Microstructure and Property Prediction of Hot-Rolled Steel: Development and Prospects from Physical Models to Human-Machine Hybrid Intelligence

doi:10.12068/j.issn.1005-3026.2025.20250092

Abstract

Abstract:

The research progress of steel microstructure and property prediction models was reviewed， and the hot-rolled industrial model driven by human-machine hybrid intelligence and its components were introduced. By comprehensively utilizing physical metallurgy principles and artificial intelligence technologies， the microstructure evolution in the rolling process was deciphered. In addition， typical application cases of hot-rolled industrial models driven by human-machine hybrid intelligence were introduced in terms of three aspects： microstructure evolution and mechanical property prediction of hot-rolled steel， alloy composition reduction design of high-strength steel， and efficient rolling process development of wide thick plates. This provides references for promoting the rational design of steel research and development from experience-based trial and error to be driven by human-machine hybrid intelligence.

Key words: human-machine hybrid intelligence, microstructure evolution, property prediction, industrial model, hot rolling

CLC Number:

TB 3

Si-wei WU, Xiao-guang ZHOU, Zhen-yu LIU, Guo-dong WANG. Microstructure and Property Prediction of Hot-Rolled Steel: Development and Prospects from Physical Models to Human-Machine Hybrid Intelligence[J]. Journal of Northeastern University(Natural Science), 2025, 46(8): 11-19.

Figures/Tables 6

Fig.1 Flow chart of hot-rolled industrial model of steel based on human-machine hybrid intelligence

Fig.2 Calculation results of microstructure evolution during hot rolling process of S420MC

Fig.3 Online prediction accuracy of mechanical properties of high-strength steel

Fig.4 Process parameters and mechanical properties of Q460C along length direction

Fig.5 Application effect of reduction of main alloy elements in high-strength steel

Fig.6 Comparison of temperature field before and after process optimization of high-strength ship plate steel （w（C）:0.17%；w（Si）:0.28%；w（Mn）:1.45%；thickness:20 mm）

