The strain-induced precipitation, recovery, and recrystallization interactions occurring during the rolling process of Nb micro-alloyed high-strength low-alloy (HSLA) steel significantly influence the evolution of austenite, thereby determining the final properties of the product. Therefore, establishing a highly accurate static recrystallization critical temperature (SRCT) model is crucial for setting the parameters of the hot rolling process. However, to date, a mathematical model that is both highly accurate and concise, specifically applicable to Nb micro-alloyed steel, has not been established. In this study, based on the SRCT experimental data of Nb micro-alloyed steel, the SRCT prediction model was constructed with physical metallurgy guidance and combined with symbolic regression machine learning (SRML) algorithm. The model uses the contents of dissolved elements such as Nb, C, N, Mn, Si, the solubility temperature (Ts), strain (ε), strain rate (), and austenite grain size (dγ) as input parameters. Compared to existing models, the SRCT prediction results of the proposed model shows a reduction in root mean square error (RMSE) from 37.1°C to 4.4°C and an increase in the correlation coefficient (R2) from 0.0279 to 0.9865. Additionally, the proposed model was used to analyze the effects of variables such as Si and Mn content in the steel, strain, and strain rate on the determination of SRCT, which were consistent with experimental results. Furthermore, the predictive accuracy of the SRCT model proposed in this study was further validated by combining additional experimental data.
LiXJiangQCuiC, et al. Physical metallurgy guided machine learning for strain-induced precipitation of Nb(C, N) based on the orthogonalized small data. Steel Res Int2023; 94(9): 1–14.
2.
MedinaSFQuispeAGómezM. Strain induced precipitation effect on austenite static recrystallisation in microalloyed steels. Mater Sci Technol2003; 19(1): 99–108.
3.
MedinaSFQuispeAGómezM. Model for static recrystallisation critical temperature in microalloyed steels. Mater Sci Technol2001; 17(5): 536–544.
4.
MedinaSFMancillaJE. Determination of static recrystallization critical temperature of austenite in microalloyed steels. ISIJ Int1993; 33(12): 1257–1264.
5.
MedinaSFMancillaJE. Static recrystallization modelling of hot deformed microlloyed steels at temperatures below the critical temperature. ISIJ Int1996; 36(8): 1077–1083.
6.
MedinaSFQuispeA. Influence of microalloy type and content on induced precipitation kinetics in microalloyed steels. Steel Res. Int1996; 67(6): 257–262.
7.
GómezMMedinaSFQuispeA, et al. Static recrystallization and induced precipitation in a low Nb microalloyed steel. ISIJ Int2002; 42(4): 423–431.
8.
MedinaSFQuispeA. Influence of strain on induced precipitation kinetics in microalloyed steels. ISIJ Int1996; 36(10): 1295–1300.
9.
SobotkaEKreycaJKahlenbergR, et al. Analysis of recrystallization kinetics concerning the experimental, computational, and empirical evaluation of critical temperatures for static recrystallization in Nb, Ti, and V microalloyed steels. Metals2023; 13(5): 884.
10.
MedinaSFQuispeA. Influence of strain rate on recrystallisation-precipitation interaction in V, Nb, and V-Ti microalloyed steels. Mater Sci Technol2000; 16(6): 635–642.
11.
MedinaSF. The influence of niobium on the static recrystallization of hot deformed austenite and on strain induced precipitation kinetics. Scr Metall Mater1995; 32(1): 43–48.
12.
GómezMRancelLMedinaSF, et al. Ti and Al on recrystallisation/precipitation interaction in microalloyed steels. Mater Sci Forum2010; 638–642: 3388–3393.
13.
MedinaSFGómezM. Nucleation rate and number of precipitates in V and Nb-microalloyed steels. Mater Sci Forum2014; 783–786: 783–1078.
14.
GómezMRancelLMedinaSF. Assessment of austenite static recrystallization and grain size evolution during multipass hot rolling of a niobium-microalloyed steel. Met Mater Int2009; 15(4): 689–699.
15.
MedinaSFGómezMGómezPP. Effects of V and Nb on static recrystallisation of austenite and precipitate size in microalloyed steels. J Mater Sci2010; 45(20): 5553–5557.
16.
MedinaSFQuispeAVallesP, et al. Recrystallization-precipitation interaction study of two medium carbon niobium microalloyed steels. ISIJ Int1999; 39(9): 913–922.
17.
MedinaSFD. Etermination of precipitation-time-temperature (PTT) diagrams for Nb, Ti or V micro-alloyed steels. J. Mater. Sci1997; 32(6): 1487–1492.
18.
MedinaSFQuispeAGomezM. Model for strain-induced precipitation kinetics in microalloyed steels. Metallurgical Mater Trans A2014; 45(3): 1524–1539.
19.
KoyamaSIshiiTNaritaK. Effects of Mn, Si, Cr and Ni on the solubility and precipitation of niobium carbide in iron austenite. J Jpn Inst Met1971; 35: 351089–351094.
20.
KurokawaSRuzzanteJEHeyAM, et al. Diffusion of Nb in Fe and Fe alloys. Met Sci1983; 17(9): 433–438.
