Removal of phosphorus is a reaction, which plays an important role in combined converter steelmaking process, and the precise control of end‐point phosphorus content during BOF steelmaking process would greatly improve the quality of liquid steel. Therefore, the relation between dephosphorization ratio and temperature of liquid steel, FeO content of slag, slag basicity is clearly clarified through thermodynamic analysis of dephosphorization process in this paper. Besides, by means of combining the methods of multivariate regression analysis and multi‐level recursive completely, the multi‐level recursive regression model, which is used to complete the prediction of end‐point phosphorus content during BOF steelmaking process, is established based on large amount of production data. The verification of the model with the data taken from three steel plants indicates that the hit rate of the multi‐level recursive regression model is above 84% when predictive errors of the model are within ±0.005%, and it could provide a relatively good reference for real production.
Through analyzing the factors that influence end-point manganese content during BOF steelmaking process, multiple linear regression model for prediction of end-point manganese content was obtained on the basis of actual production data. Given the advantages of artificial neural network, it was used to predict end-point manganese content during BOF steelmaking process, and BP neural network model was established. By means of combining the characteristics of genetic algorithm and BP neural network completely, a combined GA-BP neural network model was established. The verification and comparison of the above three models show that the combined GA-BP neural network model has the highest prediction accuracy. The hit rate of the combined GA-BP neural network model is 90% and 84% respectively when predictive errors of the model are within ±0.03% and ±0.025%. Compared with two models aboved, the combined GA-BP neural network model could provide the most accurate prediction of end-point manganese content, and thus represents a good reference for real production.
By analysing the factors that affect oxygen consumption during the basic oxygen furnace steelmaking process, a multiple linear regression model for predicting the oxygen blowing quantity was obtained on the basis of actual production data. Additionally, an oxygen balance model for prediction of the oxygen blowing quantity was established on the basis of oxygen balance. These two models were amalgamated to establish an integrated model for prediction of the oxygen blowing quantity. The average relative error of the integrated model is ,1%, and the hit rate of the integrated model is 97?14% when the relative errors of the model are within 5%. Relative to the multiple linear regression and the oxygen balance models, the integrated model may provide a more accurate prediction of the oxygen blowing quantity, and thus represents a good reference point for actual production.List of symbols c i oxygen consumed per unit mass of oxidised element i, Nm 3 kg 21 m i amount of oxidised element i, kg V balance, O 2 oxygen blowing quantity predicted from the oxygen balance model, Nm 3 V CO, O2 oxygen quantity consumed by postcombustion of carbon monoxide in the furnace hearth, Nm 3 V gas, O 2 amount of unused oxygen in the offgas, Nm 3 V O 2 oxygen blowing quantity predicted from the integrated model, Nm 3 V real, O 2 actual value of the oxygen blowing quantity, Nm 3 V regression, O 2 oxygen blowing quantity predicted from the linear regression model, Nm 3 V sinter ore, O 2 quantity of oxygen provided by the sinter ore, Nm 3 w r , w b weighting coefficients of the linear regression model and oxygen balance model
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.