Application of deep learning for predicting carbon segregation in large-diameter continuously cast steel billets

Abstract

Carbon segregation is a persistent defect in continuous casting of large-diameter steel billets, leading to deteriorated mechanical properties and compromised service reliability. Conventional empirical or machine learning models generally estimate segregation indices but cannot resolve local variations of carbon distribution across billet sections. In this work, a microstructure-informed convolutional neural network (CNN) framework is proposed to predict and map carbon segregation in 600 mm round 42CrMo steel billets. A comprehensive dataset comprising microstructural images and corresponding carbon content measurements was established. The customized CNN achieved a testing accuracy of 81.3% with a mean absolute error of 0.012 wt.% and showed good robustness in out-of-sample validation. Compared with transfer learning models (VGG16, VGG19, etc.), the customized architecture exhibited superior generalization on this domain-specific dataset. Contrast-enhanced imaging significantly improved predictive performance, while Gradient-weighted Class Activation Mapping visualizations highlighted key microstructural regions correlated with carbon distribution, providing interpretability. This study demonstrates a proof-of-concept methodology to achieve quantitative mapping of segregation patterns in large-diameter 42CrMo billets, offering a complementary tool to traditional metallurgical analysis and providing a workflow that may support future data-driven research on segregation formation mechanisms and process optimization in steel casting when extended to additional steels and casting conditions.

Keywords

Continuous casting / carbon segregation / deep learning / convolutional neural network

References

[1] Liu H.,Cheng Z.,Yu W.,Zhou Z.,Cheng L.,Cai Q.. Effect of high-temperature reduction pretreatment on internal quality of 42CrMo casting billet J. Iron Steel Res. Int. 2020 28 693 702

[2] Li G.,Ji C.,Zhu M.. Prediction of internal crack initiation in continuously cast blooms Metall. Mater. Trans. B. 2021 52 1164 78

[3] Kong Y.,Chen D.,Liu Q.,Long M.. A prediction model for internal cracks during slab continuous casting Metals 2019 9 587

[4] Thomas B. G.. Review on modeling and simulation of continuous casting Steel Res. Int. 2017 89 1700312 12848349

[5] Jiang D.,Wang W.,Luo S.,Ji C.,Zhu M.. Mechanism of macrosegregation formation in continuous casting slab: a numerical simulation study Metall. Mater. Trans. B. 2017 48 3120 31

[6] Sun H.,Zhang J.. Study on the Macrosegregation behavior for the bloom continuous casting: model development and validation Metall. Mater. Trans. B. 2013 45 1133 49

[7] Zhang Z.,Wu M.,Zhang H..et al. Modeling of the as-cast structure and macrosegregation in the continuous casting of a steel billet: Effect of M-EMS J. Mater. Process. Technol. 2022 301 117434

[8] Dong Q.,Zhang J.,Qian L.,Yin Y.. Numerical modeling of macrosegregation in round billet with different microsegregation models ISIJ Int. 2017 57 814 23

[9] Hatič V.,Mavrič B.,Šarler B.. Simulation of macrosegregation in direct-chill casting - A model based on meshless diffuse approximate method Eng. Anal. Boundary Elem. 2020 113 191 203

[10] Geng X.,Wang F.,Wu H. H..et al. Data-driven and artificial intelligence accelerated steel material research and intelligent manufacturing technology MGE Advances 2023 1 e10

[11] Wang H.,Gao S.,Wang B..et al. Recent advances in machine learning-assisted fatigue life prediction of additive manufactured metallic materials: a review J. Mater. Sci. Technol. 2024 198 111 36

[12] Zhang N.,He A.,Zhang G..et al. Interpretable machine learning-assisted design of Fe-based nanocrystalline alloys with high saturation magnetic induction and low coercivity J. Mater. Sci. Technol. 2024 188 73 83

[13] Zhang Y.,Ren K.,Wang W. Y..et al. Discovering the ultralow thermal conductive A₂B₂O₇-type high-entropy oxides through the hybrid knowledge-assisted data-driven machine learning J. Mater. Sci. Technol. 2024 168 131 42

[14] Zhang Y.,Wen C.,Dang P.,Lookman T.,Xue D.,Su Y.. Toward ultra-high strength high entropy alloys via feature engineering J. Mater. Sci. Technol. 2024 200 243 52

[15] Wang C.,Fu H.,Jiang L.,Xue D.,Xie J.. A property-oriented design strategy for high performance copper alloys via machine learning NPJ Comput. Mater. 2019 5 87

