The point prediction of slab front-end bending can provide a specific quantitative value of bending as the prediction result, but cannot accurately give the probability and fluctuation range of front-end bending in hot rolling. In this paper, an innovative full-process collaborative platform that incorporates an ensemble interval prediction method paired with a control strategy is proposed. This approach effectively represents the uncertainty associated with front-end bending prediction points in the form of probability distributions and establishes corresponding evaluation criteria with proven reliability. The machine vision technology is utilised to collect rolling data in real-time, which is subsequently processed to provide input data for the prediction model. A non-dominated sorting genetic algorithm is adopted to optimise the extreme gradient boosting model for the front-end bending prediction. Meanwhile, the prediction interval of the front-end bending is obtained by combining a non-parametric statistical analysis. Finally, based on the prediction interval combined with the proposed control strategy and evaluation criteria, an real-time regulation system of the hot rolling slab front-end bending is achieved. The online application results show that the method proposed in this paper can make timely and accurate responses to the fluctuations of slab front-end bending, effectively improving the control effect and product quality.
AndersDMünkerTArtelJ,et al.A dimensional analysis of front-end bending in plate rolling applications. J Mater Process Tech2012; 212: 1387–1398.
2.
PawelskiH. Comparison of methods for calculating the influence of asymmetry in strip and plate rolling. Steel Research Int2000; 71: 490–496.
3.
KnightCWHardySJLeesAW,et al.Investigations into the influence of asymmetric factors and rolling parameters on strip curvature during hot rolling. J Mater Process Tech2003; 134: 180–189.
4.
PhilippMSchwenzfeierWFischerFD, et al.Front end bending in plate rolling influenced by circumferential speed mismatch and geometry. J Mater Process Tech2007; 184: 224–232.
5.
KasaiDKommriAIshiiA, et al.Strip warpage behavior and mechanism in single roll driven rolling. ISIJ Int2016; 56: 1815–1824.
6.
WangJLiuXHGuoWP. Analysis of mechanical parameters for asymmetrical strip rolling by slab method. Int J Adv Manuf Tech2018; 98: 2297–2309.
7.
XuDYangQWangXC, et al.Application of TS fuzzy model for slab camber control in a hot strip rougher mill. Ironmak Steelmak2020; 47: 623–631.
8.
DingJGHeYHCKongLP,et al.Camber prediction based on fusion method with mechanism model and machine learning in plate rolling. ISIJ Int2021; 61: 2540–2551.
9.
SongLBXuDLiuPF, et al.A novel mechanism fusion data control method for slab camber in hot rolling. J Iron Steel Res Int2023; 30: 960–970.
10.
ByonSMLeeY. An in-line model for predicting front end bending in hot plate rolling and its experimental verification. Proc Inst Mech Eng2013; 227: 1111–1120.
11.
ParkJSNaDH, et al.Application of neural networks to minimize front end bending of material in plate rolling process. Proc Inst Mech Eng2016; 230: 629–642.
12.
DongZSLiXLuanF, et al.Point and interval prediction of the effective length of hot-rolled plates based on IBES-XGBoost. Measurement2023; 214: 112857.
13.
GneitingTKatzfussM. Probabilistic forecasting. Annu Rev Stat Appl2014; 1: 125–151.
14.
PengGZChengYLWangHW,et al.Industrial IoT-enabled prediction interval estimation of mechanical performances for hot-rolling steel. IEEE Trans Instrum Meas2022; 71: 1–10.
15.
PengGZChengYLZhangYF, et al.Industrial big data-driven mechanical performance prediction for hot-rolling steel using lower upper bound estimation method. J Manuf Sys2022; 65: 104–114.
16.
ZhangKZhangXWPengKX. A novel parallel feature extraction-based multi-batch process quality prediction method with application to a hot rolling mill process. J Process Control2024; 135: 103166.
17.
DongZSLiXLuanF, et al.Rolling theory-guided prediction of hot-rolled plate width based on parameter transfer strategy. ISA Trans2024; 146: 352–365.
18.
WangFJSongYLiuC, et al.Multi-objective optimal scheduling of laminar cooling water supply system for hot rolling mills driven by digital twin for energy-saving. J Process Control2023; 122: 134–146.
19.
LiJDWangXC, et al.Predicting mechanical properties lower upper bound for cold-rolling strip by machine learning-based artificial intelligence. ISA Trans2024; 147: 328–336.
20.
ZhaoYBSongYLiFF,et al.Prediction of mechanical properties of cold rolled strip based on improved extreme random tree. J Iron Steel Res Int2023; 30: 293–304.
21.
InoueTTsujiN. Quantification of strain in accumulative roll-bonding under unlubricated condition by finite element analysis. Comput Mater Sci2009; 46: 261–266.
22.
LiuSQ. Numerical simulation of plate rolling process and optimization of technology. Shandong, China: Shandong University of Science and Technology, 2005.
23.
SongLBXuDWangCY, et al.A novel intelligent method for slab front end bending control in hot rolling. Int J Adv Manuf Technol2023; 126: 4199–4212.
24.
YanSZXuDHeWZ, et al.Online measurement system of slab front-end bending in hot rough rolling based on line structured light vision[J]. Meas Sci Technol2023; 34: 095201.
25.
YanSZWangXCYangQ, et al.Online deviation measurement system of the strip in the finishing process based on machine vision[J]. Measurement2022; 202: 111735.
26.
RodríguezFInsaustiXEtxezarretaG, et al.Very short-term parametric ambient temperature confidence interval forecasting to compute key control parameters for photovoltaic generators. Energy Technol Assess2022; 51: 101931.
27.
DuBGHuangS, et al.Interval forecasting for urban water demand using PSO optimized KDE distribution and LSTM neural networks. Applied Soft Comput2022; 122: 108875.
28.
ZhouMWangBGuoSD,et al.Multi-objective prediction intervals for wind power forecast based on deep neural networks. Inf Sci2021; 550: 207–220.
29.
StiefABaranowskiJ. Fault diagnosis using interpolated kernel density estimate. Measurement2021; 176: 109230.
30.
LeeWJMendisGP, et al.Monitoring of a machining process using kernel principal component analysis and kernel density estimation. J Intell Manuf2020; 31: 1175–1189.
31.
KamalovF. Kernel density estimation based sampling for imbalanced class distribution. Inf Sci2020; 512: 1192–1201.
32.
ChenTGuestrinC. XGBoost: a scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining2016: 785–794.
33.
DaiYMZhouQLengMM, et al.Improving the bi-LSTM model with XGBoost and attention mechanism: a combined approach for short-term power load prediction. Applied Soft Comput2022; 130: 109632.
34.
ShiRXuXYLiJM,et al.Prediction and analysis of train arrival delay based on XGBoost and Bayesian optimization. Applied Soft Comput2021; 109: 107538.
35.
LiMMaHLvSY, et al.Enhanced NSGA-II-based feature selection method for high-dimensional classification. Inf Sci2024; 663: 120269.
36.
KhosraviANahavandiSCreightonD,et al.Comprehensive review of neural network-based prediction intervals and new advances. IEEE Trans Neural Netw2011; 22: 1341–1356.
