Continuous casting route is the most widely produced process in the world every year, accounting for around 95% of global steel production. Due to the various inevitable defects, including cracks, segregations, inclusions and breakout involved in the production process, tranditional control and monitoring approaches are pushed to their limits. Over the past decade, the increasing global competition has combined metals engineering with digital technology and artificial intelligence skills, to help the manufacturing industries to reap the benefits of “big data.” By targeting critical machine learning (ML) techniques, the casting industry leaders rapidly take advantage of the latest discoveries in manufacturing processes through digital twinning to enable defect-free casting. This study offers an analytical overview of ML methods applied to the examination of the continuous casting procedure. This paper examines the current research on ML in steel continuous casting, organizing the findings into categories, which aids in identification of typical application cases and approaches. This comprehensive analysis concludes with the elaboration of challenges, potential solutions, and a future outlook for further cutting-edge research and development to unleash the potential of future ML techniques and maintain casting industry's reputation.
TaoHZhangHLiuH, et al.Longitudinal corner crack of chamfered slab and optimization of mould. J Iron Steel Res Int2023; 30: 307–316.
2.
ZongNFLiuYMaSD, et al.A review of chamfer technology in continuous casting process. Metall Res Technol2020; 204: 204–219.
3.
ZongNFZhangHLiuY, et al.Analysis of the off-corner subsurface cracks of continuous casting blooms under the influence of soft reduction and controllable approaches by a chamfer technology. Metall Res Technol2019; 116: 310–319.
4.
ZongNFLiuYZhangH, et al.Application of chamfered narrow face mold technology to reduce longitudinal surface crack defects of hyperperitectic steel generated during flexible thin slab casting process. Metall Res Technol2019; 114: 413–421.
5.
ZongNFZhangHLiuY, et al.Application of a chamfer slab technology to reduce internal cracks of continuous casting bloom during soft reduction process. Metall Res Technol2019; 116: 608–619.
6.
ZongNFHuangJLiuY, et al.Analysis of internal cracks in high carbon casting bloom induced by soft reduction process and its improvement using numerical simulations and industrial experiments. Metall Res Technol2021; 118: 102–110.
7.
ZongNFZhangHLiuY, et al.Analysis on morphology and stress concentration in continuous casting bloom to learn the formation and propagation of internal cracks induced by soft reduction technology. Ironmak Steelmak2019; 46: 872–885.
8.
ZongNFJingTLiuY, et al.Comparative studies on a chamfer technology and a convex roll technology during the soft reduction process. Arch Metall Mater2021; 66: 819–829.
9.
QianHHeFXieX, et al.Recovery mechanism of the sticking-type breakout during continuous casting of steel. Ironmak Steelmak2019; 46: 259–268.
10.
ZongNFLiuYZhangH, et al.Application of chamfered slab technology to reduce straight edge seam defects of non-oriented silicon electrical steel generated during flexible thin slab casting process. Metall Res Technol2017; 114: 311–320.
11.
ZongNFLiuYJingT, et al.Application of a chamfer technology to overcome bulging deformation of slab narrow side during mechanical reduction process. Int J Adv Manuf Tech2021; 121: 3229–3241.
12.
ZongNFMaSSunW, et al.Influence of differential reduction rate in adjacent roll reduction zone on internal cracks of high carbon bloom induced by mechanical soft reduction. P I Mech Eng C-J Mec2021; 235: 5653–5664.
13.
Ghobakhloo. Industry 4.0, digitization, and opportunities for sustainability. J Clean Prod2020; 252: 119869.
14.
WangJMaYZhangL, et al.Deep learning for smart manufacturing: Methods and applications. J Manuf Syst2018; 48: 144–156.
15.
AlpaydinE. Introduction to machine learning. 2nd ed.London, UK: The MIT Press, 2010.
16.
WatzingerJPesekAHuebnerN, et al.Mold expert-operational experience and future development. Ironmak Steelmak2005; 32: 208–212.
17.
