The iron ore sinter is still the main raw material for the blast furnace ironmaking process, its properties, such as strength and reducibility, are of vital importance to the productivity and the smooth operation of the blast furnace. In the present study, one model based on an artificial neural network (ANN) was established to predict the sinter strength. The ANN model was trained with the sample set, which was generated from the credible data from the published papers. The comparison between the direct prediction model and the indirect prediction model with the amount of liquid phase and spinal phase calculated with thermodynamic theory as the middle layer was carried out. The results show that the indirect ANN model gave much higher accurate prediction results than that of the direct one without the middle layer.The parametric study with the validated model shows that the sinter strength increased first with increasing the SiO2 to 5.4% and then decreased with further increasing the SiO2.
Get full access to this article
View all access options for this article.
References
1.
YangJFet al.Equilibrium analysis and elimination of harmful element in blast furnace. China Metall. 2007;17(11):35–40.
2.
WangHet al.Influence of harmful elements in iron concentrate and its detection and control. Shandong Metall. 2019;41(5):31–33.
3.
SatoSet al.Melting model of iron ore sintering. Tetsu Hagane. 1984;70(7):657–664.
4.
SatoSet al.Strength controlling factors and their model for iron ore sinter. Tetsu Hagane. 1987;73(8):964–971.
5.
Lu-pengZet al.Prediction model of sinter properties based on BP neural network. Iron Steel. 2017;52(9):11–15.
6.
HanQHJinYLZhangJH.The elementary application of BP networks in the prediction of sinter quality. Sinter Pellet. 2005;30(1):20–22.
7.
Hong-mingLet al.Modeling of iron ore sintering process based on intelligent method. Metall Ind Autom. 2006;30(6):19–22.
8.
FerreiraFPVet al.Lateral–torsional buckling resistance prediction model for steel cellular beams generated by artificial neural networks (ANN). Thin-Walled Struct. 2022;170:108592.
9.
ÖzcanFet al.Comparison of artificial neural network and fuzzy logic models for prediction of long-term compressive strength of silica fume concrete. Adv Eng Softw. 2009;40(9):856–863.
10.
MengFet al.Experimental study on application of steel slag magnetic tailings replacing part of sintering flux during sintering. J Cent South Univ (Sci Technol). 2017;48(01):31–38.
11.
GaoQet al.Influence and mechanism of Indonesia vanadium titano-magnetite on metallurgical properties of iron ore sinter. J Cent South Univ. 2017;24(12):2805–2812.
12.
ZhangFZhuDPanJet al.Sintering performance of blends containing high proportion of limonite. In: HwangJ, editor. 8th international symposium on high-temperature metallurgical processing. Cham: Springer; 2017. p. 615–625.
13.
MousaEABabichASenkD., A novel approach for utilization of ultra-fines iron ore in sintering process. Steel Res Int. 2015;86(11):1350–1360.
14.
ZhouMet al.Corrigendum: Influence of MgO in form of magnesite on properties and mineralogy of high chromium, vanadium, titanium magnetite sinters. Ironmak Steelmak. 2015;42(4):320–320.
15.
de CarvalhoLGet al.Study of age hardening behavior in a 350 Grade Maraging Steel. In: CarpenterJS, editor. Characterization of minerals, metals, and materials 2015. Hoboken, NJ: John Wiley; 2015. p. 1–10.
16.
ZhouMet al.Influence of MgO in form of magnesite on properties and mineralogy of high chromium, vanadium, titanium magnetite sinters. Ironmak Steelmak. 2014;42(3):217–225.
17.
SilvaSNet al.Behaviour of biofuel addition on metallurgical properties of sinter. Ironmak Steelmak. 2013;36(5):333–340.
18.
FanJet al.Improvement of sinter properties with ultra fine-sized Iron concentrate by HPRG. J Iron Steel Research, Int. 2013;20(9):47–52.
19.
CoresAet al.Relationship between sinter properties and iron ore granulation index. Ironmak Steelmak. 2013;39(2):85–94.
20.
DetkovaTVMalyshevaTYPavlovRM.Sinter at Cherepovets metallurgical works (basicity 1.0–3.0). Steel Transl. 2013;43(7):409–414.
21.
UmadeviTet al., Influence of limestone particle size on iron ore sinter properties and productivity. Steel Res Int. 2010;81(6):419–425.
22.
