Optimization of smelting process of magnesium based on machine learning
Abstract
The traditional magnesium reduction process consumes a significant amount of energy, which contradicts China’s green and low-carbon development goals. Therefore, exploring more energy-efficient methods is crucial for environmental protection. The magnesium reduction rate is influenced by several factors, including gas flow rate, briquetting pressure, ferrosilicon content, reduction temperature, and reduction time. In this study, data analysis utilizing a machine learning algorithm: support vector machine (SVM)—was employed to predict the magnesium reduction rate. Given that energy-saving processes are a primary objective for enterprises, the processing was optimized using the particle swarm optimization (PSO) algorithm based on the SVM model, while maintaining a constant magnesium reduction rate. This optimization aims to reduce energy and gas consumption during the magnesium smelting process. Experimental verification of the magnesium reduction rate under the optimized processing conditions demonstrated that the application of machine learning algorithms can lead to resource savings in the magnesium reduction process. To further evaluate the environmental benefits of the optimized process, a Life Cycle Assessment (LCA) focusing on energy consumption and carbon dioxide (CO2) emissions was conducted. The LCA results indicate that the optimized process significantly reduces life cycle energy consumption (reduced by 5.33%) and CO2 emissions (reduced by 3.63%) compared with the initial process, providing precise environmental performance data for the promotion and application of magnesium alloys in lightweight structures.
References
W.J. Joost, P.E. Krajewski, Towards magnesium alloys for high-volume automotive applications, Scripta Materialia, 128 (2017) 107–112. https://doi.org/10.1016/j.scriptamat.2016.07.035
A. Maqbool, N.Z. Khan, A.N. Siddiquee, Towards Mg based light materials of future: properties, applications, problems, and their mitigation, Journal of Manufacturing Science and Engineering, 144 (3) (2022) 030801. https://doi.org/10.1115/1.4051678
T. Kurzynowski, A. Pawlak, I. Smolina, The potential of SLM technology for processing magnesium alloys in aerospace industry, Archives of Civil and Mechanical Engineering, 20 (1) (2020) 23. https://doi.org/10.1007/s43452-020-00033-1
D.D. Zhang, F. Peng, X.Y. Liu, Protection of magnesium alloys: from physical barrier coating to smart self-healing coating, Journal of Alloys and Compounds, 853 (2021) 157010. https://doi.org/10.1016/j.jallcom.2020.157010
Z.Z. Yin, W.C. Qi, R.C. Zeng, X.B. Chen, C.D. Gu, S.K. Guan, Y.F. Zheng, Advances in coatings on biodegradable magnesium alloys, Journal of Magnesium Alloys, 8 (1) (2020) 42–65. https://doi.org/10.1016/j.jma.2019.09.008
W.J. Botta, G. Zepon, T.T. Ishikawa, D.R. Leiva, Metallurgical processing of Mg alloys and MgH₂ for hydrogen storage, Journal of Alloys and Compounds, 897 (2022) 162798. https://doi.org/10.1016/j.jallcom.2021.162798
Q.C. Yu, Y. Deng, S.B. Yin, Z.Y. Li, Thermal process for magnesium production with Al-Si-Fe from coal fly ash: thermodynamics and experimental investigation, Journal of Mining and Metallurgy, Section B: Metallurgy, 57 (3) (2021) 421–430. https://doi.org/10.2298/JMMB210118038Y
J. Du, W. Han, Y. Peng, Life cycle greenhouse gases, energy and cost assessment of automobiles using magnesium from Chinese Pidgeon process, Journal of Cleaner Production, 18 (2) (2010) 112–119. https://doi.org/10.1016/j.jclepro.2009.08.013
Y.S. Che, G.P. Mai, S.J. Zhang, J.L. He, J.X. Song, J.H. Yi, Kinetic mechanism of magnesium production by silicothermic reduction of CaOxMgO in vacuum, Transactions of Nonferrous Metals Society of China, 30 (10) (2020) 2812–2822. https://doi.org/10.1016/S1003-6326(20)65423-1
Y. Tian, L.P. Wang, B. Yang, Y.N. Dai, B.Q. Xu, F. Wang, N. Xiong, Comparative evaluation of energy and resource consumption for vacuum carbothermal reduction and Pidgeon process used in magnesium production, Journal of Magnesium Alloys, 10 (3) (2022) 697–706. https://doi.org/10.1016/j.jma.2020.09.024
M. Abdellatif, Review of the development work on the Mintek thermal magnesium process (MTMP), Journal of the South African Institute of Mining and Metallurgy, 111 (6) (2011) 393–399. https://www.saimm.co.za/Journal/v111n06p393.pdf.
