| Peer-Reviewed

Prediction and Optimization of Internal Return Fines Generation in Iron Ore Sintering Using Machine Learning

Received: 3 August 2021     Accepted: 13 August 2021     Published: 28 October 2021
Views:       Downloads:
Abstract

Prior to dispatch of sinter to the blast furnace for hot metal production, the sinter product from the sinter cooler is screened to remove smaller/finer particles. The undersize so generated is called internal return fines, which are generally recirculated into the sintering machine. A very high level of internal return fines generation limits the use of virgin ore for sintering which may hamper sinter productivity. Recently, the sinter plant at Tata Steel’s Kalinganagar works has faced issues of high internal return fines generation. As the sinter plant begins to increase its productivity levels, it becomes critical to control the generation of internal return fines to allow fresh material consumption. Limited literature is available on factors affecting the internal return fines generation in sinter plant. Given the current computational capabilities, a machine learning model was developed to ascertain the factors affecting the internal return fines generation. The development of the machine learning model and the optimization carried out based on model output is described in this work. The key parameters affecting the internal return fines generation were the sintering rate, sinter basicity, charge density and temperature in the ignition hood. In Kalinganagar, the increase in ignition hood temperature was limited by the furnace refractory condition. Further, the sinter basicity is determined by the percentage of sinter in blast furnace burden. Incorporating these constraints, the model was used to optimize the process parameters to generate the lowest possible return fines. The understanding generated from this machine learning framework has resulted in a reduction of 2-3% in internal return fines generation, which implied higher net sinter production.

Published in Advances in Materials (Volume 10, Issue 3)
DOI 10.11648/j.am.20211003.12
Page(s) 42-47
Creative Commons

This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.

Copyright

Copyright © The Author(s), 2021. Published by Science Publishing Group

Keywords

Machine Learning, Internal Return Fines, Sintering Rate, Prediction

References
[1] Jesus Saiz and Maria Jose Posada, Non-linear State Estimator for Online Control of a Sinter Plant, ISIJ International, 53, 9, 1658-1664 (2013).
[2] Mróz Jan, Skowronek Ryszard and Francik Przemysław, Investigations on the Influence of Return Sinter Fines on the Iron Ores Sintering Process and on the Properties of Iron Ore Sinter, Proceedings of the 5th International Congress on the Science and Technology of Ironmaking, 2009.
[3] Ram Pravesh Bhagat, Factors Affecting Return Sinter Fines Regimes and Strand Productivity in Iron Ore Sintering, ISIJ International, 39, 9, 889-895 (1999).
[4] Kanjilal PP and Rose E, Application of adaptive prediction and control method for improved operation of the sintering process. Ironmaking and Steelmaking, 13, 289–293, 1986.
[5] Liu Song, Lyu Qing, Liu Xiaojie and Sun Yanquin, Synthetically predicting the quality index of sinter using machine learning model, Ironmaking and Steelmaking, 47, 7, 828-836 (2020).
[6] The perfect sinter plant control, Technical Document by Primetals.
[7] Shengli Wu, Juan Zhu, Jiaxin Fan, Guoliang Zhang and Shaoguo Chen, Sintering behavior of Return Fines and their effective utilization method, ISIJ International, 53, 9, 1561-1570, 2013.
[8] Himanshu Khandelwal, Shweta Srivastava, Adity Ganguly and Abhijit Roy, Prediction and Control of Coke Plant Wastewater Quality using Machine Learning Techniques, Coke and Chemistry, 63, 1, 47-56, 2020.
[9] Li-Heng Hsieh, Effect of Iron Ore Concentrate on Sintering Properties, ISIJ International, 57, 11, 1937-1946, 2017.
[10] Satendra Kumar, Arvind Kumar Jaiswal, Rameshwar Sah, Marutiram Kaza, Manjini Sambandam and Prabhat Kumar Ghorui, An Innovative Approach for Utilization of Iron Ore Microfines (-150 microns) in Sintering, AISTech 2019, pp 495-499.
[11] Ziming Wang, Takayudi Maeda, Ko-ichiro Ohno and Kazuya Kunitomo, Effect of Magnetite on Mineral Phase Formation in Sintering Process, ISIJ International, 60, 2, 233-237, 2020.
[12] Chandra Shekhar Verma, Optimizing Sinter Chemistry to Counter Alumina Effect, AISTech 2019, pp 501 – 506.
[13] Hui Guo and Xing-Min Guo, Effect of Aluminum Occurrence State on the Formation of Calcium Ferrites in the Sintering Process of Iron Ore Fines, AISTech 2018, pp 595 – 606.
[14] M. Sinha, S. H. Nistala, S. Chandra, T. R. Mankhand and A. K. Ghose, Correlating mechanical properties of sinter phases with their chemistry and its effect on sinter quality, Ironmaking and Steelmaking, 44, 2, 100-107, 2017.
[15] C. E. Loo and R. D. Dukino, Laboratory iron ore sintering studies. 2 Quantifying flame front properties, Mineral Processing and Extractive Metallurgy, 123, 4, 197-203, 2014.
Cite This Article
  • APA Style

    Srijith Mohanan, Prajna Mohapatra, Arun Kumar C., Rama Krishna Adepu, Vipul Mohan Koranne, et al. (2021). Prediction and Optimization of Internal Return Fines Generation in Iron Ore Sintering Using Machine Learning. Advances in Materials, 10(3), 42-47. https://doi.org/10.11648/j.am.20211003.12

