 KB)

Deep applications of machine learning in cold strip rolling industry: opportunities and challenges

doi: 10.7513/j.issn.1004-7638.2025.05.011

1.
Technology Center of Ben Gang Group Corporation, Digital Intelligence Research Institute, Benxi 117000, Liaoning, China
2.
Ben Gang Group Corporation, Benxi 117000, Liaoning, China
3.
Key Laboratory for Advanced Materials Processing Technology, Ministry of Education, School of Materials, Tsinghua University, Beijing 100084, China
4.
School of Engineering, University of Leicester, Leicester LE1 7RH, United Kingdom

More Information

Received Date: 2025-04-05
Accepted Date: 2025-05-08
Rev Recd Date: 2025-05-07
Publish Date: 2025-10-30

Abstract

Abstract

The strip cold rolling process is a critical component of iron and steel manufacturing, yet it is often plagued by challenges such as flatness defects, thickness variations, and rolling mill vibrations, which can significantly impact productivity and product quality. Machine learning (ML) has emerged as a powerful tool to address these issues by analyzing vast amounts of process data to predict and mitigate potential defects in real-time. By leveraging historical and real-time data, ML algorithms can identify complex patterns and correlations between operational parameters （such as roll force, roll gap, and rolling speed）and key quality indicators like flatness and thickness uniformity. This enables the optimization of process parameters dynamically, ensuring consistent product quality while minimizing waste and downtime. Furthermore, ML-driven predictive models facilitate proactive adjustments to the rolling process, reducing the occurrence of defects and enhancing the overall efficiency. The integration of ML not only improves the precision and reliability of the cold rolling process but also leads to substantial cost savings and increased productivity.
- Machine learning,
- cold rolling,
- flatness defects,
- thickness variations,
- rolling mill vibrations

FullText(HTML)

References(44)