ZhuMYLuoS. Some considerations for digitization develoment of high-efficiency continuous casting. Metallurgical Industry Automation2020; 47: 68–85.
18.
HeYZhouHLiY, et al.Multi-task learning model of continuous casting slab temperature based on DNNs and SHAP analysis. Metall Mater Trans B2024; 55: 5120–5132.
19.
LiQLanPWangH, et al.Formation and control of the surface defect in hypo-peritectic steel during continuous casting: A review. Int J Min Met Mater2023; 30: 2281–2296.
20.
CemernekDCemernekSGurschH, et al.Machine learning in continuous casting of steel: A state-of-the-art survey. J Intell Manuf2021; 33: 1561–1579.
21.
GeurtsPErnstDWehenkelL, et al.Extremely randomized trees. Machine Learning2006; 63: 3–42.
22.
SuthaharanS. Support vector machine. Machine Learning Models Algorithms for big Data Classification: Thinking with Examples for Effective Learning2016; 12: 207–235.
23.
ChenCHuiQPeiQ, et al.CRML: A convolution regression model with machine learning for hydrology forecasting. IEEE Access2019; 7: 133839–133849.
24.
AlloghaniMAl-JumeilyDMustafinaJ, et al.. A systematic review on supervised and unsupervised machine learning algorithms for data science. In: Supervised and unsupervised learning for data science. Springer US, 2020, pp.3–21.
25.
KameshwaranKMalarvizhiK. Survey on clustering techniques in data mining. Int J Comput Sci Inf Technol2014; 5: 2272–2276.
26.
MnihVKavukcuogluKSilverD, et al.Human-level control through deep reinforcement learning. Nature2015; 518: 529–533.
LiuZ. Deep Learning. In: Artificial intelligence for engineers. Cham: Springer, 2025, pp.108–168.
30.
PangGShenCCaoC, et al.Deep learning for anomaly detection: A review. ACM Comput Surv2021; 54: 1–38.
31.
LiWLiYZhangY. Study of mould breakout prediction technique in continuous casting production. In 2010 3rd International Conference on Biomedical Engineering and Informatics2010; 7: 2966–2970.
32.
RenTShiXLiD, et al.Research on breakout prediction system based on multilevel neural network. In 2010 International Conference on Electrical and Control Engineering2010: 1652–1655.
33.
TianQWangJWXueJS. Research on breakout prediction system based on multilevel neural network. IEEE Symposium on Robotics and Applications (ISRA)2012: 188–190.
34.
JiCCaiZZTaoNB, et al.Molten steel breakout prediction based on genetic algorithm and BP neural network in continuous casting process. Proceedings of the 31st Chinese Control Conference China:Chinese Control Conference2012: 3402–3406.
35.
ZhangBGZhangRZWangG, et al.Breakout prediction for continuous casting using genetic algorithm-based back propagation neural network model. Int J Model Identif2012; 16: 199–205.
36.
TirianGOFilipIProsteanG. Adaptive control system for continuous steel casting based on neural networks and fuzzy logic. Neurocomputing2014; 125: 236–245.
37.
HeFHeDFDengZH, et al.Development and application of mould breakout prediction system with online thermal map for steel continuous casting. Ironmak Steelmak2014; 42: 194–208.
38.
WangGYinSFLiS, et al.Breakout prediction model for continuous casting based on support vector machine method. Journal of Yanshan University2015; 39: 22–30.
39.
SalahBZoheirMSlimaneZ, et al.Inferential sensor-based adaptive principal components analysis of mould bath level for breakout defect detection and evaluation in continuous casting. Appl Soft Comput2015; 34: 120–128.
40.
AnsariMOSamantrayRGhoseJ. Neural network based breakout prediction system in continuous casting shop. Applied Mechanics and Materials2015; 813-814: 550–556.
41.
ZhangBGZhangXFanL. Breakout prediction based on BP neural network in continuous casting process. MATEC Web of Conferences2016; 61: 05020.
42.