References 48

[1]	丁敬国，金利，孙丽荣，等. 板带热轧过程智能化建模方法的研究现状与展望［J］. 冶金自动化， 2022， 46（6）： 25-37.
	Ding Jing-guo， Jin Li， Sun Li-rong， et al. Research status and prospect of intelligent modeling method for hot strip rolling process ［J］. Metallurgical Industry Automation， 2022， 46（6）： 25-37.
[2]	孙一康. 带钢热连轧的模型与控制［M］. 北京：冶金工业出版社， 2002.
	Sun Yi-kang. Model and control of hot strip rolling ［M］. Beijing： Metallurgical Industry Press， 2002.
[3]	刘玠，孙一康. 带钢热连轧计算机控制［M］. 北京：机械工业出版社， 1997.
	Liu Jie， Sun Yi-kang. Computer control of hot strip rolling ［M］. Beijing： China Machine Press， 1997.
[4]	刘振宇，曹光明，周晓光，等. 组织性能预测技术及其在智能热轧中的核心作用［J］. 轧钢， 2019， 36（2）： 1-7.
	Liu Zhen-yu， Cao Guang-ming， Zhou Xiao-guang， et al. The predicting technologies for microstructure and properties and their core roles in smart hot rolling processes ［J］. Steel Rolling， 2019， 36（2）： 1-7.
[5]	Ma L Q， Yuan X Q， Jiao S H， et al. Modeling of dynamic recrystallization and flow stress of Nb-bearing steels［J］. Multidiscipline Modeling in Materials and Structures， 2007， 3（1）： 27-41.
[6]	Siciliano F J， Minami K， Maccagno T M， et al. Mathematical modeling of the mean flow stress， fractional softening and grain size during the hot strip rolling of C-Mn steels［J］. ISIJ International， 1996， 36（12）： 1500-1506.
[7]	Martin H， Amoako-Yirenkyi P， Pohjonen A， et al. Statistical modeling for prediction of CCT diagrams of steels involving interaction of alloying elements［J］. Metallurgical and Materials Transactions B， 2021， 52（1）： 223-235.
[8]	Van Bohemen S M C， Sietsma J. Modeling of isothermal bainite formation based on the nucleation kinetics［J］. International Journal of Materials Research， 2008， 99（7）： 739-747.
[9]	Sellars C M， Whiteman J A. Recrystallization and grain growth in hot rolling［J］. Metal Science， 1979， 13（3/4）： 187-194.
[10]	Sellars C M. The kinetics of softening processes during hot working of austenite［J］. Czechoslovak Journal of Physics B， 1985， 35（3）： 239-248.
[11]	Wang L， Ji L K， Yang K， et al. The flow stress-strain and dynamic recrystallization kinetics behavior of high-grade pipeline steels［J］. Materials， 2022， 15（20）： 7356.
[12]	Zurob H S， Hutchinson C R， Brechet Y， et al. Rationalization of the softening and recrystallization behaviour of microalloyed austenite using mechanism maps［J］. Materials Science and Engineering： A， 2004， 382（1/2）： 64-81.
[13]	Zurob H S， Hutchinson C R， Brechet Y， et al. Modeling recrystallization of microalloyed austenite： effect of coupling recovery， precipitation and recrystallization［J］. Acta Materialia， 2002， 50（12）： 3077-3094.
[14]	Collins J， Piemonte M， Taylor M， et al. A rapid， open-source CCT predictor for low-alloy steels， and its application to compositionally heterogeneous material［J］. Metals， 2023， 13（7）： 1168.
[15]	Zhang S H， Deng L， Che L Z. An integrated model of rolling force for extra-thick plate by combining theoretical model and neural network model［J］. Journal of Manufacturing Processes， 2022， 75： 100-109.
[16]	Shen S H， Guye D， Ma X P， et al. Multistep networks for roll force prediction in hot strip rolling mill［J］. Machine Learning with Applications， 2022， 7： 100245.
[17]	李元，刘文仲，孙一康. 神经元网络在热连轧精轧机组轧制力预报的应用［J］. 钢铁， 1996（1）： 54-57， 39.
	Li Yuan， Liu Wen-zhong， Sun Yi-kang. Application of neural network to predicting rolling force for the finisher ［J］. Iron and Steel， 1996（1）： 54-57， 39.
[18]	Dong Z S， Li X， Luan F， et al. Fusion of theory and data-driven model in hot plate rolling： a case study of rolling force prediction［J］. Expert Systems with Applications， 2024， 245： 123047.
[19]	Wang Q N， Song L B， Zhao J W， et al. Application of the gradient boosting decision tree in the online prediction of rolling force in hot rolling［J］. The International Journal of Advanced Manufacturing Technology， 2023， 125（1/2）： 387-397.
[20]	Rahaman M， Mu W Z， Odqvist J， et al. Machine learning to predict the martensite start temperature in steels［J］. Metallurgical and Materials Transactions A， 2019， 50（5）： 2081-2091.
[21]	Pattanayak S， Dey S， Chatterjee S， et al. Computational intelligence based designing of microalloyed pipeline steel［J］. Computational Materials Science， 2015， 104： 60-68.
[22]	Hu X B， Li H， Liu C， et al. Multi-objective design of Ni-B-Al master alloy by adaptive machine learning-driven aluminothermic reduction experiment［J］. Journal of Alloys and Compounds， 2025， 1010： 177403.
[23]	Conrad F， Stöcker J P， Signorini C， et al. Exploring design space： machine learning for multi-objective materials design optimization with enhanced evaluation strategies［J］. Computational Materials Science， 2025， 246： 113432.
[24]	Wu S W， Zhou X G， Ren J K， et al. Optimal design of hot rolling process for C-Mn steel by combining industrial data-driven model and multi-objective optimization algorithm［J］. Journal of Iron and Steel Research International， 2018， 25（7）： 700-705.
[25]	Pan G F， Wang F Y， Shang C L， et al. Advances in machine learning-and artificial intelligence-assisted material design of steels［J］. International Journal of Minerals， Metallurgy and Materials， 2023， 30（6）： 1003-1024.
