Abstract
The main task of basic oxygen furnace (BOF) steelmaking is dephosphorization, thus the prediction and control of End-point phosphorus content of molten steel is of great significance. Four machine learning regression models (Lasso, Random Forest, Xgboost, and Neural Network) were established to predict end-point phosphorus content of molten steel in BOF according to raw and auxiliary material data, process parameters, and data of production quality. The prediction effect of four models were further compared, and their prediction results were interpreted via model’s interpretability and Permutation Importance Method. Results showed that compared with linear regression and Neural Network regression model, two kinds of ensemble tree model had higher prediction accuracy, better stability in small data sets, and lower requirements on data pre-processing. The influencing factors of end-point phosphorus (P) content in BOF were ranked by importance as: Tapping temperature > Turning down times > Steel scrap amount > Operation habits of different work groups > Blowing oxygen amount > Sulfur and Phosphorus content of molten iron > Addition amount of lime, limestone, and light-burned dolomite in slagging agents > Slag-splashing amount.
Keywords
Array
Array
Array
Array
Array
References
Authors retain copyright of the published papers and grant to the publisher the non-exclusive right to publish the article, to be cited as its original publisher in case of reuse, and to distribute it in all forms and media.
The Author(s) warrant that their manuscript is their original work that has not been published before; that it is not under consideration for publication elsewhere; and that its publication has been approved by all co-authors, if any, as well as tacitly or explicitly by the responsible authorities at the institution where the work was carried out. The Author(s) affirm that the article contains no unfounded or unlawful statements and does not violate the rights of others. The author(s) also affirm that they hold no conflict of interest that may affect the integrity of the Manuscript and the validity of the findings presented in it. The Corresponding author, as the signing author, warrants that he/she has full power to make this grant on behalf of the Author(s). Any software contained in the Supplemental Materials is free from viruses, contaminants or worms.The published articles will be distributed under the Creative Commons Attribution ShareAlike 4.0 International license (CC BY-SA).
Authors are permitted to deposit publisher's version (PDF) of their work in an institutional repository, subject-based repository, author's personal website (including social networking sites, such as ResearchGate, Academia.edu, etc.), and/or departmental website at any time after publication.
Upon receiving the proofs, the Author(s) agree to promptly check the proofs carefully, correct any typographical errors, and authorize the publication of the corrected proofs.
The Corresponding author agrees to inform his/her co-authors, of any of the above terms.