LiuYWangXDDuFM, et al.Computer vision detection of mold breakout in slab continuous casting using an optimized neural network. Int J Adv Manuf Tech2017; 88: 557–564.
43.
AnsariMOGhoseJKumarR. Neural network based breakout predicting system for all four strands of caster in a continuous casting shop-A case study. Advances in Computational Intelligence2017; 509: 89–99.
44.
FaizullinAZymblerMLieftuchtD, et al.Use of deep learning for sticker detection during continuous casting. Global Smart Industry Conference2018: 1–6.
45.
AnnapureddyRRBhattacharyaAKReddyM. Adaptive critic design for extreme learning machines applied to noisy and drifting industrial processes. IEEE symposium Series on Computational Intelligence2018: 327–334.
46.
HeFZhangL. Mold breakout prediction in slab continuous casting based on combined method of GA-BP neural network and logic rules. Int J Adv Manuf Tech2018; 95: 4081–4089.
47.
DuanHYWangXDBaiY, et al.Integrated approach to density-based spatial clustering of applications with noise and dynamic time warping for breakout prediction in slab continuous casting. Metall Mater Trans B2019; 50: 2343–2353.
48.
DuanHYWangXDBaiY, et al.Development of prediction method for mold sticking breakout based on density-based spatial clustering of applications with noise and dynamic time warping. Chinese Journal of Engineering2020; 42: 348–357.
49.
DuanHYWangXDBaiY, et al.Development of sticking breakout prediction method based on hierarchical clustering of temperature timing characteristics in continuous casting. Journal of Mechanical Engineering2020; 56: 250–256.
50.
DuanHYWangXDBaiY, et al.Modeling of breakout prediction approach integrating feature dimension reduction with K-means clustering for slab continuous casting. Int J Adv Manuf Tech2020; 109: 2707–2718.
51.
TianYPLiubY. Intelligent breakout prediction method based on support vector machine. Journal of Physics2020; 1653: 012052.
52.
DuanHYWangXDBaiY, et al.Application of k-means clustering for temperature timing characteristics in breakout prediction during continuous casting[J]. Int J Adv Manuf Tech2020; 106: 4777–4787.
53.
AnsariMOGhoseJChattopadhyayaS, et al.An intelligent logic-based mold breakout prediction system algorithm for the continuous casting process of steel: A novel study. Micromachines2022; 13: 2148–2169.
54.
WangYYWangXDYaoM. Integrated model of ACWGAN-GP and computer vision for breakout prediction in continuous casting. Metall Mater Trans B2020; 53: 2873–2883.
55.
WangRRWangMWangZL, et al.Mechanism and forecast model of sticker breakout in continuous casting. China Metallurgy2023; 33: 138.
56.
ShiCYGuoSYChenJ, et al.Breakout prediction based on twin support vector machine of improved whale optimization algorithm. ISIJ Int2020; 63: 880–888.
ZhangBYuHJieZ, et al.Research on time series steel leakage prediction model based on TS-GA optimization decision tree. JOM-US2024; 76: 6775–6784.
59.
YuHZhangBWuH, , et al.Research on a steel leakage prediction model based on one vs rest genetic algorithm optimization decision tree. Special Steel2024; 45: 112–117.
60.
ZhangBMaBShengW, et al.Research on LFFA-BP neural network model in breakout prediction. Metall Res Technol2024; 121: 259–266.
61.
LiuYMaZWangX, et al.Analysis and prediction of sticker breakout based on XGBoost forward iterative model. ISIJ Int2024; 64: 1272–1278.
62.
LiuYMaZWangX, et al.Sticker breakout recognition based on temperature characteristics and stacking multi-classifier model. Ironmak Steelmak2024; 51: 703–711.
63.
ChangHQiBZhangY, et al.Application of breakout prediction system for VAI mould in continuous casting. Angang Technology2011; 371: 45–48.
64.
ZhiJHuangKTianZ, et al.Progress in breakout prediction technique for slab caster at baosteel. Baogang Technology2007; 6: 69–72.