[26]	Wang X J， Li X， Yuan H， et al. Prediction and analysis of mechanical properties of hot-rolled strip steel based on an interpretable machine learning［J］. Materials Today Communications， 2024， 40： 109997.
[27]	Song K， Yan F， Ding T， et al. A steel property optimization model based on the XGBoost algorithm and improved PSO［J］. Computational Materials Science， 2020， 174： 109472.
[28]	Diao Y P， Yan L C， Gao K W. A strategy assisted machine learning to process multi-objective optimization for improving mechanical properties of carbon steels［J］. Journal of Materials Science & Technology， 2022， 109： 86-93.
[29]	Jiang X， Jia B R， Zhang G F， et al. A strategy combining machine learning and multiscale calculation to predict tensile strength for pearlitic steel wires with industrial data［J］. Scripta Materialia， 2020， 186： 272-277.
[30]	Li H W， Li Y， Huang J， et al. Physical metallurgy guided industrial big data analysis system with data classification and property prediction［J］. Steel Research International， 2022， 93（8）： 2100820.
[31]	任鹏帆，王振华，贾燚，等. 机理和数据融合的304不锈钢极薄带轧制力模型［J］. 钢铁， 2024， 59（10）： 64-76.
	Ren Peng-fan， Wang Zhen-hua， Jia Yi， et al. Rolling force model for 304 stainless steel ultra-thin strip based on mechanism and data fusion［J］. Iron & Steel， 2024， 59（10）： 64-76.
[32]	李鑫，周晓光，曹光明，等.融合物理冶金学与机器学习的组织性能预测及热轧工艺优化［J］. 冶金自动化， 2023， 47（2）： 16-26.
	Li Xin， Zhou Xiao-guang， Cao Guang-ming， et al. Microstructure and properties prediction and optimization of hot rolling process based on physical metallurgy and machine learning［J］. Metallurgical Industry Automation， 2023， 47（2）： 16-26.
[33]	吴思炜. 基于工业大数据的热轧带钢组织性能预测与优化技术研究［D］. 沈阳：东北大学， 2018.
	Wu Si-wei. Research on microstructure and property prediction and optimization technology of hot rolled strips based on industrial big data［D］. Shenyang： Northeastern University， 2018.
[34]	Li X， Zhou X G， Cao G M， et al. Machine learning hot deformation behavior of Nb micro-alloyed steels and its extrapolation to dynamic recrystallization kinetics［J］. Metallurgical and Materials Transactions A， 2021， 52（7）： 3171-3181.
[35]	Jiang L， Fu H D， Zhang H T， et al. Physical mechanism interpretation of polycrystalline metals’ yield strength via a data-driven method： a novel Hall-Petch relationship［J］. Acta Materialia， 2022， 231： 117868.
[36]	Zhang X C， Gong J G， Xuan F Z. A physics-informed neural network for creep-fatigue life prediction of components at elevated temperatures［J］. Engineering Fracture Mechanics， 2021， 258： 108130.
[37]	王毅，李高楠，刘哲，等. 材料基因工程与智能科学：AI+时代无尽前沿［J］. 科技导报， 2025， 43（12）： 93-109.
	Wang Yi， Li Gao-nan， Liu Zhe， et al. Materials genome engineering and intelligent science： the endless frontier in AI+ era ［J］. Science & Technology Review， 2025， 43（12）： 93-109.
[38]	Li Y F， Wang Z H， Zhang L Y， et al. Arrhenius-type constitutive model and dynamic recrystallization behavior of V-5Cr-5Ti alloy during hot compression［J］. Transactions of Nonferrous Metals Society of China， 2015， 25（6）： 1889-1900.
[39]	Maccagno T M， Jonas J J， Hodgson P D. Spreadsheet modelling of grain size evolution during rod rolling［J］. ISIJ International， 1996， 36（6）： 720-728.
[40]	Gao Z W， Wu S W， Li X， et al. Modelling strain-induced precipitation kinetics of Nb （C， N） by symbolic regression machine learning［J］. Journal of Materials Research and Technology， 2025， 35： 1712-1721.
[41]	Cui C Y， Wang H， Gao X Y， et al. Machine learning model for thickness evolution of oxide scale during hot strip rolling of steels［J］. Metallurgical and Materials Transactions A， 2021， 52（9）： 4112-4124.
[42]	Cao Y， Cao G M， Cui C Y， et al. Modeling continuous cooling transformations for HSLA steels with physical metallurgy guided hereditary machine learning［J］. Metallurgical and Materials Transactions A， 2023， 54（12）： 4891-4904.
[43]	Cao Y， Wu S W， Tang S， et al. Dynamic deep learning to predict mechanical properties of high-strength low-alloy steels［J］. Metallurgical and Materials Transactions A， 2025， 56（1）： 168-179.
[44]	Choudhary A， Kumar M， Unune D R. Experimental investigation and optimization of weld bead characteristics during submerged arc welding of AISI 1023 steel ［J］. Defence Technology， 2019， 15（1）： 72-82.
[45]	Rao V D P， Ali S R S M， Ali S M Z M S， et al. Multi-objective optimization of cutting parameters in CNC turning of stainless steel 304 with TiAlN nano coated tool ［J］. Materials Today： Proceedings， 2018， 5（12）： 25789-25797.
[46]	Wu S W， Cao G M， Zhou X G， et al. High dimensional data-driven optimal design for hot strip rolling of C-Mn steels［J］. ISIJ International， 2017， 57（7）： 1213-1220.
[47]	崔春圆. 热轧板带材集成机器学习模型开发与应用［D］. 沈阳：东北大学， 2023.
	Cui Chun-yuan. The development and application of integrated machine learning models for hot rolled plate and strip ［D］. Shenyang： Northeastern University， 2023.
[48]	Cao Y， Zhang C D， Tang S， et al. Machine learning to predict phase transformation products and their morphologies-application in design of lean high strength steel［J］. Materials & Design， 2025， 258： 114642.