[16] Song K.,Yan F.,Ding T.,Gao L.,Lu S.. A steel property optimization model based on the XGBoost algorithm and improved PSO Comput. Mater. Sci.。 2020 174 109472

[17] Wen C.,Zhang Y.,Wang C..et al. Machine learning assisted design of high entropy alloys with desired property Acta Mater. 2019 170 109 17 11068641

[18] Wu Q.,Wang Z.,Hu X..et al. Uncovering the eutectics design by machine learning in the Al–Co–Cr–Fe–Ni high entropy system Acta Mater. 2020 182 278 86

[19] Liu Y.,Wu J.,Wang Z..et al. Predicting creep rupture life of Ni-based single crystal superalloys using divide-and-conquer approach based machine learning Acta Mater. 2020 195 454 67

[20] Li S.,Dong Z.,Jin J..et al. Optimal design of high-performance rare-earth-free wrought magnesium alloys using machine learning MGE Advances 2024 2 e45

[21] Shi B.,Lookman T.,Xue D.. Multi-objective optimization and its application in materials science MGE Advances 2023 1 e14

[22] Gou W.,Shi Z. Z.,Zhu Y..et al. Multi-objective optimization of three mechanical properties of Mg alloys through machine learning MGE Advances 2024 2 e54

[23] Zou L.,Zhang J.,Liu Q.,Zeng F.,Chen J.,Guan M.. Prediction of central carbon segregation in continuous casting billet using a regularized extreme learning machine model Metals 2019 9 1312

[24] Zou L.,Zhang J.,Han Y.,Zeng F.,Li Q.,Liu Q.. Internal crack prediction of continuous casting billet based on principal component analysis and deep neural network Metals 2021 11 1976

[25] Xu Z.,Liu X.,Zhang K.. Mechanical properties prediction for hot rolled alloy steel using convolutional neural network IEEE Access 2019 7 47068 78

[26] Zhang Q.,Wang Y.. Research on mechanical property prediction of hot rolled steel based on lightweight multi-branch convolutional neural network Mater. Today Commun. 2023 37 107445

[27] Ma Y.,Deng C.,Sun Z.,Gong B.,Liu Y.. Prediction of sequential stress-strain fields in dual-phase steels via convolutional neural network Mater. Today Commun. 2025 46 112645

[28] Zhu L.,Luo Q.,Chen Q..et al. Prediction of ultimate tensile strength of Al-Si alloys based on multimodal fusion learning MGE Advances 2024 2 e26

[29] Wang W. Y.,Zhang S.,Li G..et al. Artificial intelligence enabled smart design and manufacturing of advanced materials: the endless Frontier in AI⁺ era MGE Advances 2024 2 e56

[30] Zong B.,Li J.,Zhou C.,Wang P.,Tang B.,Yuan R.. Enhancing creep rupture life prediction of high-temperature titanium alloys using convolutional neural networks MGE Advances 2024 2 e68

[31] Xu N.,Wang L.,Hu J..et al. Enabling strong and formable advanced high-strength steels through inherited homogeneous microstructure Scr. Mater. 2025 259 116560

[32] Yang Z.,Li Y.,Wei X.,Wang X.,Wang C.. Martensite start temperature prediction through a deep learning strategy using both microstructure images and composition data Materials (Basel). 2023 16 932 PMC9917892

[33] Lee S. Y.,Tama B. A.,Choi C.,Hwang J.,Bang J.,Lee S.. Spatial and sequential deep learning approach for predicting temperature distribution in a steel-making continuous casting process IEEE Access 2020 8 21953 65

[34] Lu Z.,Ren N.,Xu X..et al. Real-time prediction and adaptive adjustment of continuous casting based on deep learning Commun. Eng. 2023 2 34 PMC10955886

[35] Lian G.,Sun Q.,Liu X..et al. Automatic recognition and intelligent analysis of central shrinkage defects of continuous casting billets based on deep learning J. Iron Steel Res. Int. 2023 30 937 48

[36] Wei X.,Van Der Zwaag S.,Jia Z.,Wang C.,Xu W.. On the use of transfer modeling to design new steels with excellent rotating bending fatigue resistance even in the case of very small calibration datasets Acta Mater. 2022 235 118103

[37] Selvaraju R. R.,Cogswell M.,Das A.,Vedantam R.,Parikh D.,Batra D.. Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization. In 2017 IEEE International Conference on Computer Vision (ICCV), Venice, October 22-29, 2017; IEEE, 2017, pp 618-26 12183563