65.
WangJZhangTGanM, et al.Development and application of constant casting speed technology in slab casting. China Metallurgy2012; 22: 26–33.
66.
YeXMWuXGuoYK. Real-time quality prediction of casting billet based on random forest algorithm. 2018 IEEE International Conference on Progress in Informatics and Computing (PIC)2018: 140–143.
67.
VarfolomeevIAErshovEVVinogradovaLN. Statistical control of defects in a continuously cast billet based on machine learning and data analysis methods. Automat Rem Contr2018; 79: 1450–1457.
68.
CongJQQiuSTMinJZ, et al.Online judgment of longitudinal facial cracking on slab based on LMBP-MIV. Steelmaking2019; 35: 59–65.
69.
KongYWChenDFLiuQ, et al.A prediction model for internal cracks during slab continuous casting. Metals2019; 9: 587.
70.
ZouLLZhangJSHanYS, et al.Internal crack prediction of continuous casting billet based on principal component analysis and deep neural network. Metals2019; 11: 1976.
71.
DuanHYWeiJJQiL, et al.Longitudinal crack detection approach based on principal component analysis and support vector machine for slab continuous casting. Steel Res Int2021; 92: 2100168.
72.
DuanHYWangXDYaoM, et al.Predicting longitudinal crack of slab based on dynamic time warping and k-nearest neighbor. Continuous Casting2021; 4: 66–71.
73.
ZhangHDuanHYWangXD, et al.Longitudinal crack prediction method of continuous cast slab based on random forest and clustering. Continuous Casting2022; 6: 21–28.
74.
SalaDADeyneAVYMannensE, et al.Hybrid-Input FCN-CNN-SE for industrial applications: Classification of longitudinal cracks during continuous casting. Metals2023; 13: 1699.
75.
LiuYJiangLShiJ, et al.Recognition of longitudinal cracks on slab surfaces based on particle swarm optimization and eXtreme gradient boosting model. Processes2024; 12: 1087.
76.
NorrenaJLouhenkilpiSVisuriVV, et al.Coupling of solidification and heat transfer simulations with interpretable machine learning algorithms to predict transverse cracks in continuous casting of steel. Steel Research Int2024; 95: 2300529.
77.
DengXXLiHBZhouHC, et al.Development and applications of online prediction of longitudinal cracks. The 24th (2023) National Steelmaking Academic Conference2023: 311–313.
78.
BaratiHWuMKharichaA, et al.A transient model for nozzle clogging[J]. Powder Technol2018; 329: 181–198.
79.
WangRBLiHGuerraF, et al.Predicting quantitative indices for SEN clogging in continuous casting using long short-term memory time-series model. ISIJInt2022; 62: 2311–2318.
80.
KutheSOñaIAGlaserB. Adaptive neuro-fuzzy inference system-long short-term memory hybrid model to forecast castability of Al-killed steel prior to continuous casting. Steel Res Int2024; 95: 2400220.
81.
DinizAPMCiarelliPMSallesEOT, et al.Use of deep neural networks for clogging detection in the submerged entry nozzle of the continuous casting. Expert Syst Appl2024; 238: 121963.
82.
SahaRoyPDTiwari PK. Knowledge discovery and predictive accuracy comparison of different classification algorithms for mould level fluctuation phenomenon in thin slab caster. J Intell Manuf2016; 30: 241–254.
83.
LeiZFSuWB. Mold level predict of continuous casting using hybrid EMD-SVR-GA algorithm. Processes2019; 7: 177.
84.
SuWBLeiZFYangLD, et al.Mold-level prediction for continuous casting using VMD-SVR. Metals2019; 9: 458.
85.
SuWBLeiZF. Mold-level prediction based on long short-term memory model and multi-mode decomposition with mutual information entropy. Adv Mech Eng2019; 11: 1053.
86.