NairVHintonGE.Rectified linear units improve restricted Boltzmann machines Vinod Nair. In: JohannesFürnkranzThorstenJoachims, editors. Proceedings of the 27th international conference on international conference on machine learning. Haifa, Israel: Omnipress; 2010. p. 21–24.
23.
CoresAet al.The influence of different iron ores mixtures composition on the quality of sinter. ISIJ Int. 2010;50(8):1089–1098.
24.
UmadeviTet al.Influence of alumina on iron ore sinter properties and productivity in the conventional and selective granulation sintering process. Steel Res Int. 2009;80(9):686–692.
25.
UmadeviTet al.Influence of magnesia on iron ore sinter properties and productivity – use of dolomite and dunite. Steel Res Int. 2009;80(11):800–807.
26.
GanQHeMHeQ.Study on the influence of FeO content on quality and quantity of V-Ti-bearing sinter. Sinter Pelletizing. 2009;34(01):14–19.
27.
GanQHeQWenY.Study on influence of MgO on mineral composition and metallurgical properties of V-bearing titaniferous magnetite sinter. Iron Stee. 2008;43(08):7–11.
28.
UmadeviTet al.Influence of coke breeze particle size on quality of sinter. Ironmak Steelmak. 2013;35(8):567–574.
29.
ZhangMAndradeMet al.Effect of metallic iron sinter feed on sinter mineralogy and quality. In: LiB, editor. Characterization of minerals, metals, and materials 2019. Cham: Springer; 2019. p. 343–350.
30.
ZhangMAndradeMWet al.Effect of alumina and magnesia on microstructure and mineralogy of iron ore sinter. In: IkhmayiesS, editor. Characterization of minerals, metals, and materials 2017. Cham: Springer; 2017. p. 291–299.
31.
SinhaMet al.Correlating mechanical properties of sinter phases with their chemistry and its effect on sinter quality. Ironmak Steelmak. 2016;44(2):100–107.
32.
ZhangMAndradeMWet al.Effect of MgO and basicity on microstructure and metallurgical properties of iron ore sinter. In: IkhmayiesSJ, editor. Characterization of minerals, metals, and materials 2016. Hoboken, NJ: John Wiley; 2016. p. 167–174.
33.
YuZet al.Effect of basicity on titanomagnetite concentrate sintering. ISIJ Int. 2015;55(4):907–909.
34.
ZhouMet al.Influence of basicity on high-chromium vanadium-titanium magnetite sinter properties, productivity, and mineralogy. JOM. 2015;67(5):1203–1213.
35.
UmadeviTSahRMahapatraPC.Influence of sinter basicity (CaO/SiO2) on low and high alumina iron ore sinter quality. Min Proc Extractive Metall. 2014;123(2):75–85.
36.
UmadeviTet al.Influence of magnesia on iron ore sinter properties and productivity. Ironmak Steelmak. 2013;36(7):515–520.
37.
UmadeviTet al.Influence of iron ore fines feed size on microstructure, productivity and quality of iron ore sinter. ISIJ Int. 2011;51(6):922–929.
38.
KalengaMKGarbers-CraigAM.Investigation into how the magnesia, silica, and alumina contents of iron ore sinter influence its mineralogy and properties. J South Afr Inst Min Metall. 2010;110(8):447–456.
39.
UmadeviTet al., Influence of coating granulation process on iron ore sinter quality and productivity. Steel Res Int. 2010;81(9):716–723.
40.
MalyshevaTYet al.Mechanism of mineral formation and metallurgical properties of sinter of basicity 1.1–3.1 at OAO MMK. Steel Transl. 2007;37(2):126–130.
41.
ShenZYangHZhangS.Optimal approximation rate of ReLU networks in terms of width and depth. Journal de Mathématiques Pures et Appliquées. 2021;157:101–135.
42.
ZhouXWangH.The generalization error of graph convolutional networks may enlarge with more layers. Neurocomputing. 2021;424(3):97–106.
43.
ChengZet al.Characteristics of charcoal combustion and its effects on iron-ore sintering performance. Appl Energy. 2016;161(JAN.1):364–374.
44.
DongJJet al.Characteristics of the Sierra Leone high alumina iron ore and utilization in sintering. Adv Mat Res. 2014;881–883(25):1515–1521.
45.
GuochengZet al.Effect of basicity on liquid phase formation properties and microstructure of sinter. J Iron Steel Res. 2021;33(7):584–592.
46.
HintonGVinyalsODeanJ.Distilling the knowledge in a neural network. Comput Sci. 2015;14(7):38–39.
