Real-Time Prediction Model of Carbon Content in RH Process
In the Ruhrstahl–Heraeus (RH) vacuum degassing process, we propose a real-time prediction model for the carbon content in molten steel, and show that the decarburization endpoint can be accurately determined using this model. Firstly, we applied a novel off-gas analyzer that can measure the carbon o...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/21/10753 |
| _version_ | 1797469267347636224 |
|---|---|
| author | Jeongheon Heo Tae-Won Kim Soon-Jong Jung Soohee Han |
| author_facet | Jeongheon Heo Tae-Won Kim Soon-Jong Jung Soohee Han |
| author_sort | Jeongheon Heo |
| collection | DOAJ |
| description | In the Ruhrstahl–Heraeus (RH) vacuum degassing process, we propose a real-time prediction model for the carbon content in molten steel, and show that the decarburization endpoint can be accurately determined using this model. Firstly, we applied a novel off-gas analyzer that can measure the carbon oxide concentration produced in the decarburization reaction faster and more accurately. Next, we generate decarburization curves using the off-gas components measured by the new analyzer. The decarburization curve describes the carbon content profile well during operation, and shows good agreement with the actual carbon content. In order to predict the carbon content during operation in real time, we create an artificial neural network (ANN) using the decarburization curves and operation data. By comparing the endpoint carbon content measured at the end of the operation with the predicted values, we confirmed the excellent predictive performance of the ANN model. Finally, we show that it is possible to accurately determine the decarburization endpoint using the prediction model. We expect that the proposed real-time prediction model can increase the productivity of the RH process. |
| first_indexed | 2024-03-09T19:18:58Z |
| format | Article |
| id | doaj.art-45b042dfc36348898025ab6df7fb966f |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T19:18:58Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-45b042dfc36348898025ab6df7fb966f2023-11-24T03:32:16ZengMDPI AGApplied Sciences2076-34172022-10-0112211075310.3390/app122110753Real-Time Prediction Model of Carbon Content in RH ProcessJeongheon Heo0Tae-Won Kim1Soon-Jong Jung2Soohee Han3Smart Solution Research Group, Research Institute of Industrial Science and Technology (RIST), Pohang 37673, KoreaSmart Solution Research Group, Research Institute of Industrial Science and Technology (RIST), Pohang 37673, KoreaDepartment of Graduate Institute of Ferrous Technology, Pohang University of Science and Technology (POSTECH), Pohang 37673, KoreaDepartment of Electrical Engineering and Convergence IT Engineering, Pohang University of Science and Technology (POSTECH), Pohang 37673, KoreaIn the Ruhrstahl–Heraeus (RH) vacuum degassing process, we propose a real-time prediction model for the carbon content in molten steel, and show that the decarburization endpoint can be accurately determined using this model. Firstly, we applied a novel off-gas analyzer that can measure the carbon oxide concentration produced in the decarburization reaction faster and more accurately. Next, we generate decarburization curves using the off-gas components measured by the new analyzer. The decarburization curve describes the carbon content profile well during operation, and shows good agreement with the actual carbon content. In order to predict the carbon content during operation in real time, we create an artificial neural network (ANN) using the decarburization curves and operation data. By comparing the endpoint carbon content measured at the end of the operation with the predicted values, we confirmed the excellent predictive performance of the ANN model. Finally, we show that it is possible to accurately determine the decarburization endpoint using the prediction model. We expect that the proposed real-time prediction model can increase the productivity of the RH process.https://www.mdpi.com/2076-3417/12/21/10753artificial neural networksdecarburizationendpoint carbon concentrationnon-dispersive infrared spectroscopyRuhrstahl–Heraeus (RH) vacuum degassertunable diode laser absorption spectroscopy |
| spellingShingle | Jeongheon Heo Tae-Won Kim Soon-Jong Jung Soohee Han Real-Time Prediction Model of Carbon Content in RH Process Applied Sciences artificial neural networks decarburization endpoint carbon concentration non-dispersive infrared spectroscopy Ruhrstahl–Heraeus (RH) vacuum degasser tunable diode laser absorption spectroscopy |
| title | Real-Time Prediction Model of Carbon Content in RH Process |
| title_full | Real-Time Prediction Model of Carbon Content in RH Process |
| title_fullStr | Real-Time Prediction Model of Carbon Content in RH Process |
| title_full_unstemmed | Real-Time Prediction Model of Carbon Content in RH Process |
| title_short | Real-Time Prediction Model of Carbon Content in RH Process |
| title_sort | real time prediction model of carbon content in rh process |
| topic | artificial neural networks decarburization endpoint carbon concentration non-dispersive infrared spectroscopy Ruhrstahl–Heraeus (RH) vacuum degasser tunable diode laser absorption spectroscopy |
| url | https://www.mdpi.com/2076-3417/12/21/10753 |
| work_keys_str_mv | AT jeongheonheo realtimepredictionmodelofcarboncontentinrhprocess AT taewonkim realtimepredictionmodelofcarboncontentinrhprocess AT soonjongjung realtimepredictionmodelofcarboncontentinrhprocess AT sooheehan realtimepredictionmodelofcarboncontentinrhprocess |