XuMLiuJJLeiH, et al.Prediction of mold level fluctuation based on BP neural network optimized by whale optimization algorithm. Metallurgical Industry Automation2023; 47: 66–72.
87.
WuXJKangHJYuanS, et al.Anomaly detection of liquid level in mold during continuous casting by using forecasting and error generation. Applied Science2023; 13: 7457.
88.
JiangLHWangAGTianNY, et al.BP Neural network of continuous casting technological parameters and secondary dendrite arm spacing of spring steel. J Iron Steel Res Int2021; 18: 25–29.
89.
AhmadIKanoMHasebeS, et al.Design of inner and outer gray-box models to predict molten steel temperature in Tundish. 10th IFAC International Symposium on Dynamics and Control of Process Systems2023: 744–749.
90.
García NietoPGarcáa-GonzaloEÁlvarez AntónJ, et al.A comparison of several machine learning techniques for the centerline segregation prediction in continuous cast steel slabs and evaluation of its performance[J]. J Comput Appl Math2018; 330: 877–895.
91.
LiFWuJQDongF, et al.Ensemble machine learning systems for the estimation of steel quality control. IEEE International Conference on Big Data (Big Data)2018: 2245–2252.
92.
MiriyalSSSubramanianVRMitraK. TRANSFORMANN For online optimization of complex industrial processes: Casting process as case study. Eur J Oper Res2018; 264: 294–309.
93.
Takalo-MattilaJHeiskanenMKyllonenV, et al.Explainable steel quality prediction system based on gradient boosting decision trees. IEEE Access2022; 10: 68099–68110.
94.
ZhouYJXuKHeF, et al.Application of time series data anomaly detection based on deep learning in continuous casting process. ISIJ Int2022; 62: 689–698.
95.
JiYWangWLZhouLJ, et al.Prediction and feature analysis of entrapped slag defect on casting slab based on optimized xgboost model. Metall Mater Trans B2024; 55: 2026–2036.
96.
ZhangYXGaoZGSunJC, et al.Machine-Learning algorithms for process condition data-based inclusion prediction in continuous-casting process: A case study. Sensors2023; 23: 6719.
97.
GaoYPGaoLLiXY, et al.A semi-supervised convolutional neural network-based method for steel surface defect recognition[J]. Robotics and Computer-Integrated Manufacturing2020; 61: 101825.
98.
MengXLLuoSWangWL, et al.A detection model for corner cracks of continuous casting strand based on deep learning[J]. Ironmaking & Steelmaking2022; 49: 1048.
99.
MaZHZengKChenB, et al.Surface defect detection algorithm for continuous casting billets based on improved YOLOv7. China Metallurgy2024; 34: 101.
100.
AhmadIKanoMHasebeS, et al.Design of inner and outer gray-box models to predict molten steel temperature in tundish. In: 10th IFAC international symposium on dynamics and control of process systems. Mumbai, India: Elsevier, 2023, pp.744–749.
101.
ChoiKYiJParkC, et al.Deep learning for anomaly detection in time-series data: Review, analysis, and guidelines. IEEE Access2021; 9: 120043–120065.
102.
MaschlerBWeyrichM. Deep transfer learning for industrial automation: A review and discussion of new techniques for data-driven machine learning. IEEE Ind Electron M2021; 15: 65–75.
103.
AlzubaidiLZhangJHumaidiAJ, et al.Review of deep learning: Concepts, CNN architectures, challenges, applications, future directions. J Big Data2021; 8: 1–74.
104.
MehrishAMajumderNBharadwajR, et al.Deep transfer learning for industrial automation: A review and discussion of new techniques for data-driven machine learning. IEEE Ind Electron M2021; 15: 65–75.
105.
HochreiterSSchmidhuberJ. Long short-term memory. Neural Comput1997; 9: 1735–1780.
106.
ArrietaABDíaz-RodríguezNDel SerJ, et al.Explainable artificial intelligence (xai): Concepts, taxonomies, opportunities and challenges toward responsible ai. Inform Fusion2020; 58: 82–115.
