Prediction of end-point phosphorus content of molten steel in BOF with machine learning models
The main task in the production of steel in the basic oxygen furnace (BOF) is dephosphorization Therefore, the prediction and control of the end-point phosphorus content of molten steel is of great significance. Four machine learning regression models (Lasso, Random Forest, Xgboost, and Neural Netwo...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
University of Belgrade, Technical Faculty, Bor
2024-01-01
|
| Series: | Journal of Mining and Metallurgy. Section B: Metallurgy |
| Subjects: | |
| Online Access: | https://doiserbia.nb.rs/img/doi/1450-5339/2024/1450-53392400008K.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832572836845191168 |
|---|---|
| author | Kang Y. Ren M.-M. Zhao J.-X. Yang L.-B. Zhang Z.-K. Wang Z. Cao G. |
| author_facet | Kang Y. Ren M.-M. Zhao J.-X. Yang L.-B. Zhang Z.-K. Wang Z. Cao G. |
| author_sort | Kang Y. |
| collection | DOAJ |
| description | The main task in the production of steel in the basic oxygen furnace (BOF) is dephosphorization Therefore, the prediction and control of the 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 the end-point phosphorus content of molten steel in the BOF based on raw and auxiliary material data, process parameters, and production quality data. The prediction effect of the four models was further compared, and their prediction results were interpreted based on the interpretability of the models and the permutation importance method. The results showed that compared with linear regression and neural network regression model, two types of ensemble tree model have higher prediction accuracy, better stability with small data sets, and lower data preprocessing requirements. The factors influencing the end-point phosphorus (P) content in BOF were ranked in order of importance as: Tapping temperature > Turning down times > Steel scrap quantity> Operation habits of different working groups > Amount of oxygen injection> Sulfur and phosphorus content of molten iron > Addition amount of lime, limestone, and lightly burnt dolomite in the slag > Slag-splashing amount. |
| format | Article |
| id | doaj-art-c82925734cff4df49f869595cdfd9da9 |
| institution | Kabale University |
| issn | 1450-5339 2217-7175 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | University of Belgrade, Technical Faculty, Bor |
| record_format | Article |
| series | Journal of Mining and Metallurgy. Section B: Metallurgy |
| spelling | doaj-art-c82925734cff4df49f869595cdfd9da92025-02-02T07:38:22ZengUniversity of Belgrade, Technical Faculty, BorJournal of Mining and Metallurgy. Section B: Metallurgy1450-53392217-71752024-01-016019310310.2298/JMMB230306008K1450-53392400008KPrediction of end-point phosphorus content of molten steel in BOF with machine learning modelsKang Y.0Ren M.-M.1Zhao J.-X.2Yang L.-B.3Zhang Z.-K.4Wang Z.5Cao G.6School of Metallurgical Engineering, Xi’an University of Architecture and Technology, Xi’an, Shaanxi, ChinaSchool of Metallurgical Engineering, Xi’an University of Architecture and Technology, Xi’an, Shaanxi, ChinaSchool of Metallurgical Engineering, Xi’an University of Architecture and Technology, Xi’an, Shaanxi, ChinaCentral Iron & Steel Research Institute, Beijing, ChinaSchool of Metallurgical Engineering, Xi’an University of Architecture and Technology, Xi’an, Shaanxi, ChinaSchool of Metallurgical Engineering, Xi’an University of Architecture and Technology, Xi’an, Shaanxi, ChinaSchool of Metallurgical Engineering, Xi’an University of Architecture and Technology, Xi’an, Shaanxi, ChinaThe main task in the production of steel in the basic oxygen furnace (BOF) is dephosphorization Therefore, the prediction and control of the 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 the end-point phosphorus content of molten steel in the BOF based on raw and auxiliary material data, process parameters, and production quality data. The prediction effect of the four models was further compared, and their prediction results were interpreted based on the interpretability of the models and the permutation importance method. The results showed that compared with linear regression and neural network regression model, two types of ensemble tree model have higher prediction accuracy, better stability with small data sets, and lower data preprocessing requirements. The factors influencing the end-point phosphorus (P) content in BOF were ranked in order of importance as: Tapping temperature > Turning down times > Steel scrap quantity> Operation habits of different working groups > Amount of oxygen injection> Sulfur and phosphorus content of molten iron > Addition amount of lime, limestone, and lightly burnt dolomite in the slag > Slag-splashing amount.https://doiserbia.nb.rs/img/doi/1450-5339/2024/1450-53392400008K.pdfconverter steelmakingmachine learningensemble tree modelmodel interpretabilityinfluencing factor rankingend-point prediction |
| spellingShingle | Kang Y. Ren M.-M. Zhao J.-X. Yang L.-B. Zhang Z.-K. Wang Z. Cao G. Prediction of end-point phosphorus content of molten steel in BOF with machine learning models Journal of Mining and Metallurgy. Section B: Metallurgy converter steelmaking machine learning ensemble tree model model interpretability influencing factor ranking end-point prediction |
| title | Prediction of end-point phosphorus content of molten steel in BOF with machine learning models |
| title_full | Prediction of end-point phosphorus content of molten steel in BOF with machine learning models |
| title_fullStr | Prediction of end-point phosphorus content of molten steel in BOF with machine learning models |
| title_full_unstemmed | Prediction of end-point phosphorus content of molten steel in BOF with machine learning models |
| title_short | Prediction of end-point phosphorus content of molten steel in BOF with machine learning models |
| title_sort | prediction of end point phosphorus content of molten steel in bof with machine learning models |
| topic | converter steelmaking machine learning ensemble tree model model interpretability influencing factor ranking end-point prediction |
| url | https://doiserbia.nb.rs/img/doi/1450-5339/2024/1450-53392400008K.pdf |
| work_keys_str_mv | AT kangy predictionofendpointphosphoruscontentofmoltensteelinbofwithmachinelearningmodels AT renmm predictionofendpointphosphoruscontentofmoltensteelinbofwithmachinelearningmodels AT zhaojx predictionofendpointphosphoruscontentofmoltensteelinbofwithmachinelearningmodels AT yanglb predictionofendpointphosphoruscontentofmoltensteelinbofwithmachinelearningmodels AT zhangzk predictionofendpointphosphoruscontentofmoltensteelinbofwithmachinelearningmodels AT wangz predictionofendpointphosphoruscontentofmoltensteelinbofwithmachinelearningmodels AT caog predictionofendpointphosphoruscontentofmoltensteelinbofwithmachinelearningmodels |