References

[1]	TAKAMI K M, MAHMOUDI J, DAHLQUIST E, et al. Multivariable data analysis of a cold rolling control system to minimise defects[J]. International Journal of Advanced Manufacturing Technology, 2011, 54: 553-565. doi: 10.1007/s00170-010-2946-2
[2]	FLORIANO B R, VARGAS A N, ISHIHARA J Y, et al. Neural-network-based model predictive control for consensus of nonlinear systems[J]. Engineering Applications of Artificial Intelligence, 2022, 116: 105327. doi: 10.1016/j.engappai.2022.105327
[3]	ZONG N F, JING T, GEBELIN J C. Machine learning techniques for the comprehensive analysis of the continuous casting processes: Slab defects[J]. Ironmaking & Steelmaking, 2025.
[4]	PITTNER J, SIMAAN M A. State-dependent riccati equation approach for optimal control of a tandem cold metal rolling process[J]. IEEE Transactions on Industry Applications, 2006, 42(3): 836-843.
[5]	ZONG N F, LIU H L, LI S, et al. Application status and prospects of machine learning in high-efficiency continuous casting manufacturing[J]. Angang Technology, 2025, 450(6): 23-33. (宗男夫, 刘宏亮, 李爽, 等. 机器学习在高效连铸制造中的应用现状及展望[J]. 鞍钢技术, 2025, 450(6): 23-33. ZONG N F, LIU H L, LI S, et al. Application status and prospects of machine learning in high-efficiency continuous casting manufacturing[J]. Angang Technology, 2025, 450（6）: 23-33.
[6]	GEURTS P, ERNST D, WEHENKEL L, et al. Extremely randomized trees[J]. Machine learning, 2006, 63: 3-42. doi: 10.1007/s10994-006-6226-1
[7]	SUTHAHARAN S. Machine learning models algorithms for big data classification: thinking with examples for effective learning, [M]. Berlin: Springer, 2016.
[8]	CHEN C, HUI Q, PEI Q, et al. CRML: A convolution regression model with machine learning for hydrology forecasting[J]. IEEE Access, 2019, 7: 133839-133849. doi: 10.1109/ACCESS.2019.2941234
[9]	ALLOGHANI M, Al-JUMEILY D, MUSTAFINA J, et al. A systematic review on supervised and unsupervised machine learning algorithms for data science[J]. Supervised Unsupervised Learn Data Sci. 2020, 3-21.
[10]	KAMESHWARAN K, MALARVIZHI K. Survey on clustering techniques in data mining[J]. Journal of Computer Science and Technology, 2014, 5(2): 2272-2276.
[11]	MNIH V, KAVUKCUOGLU K, SILVER D, et al. Human-level control through deep reinforcement learning[J]. Nature, 2015, 518(7540): 529-533. doi: 10.1038/nature14236
[12]	KAELBLING L P, LITTMAN M L, MOORE A W. Reinforcement learning: a survey[J]. Journal of Artificial Intelligence Research, 1996, 4: 237-285. doi: 10.1613/jair.301
[13]	WATKINS C W, DAYAN P. Q-learning[J]. Machine learning, 1992, 8: 279-292.
[14]	LIU Z. Artificial intelligence for engineers. basics and implementations[M].Berlin:Springer, 2025.
[15]	PANG G, SHEN C, CAO C, et al. Deep learning for anomaly detection: a review[J]. ACM Comput. Surv, 2021, 54(2): 1-38.
[16]	TERCAN H, TMEISEN T. Machine learning and deep learning based predictive quality in manufacturing: a systematic review[J]. Journal of Intelligent Manufacturing, 2022, 33: 1879-1905. doi: 10.1007/s10845-022-01963-8
[17]	HU Z Y, WEI Z H, SUN H, et al. Optimization of metal rolling control using soft computing approaches: a review[J]. Archives of Computational Methods in Engineering, 2021, 28: 405-421. doi: 10.1007/s11831-019-09380-6
[18]	SUN J, SHAN P F, WEI Z, et al. Data-based flatness prediction and optimization in tandem cold rolling[J]. Journal of Iron and Steel Research, International, 2021, 11: 563-573.
[19]	LU X, SUN J, SONG Z X, et al. Prediction and analysis of cold rolling mill vibration based on a data-driven method[J]. Applied Soft Computing, 2020, 96: 106706. doi: 10.1016/j.asoc.2020.106706
[20]	HU Y, SUN J, PENG W, et al. A novel forecast model based on CF-PSO-SVM approach for predicting the roll gap in acceleration and deceleration process[J]. Engineering Computations, 2020, 38(3): 1117-1133.
[21]	SONG J, REN T Z, WANG K Y, et al. Optimization of work roll bending model in unsteady process of tandem cold rolling based on CF-PSO-SVM[J]. Iron and Steel, 2021, 11: 78-86. (宋君, 任廷志, 王奎越, 等. 基于CF-PSO-SVM的冷连轧非稳态工作辊弯辊模型优化[J]. 钢铁, 2021, 11: 78-86. SONG J, REN T Z, WANG K Y, et al. Optimization of work roll bending model in unsteady process of tandem cold rolling based on CF-PSO-SVM[J]. Iron and Steel, 2021, 11: 78-86.
[22]	WANG Y, LI C S, PENG L G, et al. Application of convolutional neural networks for prediction of strip flatness in tandem cold rolling process[J]. Journal of Manufacturing Processes, 2021, 68: 512-522. doi: 10.1016/j.jmapro.2021.05.062
[23]	CHEN L Z, SUN W Q, HE A R, et al. Research on thickness defect control of strip head based on GA-BP rolling force preset model[J]. Metals, 2022, 12: 924-940. doi: 10.3390/met12060924
[24]	HUANG Y, ZHOU X M, GAO Z Y. Thickness prediction of thin strip cold rolling based on VBGM-RBF[J]. The International Journal of Advanced Manufacturing Technology, 2022, 120: 5865-5884. doi: 10.1007/s00170-022-09122-2
[25]	CHEN S Z, BAI Y S, HOU J Q, et al. Rolling force prediction model for cold rolling based on GA-FELM[J]. Journal of Yanshan University, 2022, 46(3): 46v224-229. (陈树宗, 白芸松, 侯佳琦, 等. 基于GA-FELM算法的冷轧轧制力预测模型[J]. 燕山大学学报, 2022, 46(3): 46v224-229. doi: 10.3969/j.issn.1007-791X.2022.03.005 CHEN S Z, BAI Y S, HOU J Q, et al. Rolling force prediction model for cold rolling based on GA-FELM[J]. Journal of Yanshan University, 2022, 46（3）: 46v224-229. doi: 10.3969/j.issn.1007-791X.2022.03.005
