Abstract
An artificial neural network model to predict the performance of induced roll high-intensity magnetic separator while upgrading low-grade iron ore fines is presented in the present investigation. Key process parameters of induced roll magnetic separator operation, i.e., applied current, speed of rotor, splitter position, particle size, and feed rate, are used as the network input. A feedforward ANN is designed with one hidden layer, with units varying from 9 to 40 and capable of estimating the separation performance (iron content, silica content, iron recovery, and silica rejection of the magnetic product) in an induced roll magnetic separator. Simulated results obtained using the neural network modeling correspond closely to the actual results with a correlation of coefficient (R2) > 0.95 in training and testing stages. The developed models are further used to understand the sensitivity of the studied variables. The effects of speed of the rotor and splitter position are found to be more sensitive to the separation. Furthermore, an optimized solution is designed to predict the best achievable grade-recovery curve for this pre-concentration.
Similar content being viewed by others
References
Pradip, Met Mater Process6 (1994) 179.
Jena S, Sahoo H, Rath S, Rao D, Das S, and Das B, Miner Process Extract Metall Rev36 (2015) 174.
Das B, Prakash S, Bhaumik S, Mohapatra B, and Narasimhan K, Trans Indian Inst Met India44 (1991) 355.
Li C, Sun H, Bai J, and Li L, J Hazard Mater174 (2010) 71.
Song S, Lu S, and Lopez-Valdivieso A, Miner Eng15 (2002) 415.
Filippov L, Severov V, and Filippova I, Int J Miner Process127 (2014) 62.
Zhang X, Han Y, Sun Y, Lv Y, Li Y, and Tang Z, Miner Process Extract Metall Rev41 (2020) 117.
Suthers S P, Pinto P, Nunna V, and Nguyen A V, Miner Process Extract Metall Rev40 (2019) 344.
Nunna V, Hapugoda S, Eswarappa S G, Raparla S K, Kumar R, and Nanda N K, Miner Process Extract Metall Rev40 (2019) 356.
Song S, Zhang G, Luo Z, and Lv B, Miner Process Extract Metall Rev40 (2019) 307.
Xu X, Chen J, Luo Z, Tang L, Zhao Y, Lv B, Fu Y, and Chen C, Miner Process Extract Metall Rev40 (2019) 299.
Moura L C, André F P, Miceli H, Neumann R, and Tavares L M, Miner Process Extract Metall Rev40 (2019) 333.
Eswaraiah C, Soni R K, Tripathy S K, and Filippov L O, Miner Process Extract Metall Rev 1 (2019).
Dwari R K, Rao D S, and Reddy P S R, Int J Min Sci Technol23 (2013) 1.
Dwari R, Rao D, and Reddy P, J Inst Eng India Ser D95 (2014) 115.
Tripathy S K, Banerjee P, and Suresh N, Powder Technol264 (2014) 527.
Tripathy S K, Banerjee P, Suresh N, Murthy Y R, and Singh V, Miner Process Extract Metall Rev38 (2017) 339.
Mohanty I and Bhattacherjee D, Computational Approaches to Materials Design: Theoretical and Practical Aspects, IGI Global, pp. 267–300 (2016).
Jorjani E, Chelgani S C, and Mesroghli S, Miner Eng20 (2007) 1285.
Al-Thyabat S, J China Univ Min Technol18 (2008) 418.
Cilek E, Miner Eng15 (2002) 1095.
Moolman D, Aldrich C, Van Deventer J, and Stange W, Int J Miner Process43 (1995) 193.
Massinaei M and Doostmohammadi R, Miner Eng23 (2010) 83.
Labidi J, Pelach M, Turon X, and Mutje P, Chem Eng Process Process Intensif46 (2007) 314.
Kalyani V, Charan T G, Haldar D, Sinha A, and Suresh N, Int J Coal Prep Util28 (2008) 94.
Charan T G, Kalyani V, Sharma K, Kumar L, Kumari S, and Sinha A, Int J Coal Prep Util34 (2014) 229.
Kalyani V, Pallavika, Chaudhuri S, Gouri Charan T, Haldar D, Kamal K, Badhe Y, Tambe S, and Kulkarni B, Miner Process Extract Metall Rev29 (2007) 130.
Özbayoğlu G, Özbayoğlu A M, and Özbayoğlu M E, Int J Miner Process85 (2008) 93.
Chelgani S C, Hower J C, Jorjani E, Mesroghli S, and Bagherieh A, Fuel Process Technol89 (2008) 13.
Jämsä-Jounela S L and Oja M, Filtrat Sep37 (2000) 39.
Raman G S and Klima M S, Miner Process Extract Metall Rev38 (2017) 47.
Raman G S, Klima M S, and Bishop J M, Int J Miner Process158 (2017) 76.
Raman G S and Klima M S, Miner Process Extract Metall Rev40 (2019) 148.
Panda L and Tripathy S K, Int J Min Sci Technol24 (2014) 461.
Lai K C, Lim S K, Teh P C, and Yeap K H, Proc Comput Sci91 (2016) 372.
Fujiwara E, dos Santos M F M, Schenkel E A, Ono E, and Suzuki C K, Miner Process Extract Metall Rev36 (2015) 281.
Karimi M, Dehghani A, Nezamalhosseini A, and Talebi S, J S Afr Inst Min Metall110 (2010) 207.
Chaurasia R C and Nikkam S, Part Sci Technol35 (2017) 93.
Tripathy S K, Singh V, Murthy Y R, Banerjee P, and Suresh N, Int J Miner Process160 (2017) 16.
Tripathy S K and Suresh N, Adv Powder Technol28 (2017) 1092.
Zong Q X, Fu L Z, and Bo L, EDP Sciences, p. 02019 (2018).
Mohanty I, Bhattacharjee D, and Datta S, Comput Mater Sci50 (2011) 2331.
Mohanty I, Datta S, and Bhattacharjee D, Mater Manuf Process24 (2008) 100.
Haykin S, Neural Networks: A Comprehensive Foundation, Prentice Hall PTR (1994).
Mohanty I, Sarkar S, Jha B, Das S, and Kumar R, Ironmak Steelmak41 (2014) 618.
Acknowledgement
The authors are thankful to the management of Tata Steel Ltd. for the support and permission to publish this study. SKT would like to acknowledge Labex Resources 21 supported by the French National Research Agency through the national program “Investissements d’Avenir” [reference ANR–10–LABX–21] for his fellowship.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Tripathy, S.K., Mohanty, I. & Filippov, L.O. Application of Artificial Neural Networks to Predict Dry Magnetic Separation of Low-Grade Hematite Fines. Trans Indian Inst Met 73, 1797–1807 (2020). https://doi.org/10.1007/s12666-020-01985-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12666-020-01985-x