This study developed an indicator prediction model for steel processes adapting to dynamic operating condition deviations. By combining just-in-time learning, ensemble learning techniques, and target similarity extraction, the model improves prediction accuracy and robustness. Validated on industrial rolling and sintering data, the model achieves up to 18% improvement over traditional models. Utilizing multi-dimensional parameters, the 6% error margin hit rates for yield and tensile strength reached 86% and 99% in rolling data, while the Al2O3 hit rate reached 96% in sintering. Notably, for boundary samples (top/bottom 25% quantiles), the model achieved a 56% relative improvement in hit rate. Furthermore, the model significantly enhances prediction robustness under dynamic operating deviations, reducing the accuracy fluctuation across time segments from 12% to 5%.
JiangTZhaoKZhaoW, et al.A joint model for hot-rolled strip quality in advance prediction. Ironmak Steelmak2023; 50: 1224–1233.
2.
SongLQingLXiaojieL, et al.Synthetically predicting the quality index of sinter using machine learning model. Ironmak Steelmak2020; 47: 828–836.
3.
de MatosSSda SilvaCAPeixotoJJM, et al.A hybrid approach using multiple linear regression and random forest regression to predict molten steel temperature in a continuous casting tundish. Ironmak Steelmak2023; 50: 1659–1667.
4.
ShiQTangJChuM. Process metallurgy and data-driven prediction and feedback of blast furnace heat indicators. Int J Miner Metall Mater2024; 31: 1228–1240.
5.
DuSMaXFanH, et al.Intelligent prediction and soft-sensing of comprehensive production indicators for iron ore sintering: a review. Comput Ind2025; 165: 104215.
6.
Diez-OlivanADel SerJGalarD, et al.Data fusion machine learning for industrial prognosis: trends and perspectives towards Industry 4.0. Inform Fusion2019; 50: 92–111.
7.
XieQSuvarnaMLiJ, et al.Online prediction of mechanical properties of hot rolled steel plate using machine learning. Mater Des2021; 197: 109201.
8.
KwakSKimJDingH, et al.Machine learning prediction of the mechanical properties of -tial alloys produced using random forest regression model. J Mater Res Technol2022; 18: 520–530.
9.
ChenRZengJYaoG, et al.Flow-stress model of 300m steel for multi-pass compression. Metals2020; 10: 438.
10.
XiongSYangNGuanH, et al.Combination of plasma acoustic emission signal and laser-induced breakdown spectroscopy for accurate classification of steel. Anal Chim Acta2025; 1336: 343496.
11.
ChenRZhangSLiuX, et al.A flow stress model of 300m steel for isothermal tension. Materials2021; 14: 252.
12.
ShenCWangCWeiX, et al.Physical metallurgy-guided machine learning and artificial intelligent design of ultrahigh-strength stainless steel. Acta Mater2019; 179: 201–214.
13.
HuangMJiaCShenC, et al.Deformation behavior and tensile properties of layered bis austenitic steel. JOM2026; 1–12.
14.
PengJXieSXiaJ, et al.Investigation of process and properties of Cu–Mn–Al alloy cladding deposited on 27SiMn steel via cold metal transfer. Crystals2025; 15: 858.
15.
LiYYangCSunY. Dynamic time features expanding and extracting method for prediction model of sintering process quality index. IEEE Trans Ind Inform2021; 18: 1737–1745.
16.
QiXMaCLiM, et al.A novel thermal error compensation framework towards precision manufacturing: integrating digital twin technology and edge server deployment. J Intell Manufactur2026; : 1–39.
17.
WangZTaoYZhangS, et al.Spatial spiral tube multi-roller bending: accurate axial prediction utilizing AWPSO–FECAM–LSTM framework. Expert Syst Appl2025; 128960.
18.
LiYSan MartínDWangJ, et al.A review of the thermal stability of metastable austenite in steels: martensite formation. J Mater Sci Technol2021; 91: 200–214.
19.