[26]	CHEN S Z, HOU J Q, BAI Y S, et al. Rolling force prediction model for cold rolling based on MA-SVM[J]. Journal of Yanshan University, 2023, 47(5): 428-432. (陈树宗, 白芸松, 侯佳琦, 等. 基于MA-SVM算法的冷轧轧制力预测模型[J]. 燕山大学学报, 2023, 47(5): 428-432. doi: 10.3969/j.issn.1007-791X.2023.05.006 CHEN S Z, HOU J Q, BAI Y S, et al. Rolling force prediction model for cold rolling based on MA-SVM[J]. Journal of Yanshan University, 2023, 47（5）: 428-432. doi: 10.3969/j.issn.1007-791X.2023.05.006
[27]	YUAN T H, SUN W Q, HE A R, et al. Research on quarter wave shape control of cold rolled high strength steel based on BP-MOPSO[J]. The International Journal of Advanced Manufacturing Technology, 2022, 122: 3867-3880. doi: 10.1007/s00170-022-10101-w
[28]	DING Y, DING C Y, SUN J, et al. Research on quarter wave shape control of cold rolled high strength steel based on BP-MOPSO[J]. Rolling, 2022, 39(6): 99-105.
[29]	CHEN Y F, PENG L G, WANG Y, et al. Prediction of tandem cold-rolled strip flatness based on Attention-LSTM model[J]. Journal of Manufacturing Processes, 2023, 91: 110-121. doi: 10.1016/j.jmapro.2023.02.048
[30]	ZHAO J W, LI J D, YANG Q, et al. A novel paradigm of flatness prediction and optimization for strip tandem cold rolling by cloud-edge collaboration[J]. Journal of Materials Processing Technology, 2023, 316: 117947. doi: 10.1016/j.jmatprotec.2023.117947
[31]	ZHAO J W, LI J D, QIE H T, et al. Online prediction of deformation resistance for strip tandem cold rolling based on data-driven[J]. Metals, 2023, 13: 737-756. doi: 10.3390/met13040737
[32]	YAN Z W, BU H N, HU C Z, et al. Rolling force prediction during FGC process of tandem cold rolling based on IQGA-WNN ensemble learning[J]. The International Journal of Advanced Manufacturing Technology, 2023, 125: 2869-2884. doi: 10.1007/s00170-023-10899-z
[33]	XIA J S, KHABAZ M K, PATRA I, et al. Using feed-forward perceptron Artificial Neural Network (ANN) model to determine the rolling force, power and slip of the tandem cold rolling[J]. ISA Transactions, 2023, 132: 353-363. doi: 10.1016/j.isatra.2022.06.009
[34]	SONG J, WANG K Y, CAO Z H. Application of fruit fly optimization neural network in cold rolling bending model[J]. Metallurgical Industry Automation, 2023, 47(3): 116-125. (宋君, 王奎越, 曹忠华. 果蝇优化神经网络在冷轧弯辊模型中的应用[J]. 冶金自动化, 2023, 47(3): 116-125. doi: 10.3969/j.issn.1000-7059.2023.03.013 SONG J, WANG K Y, CAO Z H. Application of fruit fly optimization neural network in cold rolling bending model[J]. Metallurgical Industry Automation, 2023, 47（3）: 116-125. doi: 10.3969/j.issn.1000-7059.2023.03.013
[35]	LI J D, ZHAO J W, WANG X C, et al. An industrial IoT-based deformation resistance prediction and thickness control method of cold-rolled strip in steel production systems[J]. Information Sciences, 2024, 674: 120735. doi: 10.1016/j.ins.2024.120735
[36]	HAN G M, LI H B, WANG G, et al. Prediction and control of profile for silicon steel strip in the whole tandem cold rolling based on PSO-BP algorithm[J]. Journal of Manufacturing Processes, 2024, 120: 250-259. doi: 10.1016/j.jmapro.2024.04.050
[37]	CAO L, LI X, LI X H, et al. Variable speed rolling force prediction with theoretical and data-driven models[J]. International Journal of Mechanical Sciences, 2024, 264: 108833. doi: 10.1016/j.ijmecsci.2023.108833
[38]	DING C Y, YE J C, LEI J W, et al. An interpretable framework for high-precision flatness prediction in strip cold rolling[J]. Journal of Materials Processing Technology, 2024, 329: 118452. doi: 10.1016/j.jmatprotec.2024.118452
[39]	WANG Q L, SUN J, HU Y J, et al. Deep learning-based flatness prediction via multivariate industrial data for steel strip during tandem cold rolling[J]. Expert Systems With Applications, 2024, 237: 121777. doi: 10.1016/j.eswa.2023.121777
[40]	YANG W Q, ZHAO Z T, ZHU L Y, et al. Strip flatness prediction of cold rolling based on ensemble methods[J]. Journal of Iron and Steel Research, International, 2024, 31: 237-251. doi: 10.1007/s42243-023-01060-x
[41]	CHEN S Z, LIU Y X, WANG Y L, et al. Multi-dimension and multi-modal rolling mill vibration prediction model based on multi-level network fusion[J]. Journal of Central South University, 2024, 31: 3329-3348. doi: 10.1007/s11771-024-5762-9
[42]	NIU Y Y, LI X J, DENG C, et al. RBF neural network-based distributed nonlinear model predictive control on tandem cold rolling stands[J]. International Journal of Robust and Nonlinear Control, 2025, 35(6): 2451-2461.
[43]	BABAJAMALI Z, KHABAZ M K, AGHADAVOUDI F, et al. Pareto multi-objective optimization of tandem cold rolling settings for reductions and inter stand tension using Nsga-Ii[J]. ISA Transactions, 2022, 130: 399-408. doi: 10.1016/j.isatra.2022.04.002
[44]	HAN H G, FU S J, SUN H Y, et al. Hierarchical nonlinear model predictive control with multi-time-scale for wastewater treatment process[J]. Journal of Process Control, 2021, 108: 125-135. doi: 10.1016/j.jprocont.2021.11.002