Continuous casting process control is crucial for enhancing the quality of steel. Center segregation, a key indicator of quality, plays a significant role in ensuring the quality of cord steel. However, the complexities of the continuous casting process, such as data silos, delayed inspections, uneven sampling and non-linearity, pose challenges to making timely improvements in quality. This study introduces an ensemble learning algorithm called LOF-KPCA-XGBoost, which combines Local Outlier Factor (LOF) sample weight, Kernel Principal Component Analysis (KPCA) and eXtreme Gradient Boosting (XGBoost) for online prediction of the center segregation coefficient of continuous casting billets. The algorithm achieves an accuracy of 90% and 98% within ±3% and ±5% relative error, respectively, with an average relative error of 1.6%. A sensitivity analysis method that leverages multivariable feature fluctuations is proposed to identify the process parameters that affect billet quality. The proposed method assists steel enterprises in improving the quality of cord steel billets.
KirharaK. Production technology of wire rod for high tensile strength steel cord. Kobelco Technol. Rev2011; 30: 62–65.
2.
YuJ. Online quality prediction of nonlinear and non-Gaussian chemical processes with shifting dynamics using finite mixture model based Gaussian process regression approach. Chem Eng Sci2012; 82: 22–30.
3.
MatskoI. Adaptive fuzzy decision tree with dynamic structure for automatic process control system of continuous cast billet production. IOSR J Eng2012; 2: 53–55.
4.
FernandezAMendezLBlancoJ, et al.Application of techniques of dimension reduction to predict the steel quality at the end of the secondary steelmaking. In: Industry Applications Conference. 2005, pp.537–542: IEEE.
5.
WangWJiCLuoS, et al.Modeling of dendritic evolution of continuously cast steel billet with cellular automaton. Metall Mater Trans B2018; 49: 200–212.
6.
ChenHLongMChenD, et al.Numerical study on the characteristics of solute distribution and the formation of centerline segregation in continuous casting (CC)slab. Int J Heat Billet Qual Transfer2017; 126: 864–853.
7.
Jiang DBWang WLLuoS, et al.Numerical simulation of slab centerline segregation with mechanical reduction during continuous casting process. Int J Heat Billet Qual Transfer2018; 122: 315–323.
8.
Jiang DBWang WLLuoS, et al.Mechanism of macrosegregation formation in continuous casting slab: a numerical simulation study. Metall Mater Trans B2017; 48: 3120–3131.
9.
Choudhary SKGangulySSenguptaA, et al.Solidification morphology and segregation in continuously cast steel slab. J Mater Process Technol2017; 243: 312–321.
10.
RenTShiXLiD, et al.Research on breakout prediction system based on multilevel neural network. In: International Conference on Electrical & Control Engineering, 2010, 407, pp.1652–1655: IEEE Computer Society.
11.
CemernekDCemernekSGurschH, et al.Machine learning in continuous casting of steel: a state-of-the-art survey. J Intell Manuf2021; 33: 1561–1579.
12.
MehdiyevNLahannJEmrichA, et al.Time series classification using deep learning for process planning: a case from the process industry. Proc Comput Sci2017; 114: 242–249.
13.
VarfolomeevIAErshovEVVinogradovaLN. Statistical control of defects in a continuously cast billet based on machine learning and data analysis methods. Autom Remote Control2018; 79: 1450–1457.
14.
García NietoPGarcáa-GonzaloEÁlvarez AntónJ. A comparison of several machine learning techniques for the centerline segregation prediction in continuous cast steel slabs and evaluation of its performance. J Comput Appl Math2018; 330: 877–895.
15.
García NietoPSuárezVAntónJ, et al.A new predictive model of centerline segregation in continuous cast steel slabs by using multivariate adaptive regression splines approach. Materials2015; 8: 3562–3583.
16.
JiangLHWangAGTianNY, et al.BP Neural network of continuous casting technological parameters and secondary dendrite arm spacing of spring steel. J Iron Steel Res Int2011; 8: 25–29.
17.
ZouLLZhangJSLiuQ, et al.Internal crack prediction of continuous casting billet based on principal component analysis and deep neural network. Metals2021; 11: 1976–1976.
18.
PianosiFBevenKFreerJ, et al.Sensitivity analysis of environmental models: a systematic review with practical workflow. Environ Modell Software2016; 79: 214–232.
19.
DongLPenghaoJChenH, et al.Comparison of local and global sensitivity analysis methods and application to thermal hydraulic phenomena. Progress Nuclear Energy2023; 158: 104612.
20.
GanYDuanQGongW, et al.A comprehensive evaluation of various sensitivity analysis methods: a case study with a hydrological model. Environ Modell Software2014; 51: 269–285.
21.
ZhanCSongXXiaJ, et al.An efficient integrated approach for global sensitivity analysis of hydrological model parameters. Environ Modell Software2013; 41: 39–52.
22.
SongXZhangJZhanC, et al.Global sensitivity analysis in hydrological modeling: review of concepts, methods, theoretical framework, and applications. J Hydrol2015; 523: 739–757.
23.
RoblesARuanoMVRibesJ, et al.Global sensitivity analysis of a filtration model for submerged anaerobic membrane bioreactors (AnMBR). Bioresour Technol2014; 158: 365–373.
24.
MorganeMSylvainDJérômeM, et al.Variance based sensitivity analysis for Monte Carlo and importance sampling reliability assessment with Gaussian processes. Struct Safety2021; 93: 102116.
25.
MontgomeryDC. Design and Analysis of Experiments seventh ed. New York: Wiley, 2008.
26.
Xiao AYQingTJunF, et al.Dimensionality reduction for machine learning using statistical methods: a case study on predicting mechanical properties of steels. Mater Today Commun2023; 34: 105162.
27.
LinCPengFWangB, et al.Research on PCA and KPCA self-fusion based MSTAR SAR automatic target recognition algorithm. J Electron Sci Technol2012; 10: 352–357.
28.
XuYLiuYZhuQ. Multivariate time delay analysis based local KPCA fault prognosis approach for nonlinear processes. Chin J Chem Eng2016; 24: 1413–1422.
29.
ChenTGuestrinC. XGBoost: a scalable tree boosting system. CoRR 2016; abs/1603.02754.
30.
KaiSFengYTingD, et al.A steel property optimization model based on the XGBoost algorithm and improved PSO. Comput Mater Sci2020; 174: 109472.
31.
LeiZZhihaoGQianhuiT, et al.XGBoost-based short-term prediction method for power system inertia and its interpretability. Energy Rep2023; 9: 1458–1469.
32.
ZhouXWenHLiZ, et al.An interpretable model for the susceptibility of rainfall-induced shallow landslides based on SHAP and XGBoost. Geocarto Int2022; 37: 13419–13450.