    Copy | Download

    ACS Style

    Srijith Mohanan; Prajna Mohapatra; Arun Kumar C.; Rama Krishna Adepu; Vipul Mohan Koranne, et al. Prediction and Optimization of Internal Return Fines Generation in Iron Ore Sintering Using Machine Learning. Adv. Mater. 2021, 10(3), 42-47. doi: 10.11648/j.am.20211003.12

    Copy | Download

    AMA Style

    Srijith Mohanan, Prajna Mohapatra, Arun Kumar C., Rama Krishna Adepu, Vipul Mohan Koranne, et al. Prediction and Optimization of Internal Return Fines Generation in Iron Ore Sintering Using Machine Learning. Adv Mater. 2021;10(3):42-47. doi: 10.11648/j.am.20211003.12

    Copy | Download

  • @article{10.11648/j.am.20211003.12,
      author = {Srijith Mohanan and Prajna Mohapatra and Arun Kumar C. and Rama Krishna Adepu and Vipul Mohan Koranne and Y. G. S. Prasad and A. S. Reddy and R. V. Ramna},
      title = {Prediction and Optimization of Internal Return Fines Generation in Iron Ore Sintering Using Machine Learning},
      journal = {Advances in Materials},
      volume = {10},
      number = {3},
      pages = {42-47},
      doi = {10.11648/j.am.20211003.12},
      url = {https://doi.org/10.11648/j.am.20211003.12},
      eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.am.20211003.12},
      abstract = {Prior to dispatch of sinter to the blast furnace for hot metal production, the sinter product from the sinter cooler is screened to remove smaller/finer particles. The undersize so generated is called internal return fines, which are generally recirculated into the sintering machine. A very high level of internal return fines generation limits the use of virgin ore for sintering which may hamper sinter productivity. Recently, the sinter plant at Tata Steel’s Kalinganagar works has faced issues of high internal return fines generation. As the sinter plant begins to increase its productivity levels, it becomes critical to control the generation of internal return fines to allow fresh material consumption. Limited literature is available on factors affecting the internal return fines generation in sinter plant. Given the current computational capabilities, a machine learning model was developed to ascertain the factors affecting the internal return fines generation. The development of the machine learning model and the optimization carried out based on model output is described in this work. The key parameters affecting the internal return fines generation were the sintering rate, sinter basicity, charge density and temperature in the ignition hood. In Kalinganagar, the increase in ignition hood temperature was limited by the furnace refractory condition. Further, the sinter basicity is determined by the percentage of sinter in blast furnace burden. Incorporating these constraints, the model was used to optimize the process parameters to generate the lowest possible return fines. The understanding generated from this machine learning framework has resulted in a reduction of 2-3% in internal return fines generation, which implied higher net sinter production.},
     year = {2021}
    }
    

    Copy | Download

  • TY  - JOUR
    T1  - Prediction and Optimization of Internal Return Fines Generation in Iron Ore Sintering Using Machine Learning
    AU  - Srijith Mohanan
    AU  - Prajna Mohapatra
    AU  - Arun Kumar C.
    AU  - Rama Krishna Adepu
    AU  - Vipul Mohan Koranne
    AU  - Y. G. S. Prasad
    AU  - A. S. Reddy
    AU  - R. V. Ramna
    Y1  - 2021/10/28
    PY  - 2021
    N1  - https://doi.org/10.11648/j.am.20211003.12
    DO  - 10.11648/j.am.20211003.12
    T2  - Advances in Materials
    JF  - Advances in Materials
    JO  - Advances in Materials
    SP  - 42
    EP  - 47
    PB  - Science Publishing Group
    SN  - 2327-252X
    UR  - https://doi.org/10.11648/j.am.20211003.12
    AB  - Prior to dispatch of sinter to the blast furnace for hot metal production, the sinter product from the sinter cooler is screened to remove smaller/finer particles. The undersize so generated is called internal return fines, which are generally recirculated into the sintering machine. A very high level of internal return fines generation limits the use of virgin ore for sintering which may hamper sinter productivity. Recently, the sinter plant at Tata Steel’s Kalinganagar works has faced issues of high internal return fines generation. As the sinter plant begins to increase its productivity levels, it becomes critical to control the generation of internal return fines to allow fresh material consumption. Limited literature is available on factors affecting the internal return fines generation in sinter plant. Given the current computational capabilities, a machine learning model was developed to ascertain the factors affecting the internal return fines generation. The development of the machine learning model and the optimization carried out based on model output is described in this work. The key parameters affecting the internal return fines generation were the sintering rate, sinter basicity, charge density and temperature in the ignition hood. In Kalinganagar, the increase in ignition hood temperature was limited by the furnace refractory condition. Further, the sinter basicity is determined by the percentage of sinter in blast furnace burden. Incorporating these constraints, the model was used to optimize the process parameters to generate the lowest possible return fines. The understanding generated from this machine learning framework has resulted in a reduction of 2-3% in internal return fines generation, which implied higher net sinter production.
    VL  - 10
    IS  - 3
    ER  - 

    Copy | Download

Author Information
  • Tata Steel Kalinganagar, Duburi, India

  • Tata Steel Kalinganagar, Duburi, India

  • Tata Steel Jamshedpur, Jamshedpur, India

  • Tata Steel Kalinganagar, Duburi, India

  • Tata Steel Jamshedpur, Jamshedpur, India

  • Tata Steel Kalinganagar, Duburi, India

  • Tata Steel Jamshedpur, Jamshedpur, India

  • Tata Steel Jamshedpur, Jamshedpur, India

  • Sections