Endpoint temperature prediction of molten steel in RH using improved case-based reasoning

Abstract

An improved case-based reasoning (CBR) method was proposed to predict the endpoint temperature of molten steel in Ruhrstahl Heraeus (RH) process. Firstly, production data were analyzed by multiple linear regressions and a pairwise comparison matrix in analytic hierarchy process (AHP) was determined by this linear regression’s coefficient. The weights of various influencing factors were obtained by AHP. Secondly, the dividable principles of case base including “0–1” and “breakpoint” were proposed, and the case base was divided into several homogeneous parts. Finally, the improved CBR was compared with ordinary CBR, which is based on the even weight and the single base. The results show that the improved CBR has a higher hit rate for predicting the endpoint temperature of molten steel in RH.

Keywords

steelmaking / degassing / case-based reasoning / analytic hierarchy process / temperature / prediction

References

[1] Liu BS, Zhu GS, Li HX, Li BH, Cui Y, Cui AM. Decarburization rate of RH refining for ultra low carbon steel. Int. J. Miner. Metall. Mater., 2010, 17(1): 22.

[2] Tang FP, Li Z, Wang XF, Chen BW, Fei P. Cleaning IF molten steel with dispersed in-situ heterophases induced by the composite sphere explosive reaction in RH ladles. Int. J. Miner. Metall. Mater., 2011, 18(2): 144.

[3] Ai XG, Bao YP, Jiang W, Liu JH, Li PH, Li TQ. Periodic flow characteristics during RH vacuum circulation refining. Int. J. Miner. Metall. Mater., 2010, 17(1): 17.

[4] Lin L, Bao YP, Yue F, Zhang LQ, Qu HL. Physical model of fluid flow characteristics in RH-TOP vacuum refining process. Int. J. Miner. Metall. Mater., 2012, 19(6): 483.

[5] Wang HB, Xu AJ, Ai LX, Tian NY, Du X. An integrated CBR model for predicting endpoint temperature of molten steel in AOD. ISIJ Int., 2012, 52(1): 80.

[6] Wang HB, Ai LX, Xu AJ, Tian NY, Hou ZC, Zhou ZW. Prediction on the starting temperature of molten steel in second refining by using case-based reasoning. J. Univ. Sci. Technol. Beijing, 2012, 34(3): 264

[7] Liu DH, Wang HB, Xu AJ. Predicting the end temperature of molten steel using CBR. Appl. Mech. Mater., 2012, 164, 7.

[8] Tian HX, Mao ZZ, Wang Y. Hybrid modeling of molten steel temperature prediction in LF. ISIJ Int., 2008, 48(1): 58.

[9] Tian HX, Mao ZZ, Wang AN. A new incremental learning modeling method based on multiple models for temperature prediction of molten steel in LF. ISIJ Int., 2009, 49(1): 58.

[10] 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.

[11] Lü W, Mao ZZ, Yuan P. Ladle furnace liquid steel temperature prediction model based on optimally pruned bagging. J. Iron Steel Res. Int, 2012, 19(12): 21.

[12] Wang YN, Bao YP, Cui H, Chen B, Ji CX. Final temperature prediction model of molten steel in RH-TOP refining process for IF steel production. J. Iron Steel Res. Int., 2012, 19(3): 1.

[13] Wang YN, Bao YP, Cui H, Chen B, Ji CX. Study on regularity of temperature reduction of IF steel slab casting liquid with 210 t top and bottom combined blown converter-RH flow sheet. Spec. Steel, 2011, 32(1): 40

[14] Yuan P, Wang FL, Mao ZZ. CBR based endpoint prediction of EAF. J. Northeast. Univ. Nat. Sci., 2011, 32(12): 1673

[15] Yuan P, Mao ZZ, Wang FL. Prediction model of molten steel temperature in LF. Control and Decision Conference, 2009 3747

[16] 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.

[17] He F, Xu AJ, Wang HB, He DF, Tian NY. End temperature prediction of molten steel in LF based on CBR. Steel Res. Int., 2012, 83(11): 1079.

[18] Lv W, Mao ZZ, Yuan P. Ladle furnace steel temperature prediction model based on partial linear regularization networks with sparse representation. Steel Res. Int., 2012, 83(3): 288.

[19] Lv W, Mao ZZ, Yuan P, Jia MX. Multi-kernel learnt partial linear regularization network and its application to predict the liquid steel temperature in ladle furnace. Knowl. Based Syst., 2012, 36, 280.

[20] Huang H, Chai TY, Zhang BL, Luo XC, Zhang H. Two-stage case-based reasoning for molten iron dynamic scheduling system oriented iron-steel correspondence. CIESC J., 2010, 61(8): 2021

[21] Liu CH, Chen HC. A novel CBR system for numeric prediction. Inf. Sci., 2012, 185, 178.

[22] Han M, Wang XZ. BOF oxygen control by mixed case retrieve and reuse CBR. Proceedings of the 18th IFAC World Congress, 2011 3575

[23] Han M, Wang XZ. Case based reasoning for converter steelmaking dynamic oxygen volume control. Proceedings of 2010 International Conference on Intelligent Control and Information Processing, 2010 398.