ZhangSZhaoC. Slow-feature-analysis-based batch process monitoring with comprehensive interpretation of operation condition deviation and dynamic anomaly. IEEE Trans Ind Electron2018; 66: 3773–3783.
20.
WidmerGKubatM. Learning in the presence of concept drift and hidden contexts. Mach Learn1996; 23: 69–101.
21.
StenmanA. Model on demand: Algorithms, analysis and applications. Linköping: Department of Electrical Engineering, Linköping University, 1999.
22.
BontempiGBirattariMBersiniH. Local learning for iterated time series prediction. In ICML. pp. 32–38.
23.
YangZGeZ. Rethinking the value of just-in-time learning in the era of industrial big data. IEEE Trans Ind Inform2021; 18: 976–985.
24.
DongXYuZCaoW, et al.A survey on ensemble learning. Front Comput Sci2020; 14: 241–258.
25.
ShengWQianJSongZ, et al.A review of just-in-time learning-based soft sensor in industrial process. Can J Chem Eng2024; 102: 1884–1898.
26.
GuoFLiuKHuangB. Just-in-time framework for robust soft sensing based on robust variational autoencoder. J Process Control2024; 143: 103325.
27.
ShaoWGeZSongZ. Bayesian just-in-time learning and its application to industrial soft sensing. IEEE Trans Ind Inform2019; 16: 2787–2798.
28.
DongJTianYzPengKx. Local multi-model integrated soft sensor based on just-in-time learning for mechanical properties of hot strip mill process. J Iron Steel Res Int2021; 28: 830–841.
29.
SongWCaoWLiuKZ, et al.A local-model integration approach to the transition state prediction of continuous annealing processes. IEEE Trans Ind Inform2025; 21: 743–751. DOI: 10.1109/TII.2024.3459050.
30.
HuJWuMCaoW, et al.Soft-sensing of burn-through point based on weighted kernel just-in-time learning and fuzzy broad-learning system in sintering process. IEEE Trans Ind Inform2024; 20: 7316–7324.
31.
WangPYinYZhouJ, et al.A semisupervised just-in-time learning framework based on local label propagation and its application to industrial virtual sensing. IEEE Sens J2023; 23: 24983–24992.
32.
UyanıkGKGülerN. A study on multiple linear regression analysis. Procedia-Soc Behav Sci2013; 106: 234–240.
33.
HeydariSMahmoudQH. Tiny machine learning on-device inference: a survey of applications, challenges, and future directions. Sensors2025; 25: 3191.
34.
JinFWuHLiuY, et al.Varying-scale HCA-DBSCAN-based anomaly detection method for multi-dimensional energy data in steel industry. Inf Sci (NY)2023; 647: 119479.
35.
LuH. Evaluating the performance of SVM, isolation forest, and DBSCAN for anomaly detection. ITM Web Conf2025; 70: 04012.
36.
ThengDBhoyarKK. Feature selection techniques for machine learning: a survey of more than two decades of research. Knowledge Inform Syst2024; 66: 1575–1637.
37.
IranzadRLiuX. A review of random forest-based feature selection methods for data science education and applications. Int J Data Sci Anal2025; 20: 197–211.
38.
ChenTGuestrinC. XGBoost: a scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining. pp. 785–794.
39.
LiSJinNDoganiA, et al.Enhancing LightGBM for industrial fault warning: an innovative hybrid algorithm. Processes2024; 12: 221.
40.
HollmannNMüllerSPuruckerL, et al.Accurate predictions on small data with a tabular foundation model. Nature2025; 637: 319–326.
41.
ChenWYangKYuZ, et al.A survey on imbalanced learning: latest research, applications and future directions. Artif Intell Rev2024; 57: 137.
42.
LiDLiuYHuangD, et al.A semisupervised soft-sensor of just-in-time learning with structure entropy clustering and applications for industrial processes monitoring. IEEE Trans Artif Intell2022; 4: 722–733.
43.
WangZLiJLiuX, et al.Diameter-adjustable mandrel for thin-wall tube bending and its domain knowledge-integrated optimization design framework. Eng Appl Artif Intell2025; 139: 109634.
