This study addresses the prediction inaccuracy and poor adaptability of conventional temperature prediction models for ladle furnace refining. The historical production data of a steel plant were used to establish a hybrid prediction model based on mathematical mechanisms and a backpropagation neural network optimized using a genetic algorithm. The coefficient of determination (R2) of the hybrid model was 0.98, and the hit ratio of temperature prediction within ±5°C was 99.3%. The ladle's thermal status affected the model prediction accuracy. A steel plant with a compact production rhythm and good baking state was less affected by the ladle's thermal status. The model input variables exhibited varying degrees of influence on the end temperature of molten steel in two steel plants with the starting temperature of the molten steel entering the station having the greatest influence. For accurate temperature control and prediction in actual production, high-influence variables must be given focus to ensure their stable control and process interference must be mitigated.
GaoCShenMGLiuXP, et al.End-point dynamic control of basic oxygen furnace steelmaking based on improved unconstrained twin support vector regression. J Iron Steel Res Int2020; 27: 42–54.
2.
ZhouKXLinWHSunJK, et al.Prediction model of end-point phosphorus content for BOF based on monotone-constrained BP neural network. J Iron Steel Res Int2022; 29: 751–760.
3.
ChenCWangNChenM. Prediction model of end-point phosphorus content in consteel electric furnace based on PCA-extra tree model. ISIJ Int2021; 61: 1908–1914.
4.
HeFZhangLY. Prediction model of end-point phosphorus content in BOF steelmaking process based on PCA and BP neural network. J Process Contr2018; 66: 51–58.
5.
WeiGSZhuRChengT, et al.Modelling on the penetration depth of the coherent supersonic jet in EAF steelmaking. Ironmak Steelmak2018; 45: 828–838.
6.
MaiaTACOnnfriVC. Survey on the electric arc furnace and ladle furnace electric system. Ironmak Steelmak2022; 49: 976–994.
7.
NathNKMandalKSinghAK, et al.Ladle furnace on-line reckoner for prediction and control of steel temperature and composition. Ironmak Steelmak2006; 33: 140–150.
8.
KomolovaOAGrigorovichKV. Mathematical models, algorithms and software for dynamic simulation of ladle treatment technology. Metall Ital2019; 3: 20–24.
9.
GrigorovichKKomolovaOTerebikinaD. Analysis and optimization of ladle treatment technology of steels processing.J Chem Technol Metall2015; 50: 574–580.
10.
LvWMaoZZYuanP. Ladle furnace liquid steel temperature prediction model based on optimally pruned bagging. J Iron Steel Res Int2012; 19: 21–28.
11.
FengKHeDFXuAJ,et al.End temperature prediction of molten steel in LF based on CBR–BBN. Steel Res Int2016; 87: 79–86.
12.
WangXJWangXYZhangQ,et al.The soft sensor of the molten steel temperature using the modified maximum entropy based pruned bootstrap feature subsets ensemble method. Chem Eng Sci2018; 189: 401–412.
13.
WangXJYuanPMaoZZ,et al.Molten steel temperature prediction model based on bootstrap feature subsets ensemble regression trees. Knowl Based Syst2016; 101: 48–59.
14.
ChenCWangNChenM,et al.A framework based on heterogeneous ensemble models for liquid steel temperature prediction in LF refining process. Appl Soft Comput2022; 131: 109724.
15.
TianHXMaoZZWangAN. Hybrid modeling for soft sensing of molten steel temperature in LF. J Iron Steel Res Int2009; 16: 1–6.
16.
YangQDFuYCZhangJ. Molten steel temperature prediction using a hybrid model based on information interaction-enhanced cuckoo search. Neural Comput Appl2021; 33: 6487–6509.
17.
YuanFXuAJGuMQ. Development of an improved CBR model for predicting steel temperature in ladle furnace refining. Int J Min Met Mater2021; 28: 1321–1331.
18.
LvWMaoZZYuanP,et al.Pruned bagging aggregated hybrid prediction models for forecasting the steel temperature in ladle furnace. Steel Res Int2014; 85: 405–414.
19.
TianHXMaoZZWangY. Hybrid modeling of molten steel temperature prediction in LF. ISIJ Int2008; 48: 58–62.
20.
XinZCZhangJSPengKX, et al.Modeling of LF refining process: a review. J Iron Steel Res Int2024; 31: 289–317.
21.
HeFHeDFXuAJ, et al.Hybrid model of molten steel temperature prediction based on ladle heat status and artificial neural network. J Iron Steel Res Int2014; 21: 181–190.
22.
Farrera-BuenrostroJEHernandez-BocanegraCARamos-BanderasJA, et al.Analysis of temperature losses of the liquid steel in a ladle furnace during desulfurization stage. T Indian I Metals2019; 72: 899–909.
23.
TianRLYueFShiJK. Study on temperature field of ladle and temperature drop of molten steel in smelting. Steelmaking2022; 38: 42–48.
ZhengFLZengLCLuYD, et al.Fault diagnosis research for servo valve based on GA-BP neural network. J Comput Theor Nanos2015; 12: 2846–2850.
26.
ZhengDQianZDLiuY,et al.Prediction and sensitivity analysis of long-term skid resistance of epoxy asphalt mixture based on GA-BP neural network. Constr Build Mater2018; 158: 614–623.
27.
LiangYJRenCWangHY, et al.Research on soil moisture inversion method based on GA-BP neural network model. Int J Remote Sens2019; 40: 2087–2103.
28.
WangBMaoZZHuangKK. A prediction and outlier detection scheme of molten steel temperature in ladle furnace. Chem Eng Res Des2018; 138: 229–247.
29.
TianHX. End temperature prediction of molten steel in LF based on genetic algorithm and BP neural network. End temperature prediction of molten steel in LF based on genetic algorithm and BP neural network. Shenyang, China: Northeastern University, 2005.
30.
XinZCLiuQZhangJS, et al.A hybrid modeling method based on expert control and deep neural network for temperature prediction of molten steel in LF. ISIJ Int2022; 62: 532–541.