C. Zhang, C. Wang, S.J. Zhang, L.J. Guo, Experimental and numerical studies on a one-step method for the production of Mg in the silicothermic reduction process, Industrial & Engineering Chemistry Research, 54 (36) (2015) 8883–8892. https://doi.org/10.1021/acs.iecr.5b01830.
D.X. Fu, T.A. Zhang, Z.H. Dou, L.K. Guan, A new energy-efficient and environmentally friendly process to produce magnesium, Canadian Metallurgical Quarterly, 56 (4) (2017) 418–425. https://doi.org/10.1080/00084433.2017.1361178
Y. Wada, S. Fujii, E. Suzuki, M.M. Maitani, S. Tsubaki, S. Chonan, M. Fukui, N. Inazu, Smelting magnesium metal using a microwave Pidgeon method, Scientific Reports, 7 (1) (2017) 46512. https://doi.org/10.1038/srep46512
N. Xiong, Y. Tian, D. Yang, B.Q. Xu, T. Dai, Y.N. Dai, Results of recent investigations of magnesia carbothermal reduction in vacuum, Vacuum, 160 (2019) 213–225. https://doi.org/10.1016/j.vacuum.2018.11.007
B.A. Chubukov, S.C. Rowe, A.W. Palumbo, M.A. Wallace, A.W. Weimer, Investigation of continuous carbothermal reduction of magnesia by magnesium vapor condensation onto a moving bed of solid particles, Powder Technology, 365 (2020) 2–11. https://doi.org/10.1016/j.powtec.2019.01.067
J.H. Guo, D.X. Fu, J.B. Han, Z.H. Ji, Z.H. Dou, T.A. Zhang, Kinetics of extracting magnesium from prefabricated pellets by silicothermic process under flowing argon atmosphere, Journal of Mining and Metallurgy, Section B: Metallurgy, 56 (3) (2020) 379– 386. https://doi.org/10.2298/JMMB200712031G.
J.H. Guo, X. Li, T.A. Zhang, J.B. Han, J.Y. Geng, Y.S. Wang, Comparison of extraction behavior of magnesium from magnesite/magnesia by aluminothermic process in flowing argon, Journal of Sustainable Metallurgy, 8 (2022) 1756–1768. https://doi.org/10.1007/s40831-022-00604-x
J.B. Han, D.X. Fu, J.H. Guo, Z.H. Ji, T.A. Zhang, Volatilization and condensation behavior of magnesium vapor during magnesium production via a silicothermic process with magnesite, Vacuum, 189 (2021) 110227. https://doi.org/10.1016/j.vacuum.2021.110227
S.H. Farjana, N. Huda, M.A.P. Mahmud, R. Saidur, A review on impact of mining and mineral processing industries through life cycle assessment, Journal of Cleaner Production, 231 (2019) 1200-1217. https://doi.org/10.1016/j.jclepro.2019.05.264
Y.T. Wang, C.Y. Zhang, Y. Rezgui, A. Ghoroghi, Z.W. Luo, Y.J. Li, T.Y. Zhao, From buildings to district: A systematic review of life cycle assessment approaches for energy system planning and optimization, Building and Environment, 295 (2026) 114441. https://doi.org/10.1016/j.buildenv.2026.114441.
Y.L. Liu, C. Niu, Z. Wang, Y. Gan, Y. Zhu, S. Sun, T. Shen, Machine learning in materials genome initiative: A review, Journal of Materials Science & Technology, 57 (2020) 113–122. https://doi.org/10.1016/j.jmst.2020.01.067.
C.G. Shen, C.C. Wang, X.L. Wei, Y. Li, S.V.D. Zwaag, W. Xu, Physical metallurgy-guided machine learning and artificial intelligent design of ultrahigh-strength stainless steel, Acta Materialia, 179 (2019) 201-214. https://doi.org/10.1016/j.actamat.2019.08.033.
X. Li, Q.M. Jiang, X.G. Zhou, G.M. Cao, G.D. Wang, Z.Y. Liu, Machine learning complex interactions among recovery, precipitation, and recrystallization for Nb micro-alloyed steels, Metals and Materials International, 30 (1) (2023) 167–181. https://doi.org/10.1007/s12540-023-01493-9.
X.F. Wang, F. Mao, X. Li, K.L. Miao, R.X. Shi, Y.C. Lin, C. Chen, C.J. Wang, H. Yu, S.Z. Wei, Machine learning-based prediction of microstructure and mechanical properties for 12Cr2Mo1V large cylindrical forgings, Materials Today Communications, 47 (2025) 112983. https://doi.org/10.1016/j.mtcomm.2025.112983
Y. Zhong, F. Mao, X. Li, K.L. Miao, R.X. Shi, B.N. