Development of an improved CBR model for predicting steel temperature in ladle furnace refining

Abstract

In the prediction of the end-point molten steel temperature of the ladle furnace, the influence of some factors is nonlinear. The prediction accuracy will be affected by directly inputting these nonlinear factors into the data-driven model. To solve this problem, an improved case-based reasoning model based on heat transfer calculation (CBR-HTC) was established through the nonlinear processing of these factors with software Ansys. The results showed that the CBR-HTC model improves the prediction accuracy of end-point molten steel temperature by 5.33% and 7.00% compared with the original CBR model and 6.66% and 5.33% compared with the back propagation neural network (BPNN) model in the ranges of [−3, 3] and [−7, 7], respectively. It was found that the mean absolute error (MAE) and root-mean-square error (RMSE) values of the CBR-HTC model are also lower. It was verified that the prediction accuracy of the data-driven model can be improved by combining the mechanism model with the data-driven model.

Keywords

case-based reasoning / LF refining / steel temperature prediction / ladle lining

References

[1] He F, He DF, Wang HB, Xu AJ, Tian NY. Prediction of molten steel temperature in BOF→LF→CC route. Steelmaking, 2012, 28(3): 53

[2] Gao ZB. Study on Non-contact Temperature Measurement Technology of Molten Steel in LF Furnace, 2020, Hefei, Anhui University, 42 [Dissertation]

[3] M. Sugiura, T. Yamazaki, R. Nakao, T. Tanaka, S. Nagata, H. Kumazawa, E. Tsubota, and W. Nagai, Development of new technique for continuous molten steel temperature measurement, Nippon Steel Tech. Rep., 2004, No. 89, p. 23.

[4] Gao Y. Research on Temperature Prediction Model of Molten Steel in LF, 2008, Shenyang, Northeastern University, 34 [Dissertation]

[5] Luo JZ, Huang CY, Qiu L, Li YJ, Zhao GG, Fan BL, Lian KF, Xin WP. Research on temperature field of energy-saving ladle with adding lid by thermal coupling numerical simulation. Iron Steel Vanadium Titanium, 2017, 38(2): 98

[6] Li GF, Liu J, Jiang GZ, Liu HH. Numerical simulation of temperature field and thermal stress field in the new type of ladle with the nanometer adiabatic material. Adv. Mech. Eng., 2015, 7(4): 30

[7] Samuelsson P, Sohlberg B. ODE-based modeling and calibration of temperatures in steelmaking ladles. IEEE Trans. Contr. Sys. Technol., 2010, 18(2): 474.

[8] Tian SX, Gao GZ, Li DF. Research on reducing heat loss of ladle. Refractories, 2016, 50(1): 51

[9] Tripathi A, Saha JK, Singh JB, Ajmani S. Numerical simulation of heat transfer phenomenon in steel making ladle. ISIJ Int., 2012, 52(9): 1591.

[10] Davila O, Garcia-Demedices L, Morales RD. Mathematical simulation of fluid dynamics during steel draining operations from a ladle. Metall. Mater. Trans. B, 2006, 37(1): 71.

[11] Zhao HL, Zhao X, Mu LZ, Zhang LF, Yang LQ. Gas-liquid mass transfer and flow phenomena in a peirce-smith converter: a numerical model study. Int. J. Miner. Metall. Mater., 2019, 26(9): 1092.

[12] Ni B, Zhang T, Ni HQ, Luo ZG. Mechanism and simulation of droplet coalescence in molten steel. Int. J. Miner. Metall. Mater., 2017, 24(11): 1251.

[13] Sonoda S, Murata N, Hino H, Kitada H, Kano M. A statistical model for predicting the liquid steel temperature in ladle and tundish by bootstrap filter. ISIJ Int., 2012, 52(6): 1086.

[14] Q.D. Yang, J. Zhang, and Z. Yi, Predicting molten steel endpoint temperature using a feature-weighted model optimized by mutual learning cuckoo search, Appl. Soft Comput., 83(2019), art. No. 105675.

[15] Wang XJ. Ladle furnace temperature prediction model based on large-scale data with Random Forest. IEEE J. Autom. Sin., 2017, 4(4): 770.

[16] Wang XJ, Yuan P, Mao ZZ, You MS. Molten steel temperature prediction model based on bootstrap feature subsets ensemble regression trees. Knowl.-Based Syst., 2016, 101, 48.

[17] Gao C, Shen MG, Wang HQ. End-point prediction of BOF steel making based on twin support vector regression. China Metall., 2019, 29(4): 12

[18] Gao C, Shen MG. End-point static prediction of bof steel making based on unconstrained wavelet weighted twin support vector regression. Steelmaking, 2019, 35(2): 20

[19] W. Lv, Z.Z. Mao, and M.X. Jia, ELM based lf temperature prediction model and its online sequential learning, [in] 24th Chinese Control and Decision Conference, Taiyuan, 2012, p. 2362.

[20] Wang XJ, You MS, Mao ZZ, Yuan P. Tree-structure ensemble general regression neural networks applied to predict the molten steel temperature in ladle furnace. Adv. Eng. Inform., 2016, 30(3): 368.

[21] Tian HX, Mao ZZ. An ensemble elm based on modified adaboost.rt algorithm for predicting the temperature of molten steel in ladle furnace. IEEE Trans. Autom. Sci. Eng., 2010, 7(1): 73.

[22] Zhang XZ. Temperature Prediction of LandlwFurnace Based on ADABOOST Algorithm and Elmalgorithm, 2015, Shenyang, Northeastern University, 31 [Dissertation]

[23] Feng K, Wang HB, Xu AJ, He DF, Tian NY. LF endpoint temperature prediction of molten steel by gmdh neural network based on material model. Steelmaking, 2013, 29(2): 38

[24] Feng K, He DF, Xu AJ, Wang HB. End temperature prediction of molten steel in LF based on CBR-BBN. Steel Res. Int., 2016, 87(1): 79.

[25] K. Feng, A.J. Xu, D.F. He, and H.B. Wang, An improved CBR model based on mechanistic model similarity for predicting end phosphorus content in dephosphorization converter, Steel Res. Int., 89(2018), No. 6, art. No. 1800063.

[26] Feng K, Xu AJ, Wu PF, He DF, Wang HB. Case-based reasoning model based on attribute weights optimized by genetic algorithm for predicting end temperature of molten steel in RH. J. Iron Steel Res. Int., 2019, 26(6): 585.

[27] Hou YM, Xu CY. The review of case-based reasoning research. J. Yanshan Univ. Philos. Soc. Sci. Ed., 2011, 12(4): 102

[28] Yuan F. Simulating Research on Temperature and Effects on Temperature Drop of Molten Steel of Turnover Ladles in Qiangang, 2013, Beijing, University of Science and Technology Beijing, 55 [Dissertation]

[29] Liu ZZ, Jiang YH, Guo HZ. Research on numerical simulation of ladle conduction in the steel-making plant. Wisco Technol., 2007, 45(4): 20

[30] Volkova O, Janke D. Modelling of temperature distribution in refractory ladle lining for steelmaking. ISIJ Int., 2003, 43(8): 1185.

[31] J. Li, J. Fu, P. Wang, C.G. Huang, P. Zhang, and Z.C. Zhang, Effect of slag on liquid steel temperature, Res. Iron Steel, 1998, No. 6, p. 19.