21.
ZhouXGLiuZYYuanXQ, et al. Modeling of strain-induced precipitation kinetics and evolution of austenite grains in Nb microalloyed steels. J Iron Steel Res Int2008; 15(3): 65–69.
22.
DongJSicilianoFJrJonasJJ, et al. Effect of silicon on the kinetics of Nb(C, N) precipitation during the hot working of Nb-bearing steels. ISIJ Int2000; 40(6): 613–618.
23.
LlanosLPeredaBLópezB. Interaction between recovery, recrystallization, and NbC strain-induced precipitation in high-Mn steels. Metallurgical Mater Trans A2015; 46(11): 5248–5265.
24.
ZareAHosseiniRK. A breakthrough in creep lifetime prediction: Leveraging machine learning and service data. Scr Mater2024; 245: 116037.
25.
SaiNJRathorePChauhanA. Machine learning-based predictions of fatigue life for multi-principal element alloys. Scr Mater2023; 226: 226115214–226115221.
26.
WangMChenYZhangCL, et al. Length-scale effect on the hardness of metallic/ceramic multilayered composites: a machine learning prediction. Scr Mater2024; 242: 115921.
27.
YinJRaoZWuD, et al. Interpretable predicting creep rupture life of superalloys: enhanced by domain-specific knowledge. Adv Sci2024; 11: 2307982. DOI: 10.1002/advs.202307982.
28.
ShangCZhuDWuH-H, et al. A quantitative relation for the ductile-brittle transition temperature in pipeline steel. Scr Mater2024; 244: 116023.
29.
GuoWWangLZhuL, et al. Exploration of high-temperature oxidation resistance laws in ultra-high temperature boride ceramics through data-driven approaches. Corros Sci2024; 230: 111943.
30.
WangXLiSLiuF. Modeling for free dendrite growth based on physically-informed machine learning method. Scr Mater2024; 242: 242115918–242115923.
31.
MakkeNChawlaS. Interpretable scientific discovery with symbolic regression: a review. Artif Intell Rev2024; 57(1): 2–39. DOI: 10.1007/s10462-023-10622-0.
32.
AngelisDSofosFKarakasidisTE. Artificial intelligence in physical sciences: symbolic regression trends and perspectives. Arch Comput Methods Eng2023; 30(6): 3845–3865.
33.
ZhangZZhangYLiuS. Integrative approach of machine learning and symbolic regression for stability prediction of multicomponent perovskite oxides and high-throughput screening. Comput Mater Sci2024; 236: 112889.
34.
Montes de Oca ZapiainDLaneJMDCarrollJD, et al. Establishing a data-driven strength model for β-tin by performing symbolic regression using genetic programming. Comput Mater Sci2023; 218: 218.
35.
AugustoDABarbosaHJC. Symbolic regression via genetic programming. In: Proceedings. Vol.1. Sixth Brazilian Symposium on Neural Networks. Rio de Janeiro, Brazil, 2000, pp. 173–178.
36.
ZhouSYangBXiaoS, et al. Interpretable machine learning method for modelling fatigue short crack growth behaviour. Met Mater Int2024; 30: 1944–1964.
37.
YinWJ. Density functional theory-free descriptor for the practical discovery of perovskite catalysts. Comput Mater Sci2021; 193: 193110342–193110347.
38.
WangCZhangYWenC, et al. Symbolic regression in materials science via dimension-synchronous-computation. J Mater Sci Technol2022; 122: 77–83.
39.
LundbergSMLeeS. A unified approach to interpreting model predictions. In: 31st Conference on Neural Information Processing Systems (NIPS 2017), CA, 2017, pp. 1–10.
40.
LuSZhouQOuyangY, et al. Accelerated discovery of stable lead-free hybrid organic-inorganic perovskites via machine learning. Nat Commun2018; 9(1): 3405.
41.
ZhouCYuanRSuB, et al. Creep rupture life prediction of high-temperature titanium alloy using cross-material transfer learning. J Mater Sci Technol2024; 178: 39–47.
42.
GómezMMedinaSF. Role of microalloying elements in the microstructure of hot rolled steels. Int J Mater Res2011; 102(10): 1197–1207.
43.
GómezMQuispeAMedinaSF. Influence of the microalloying elements on the temporary inhibition of static recrystallization by strain-induced precipitates. Steel Res Int2014; 85(10): 1440–1445.
44.
HuangYLiuJZhuC, et al. An explainable machine learning model for superalloys creep life prediction coupling with physical metallurgy models and CALPHAD. Comput Mater Sci2023; 227: 112283.
45.
SicilianoFJonasJJ. Mathematical modeling of the hot strip rolling of microalloyed Nb, multiply-alloyed Cr-Mo, and plain C-Mn steels. Metallurgical Mater Trans A2000; 31(2): 511–530.
46.
AkbenMGWeissIJonasJJ. Dynamic precipitation and solute hardening in A V microalloyed steel and two Nb steels containing high levels of Mn. Acta Metallurgica1981; 29(1): 111–121.
