Prediction of Temperature and Carbon Concentration in Oxygen Steelmaking by Machine Learning: A Comparative Study
The basic oxygen steelmaking process (BOS) faces the issue of the absence of information about the melt temperature and the carbon concentration in the melt. Although deterministic models for predicting steelmaking process variables are being developed in metallurgical research, machine-learning mod...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-08-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/15/7757 |
| _version_ | 1797432965559484416 |
|---|---|
| author | Ján Kačur Patrik Flegner Milan Durdán Marek Laciak |
| author_facet | Ján Kačur Patrik Flegner Milan Durdán Marek Laciak |
| author_sort | Ján Kačur |
| collection | DOAJ |
| description | The basic oxygen steelmaking process (BOS) faces the issue of the absence of information about the melt temperature and the carbon concentration in the melt. Although deterministic models for predicting steelmaking process variables are being developed in metallurgical research, machine-learning models can model the nonlinearities of process variables and provide a good estimate of the target process variables. In this paper, five machine learning methods were applied to predict the temperature and carbon concentration in the melt at the endpoint of BOS. Multivariate adaptive regression splines (MARS), support-vector regression (SVR), neural network (NN), <i>k</i>-nearest neighbors (<i>k</i>-NN), and random forest (RF) methods were compared. Machine modeling was based on static and dynamic observations from many melts. In predicting from dynamic melting data, a method of pairing static and dynamic data to create a training set was proposed. In addition, this approach has been found to predict the dynamic behavior of temperature and carbon during melting. The results showed that the piecewise-cubic MARS model achieved the best prediction performance for temperature in testing on static and dynamic data. On the other hand, carbon predictions by machine models trained on joined static and dynamic data were more powerful. In the case of predictions from dynamic data, the best results were obtained by the <i>k</i>-NN-based model, i.e., carbon, and the piecewise-linear MARS model in the case of temperature. In contrast, the neural network recorded the lowest prediction performance in more tests. |
| first_indexed | 2024-03-09T10:09:20Z |
| format | Article |
| id | doaj.art-4bbcd98f076944ceb947ff006b20d47d |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T10:09:20Z |
| publishDate | 2022-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-4bbcd98f076944ceb947ff006b20d47d2023-12-01T22:50:50ZengMDPI AGApplied Sciences2076-34172022-08-011215775710.3390/app12157757Prediction of Temperature and Carbon Concentration in Oxygen Steelmaking by Machine Learning: A Comparative StudyJán Kačur0Patrik Flegner1Milan Durdán2Marek Laciak3Institute of Control and Informatization of Production Processes, Faculty BERG, Technical University of Košice, Němcovej 3, 042 00 Košice, SlovakiaInstitute of Control and Informatization of Production Processes, Faculty BERG, Technical University of Košice, Němcovej 3, 042 00 Košice, SlovakiaInstitute of Control and Informatization of Production Processes, Faculty BERG, Technical University of Košice, Němcovej 3, 042 00 Košice, SlovakiaInstitute of Control and Informatization of Production Processes, Faculty BERG, Technical University of Košice, Němcovej 3, 042 00 Košice, SlovakiaThe basic oxygen steelmaking process (BOS) faces the issue of the absence of information about the melt temperature and the carbon concentration in the melt. Although deterministic models for predicting steelmaking process variables are being developed in metallurgical research, machine-learning models can model the nonlinearities of process variables and provide a good estimate of the target process variables. In this paper, five machine learning methods were applied to predict the temperature and carbon concentration in the melt at the endpoint of BOS. Multivariate adaptive regression splines (MARS), support-vector regression (SVR), neural network (NN), <i>k</i>-nearest neighbors (<i>k</i>-NN), and random forest (RF) methods were compared. Machine modeling was based on static and dynamic observations from many melts. In predicting from dynamic melting data, a method of pairing static and dynamic data to create a training set was proposed. In addition, this approach has been found to predict the dynamic behavior of temperature and carbon during melting. The results showed that the piecewise-cubic MARS model achieved the best prediction performance for temperature in testing on static and dynamic data. On the other hand, carbon predictions by machine models trained on joined static and dynamic data were more powerful. In the case of predictions from dynamic data, the best results were obtained by the <i>k</i>-NN-based model, i.e., carbon, and the piecewise-linear MARS model in the case of temperature. In contrast, the neural network recorded the lowest prediction performance in more tests.https://www.mdpi.com/2076-3417/12/15/7757steelmakingmelt temperaturecarbon concentrationmachine learningmodelingprediction |
| spellingShingle | Ján Kačur Patrik Flegner Milan Durdán Marek Laciak Prediction of Temperature and Carbon Concentration in Oxygen Steelmaking by Machine Learning: A Comparative Study Applied Sciences steelmaking melt temperature carbon concentration machine learning modeling prediction |
| title | Prediction of Temperature and Carbon Concentration in Oxygen Steelmaking by Machine Learning: A Comparative Study |
| title_full | Prediction of Temperature and Carbon Concentration in Oxygen Steelmaking by Machine Learning: A Comparative Study |
| title_fullStr | Prediction of Temperature and Carbon Concentration in Oxygen Steelmaking by Machine Learning: A Comparative Study |
| title_full_unstemmed | Prediction of Temperature and Carbon Concentration in Oxygen Steelmaking by Machine Learning: A Comparative Study |
| title_short | Prediction of Temperature and Carbon Concentration in Oxygen Steelmaking by Machine Learning: A Comparative Study |
| title_sort | prediction of temperature and carbon concentration in oxygen steelmaking by machine learning a comparative study |
| topic | steelmaking melt temperature carbon concentration machine learning modeling prediction |
| url | https://www.mdpi.com/2076-3417/12/15/7757 |
| work_keys_str_mv | AT jankacur predictionoftemperatureandcarbonconcentrationinoxygensteelmakingbymachinelearningacomparativestudy AT patrikflegner predictionoftemperatureandcarbonconcentrationinoxygensteelmakingbymachinelearningacomparativestudy AT milandurdan predictionoftemperatureandcarbonconcentrationinoxygensteelmakingbymachinelearningacomparativestudy AT mareklaciak predictionoftemperatureandcarbonconcentrationinoxygensteelmakingbymachinelearningacomparativestudy |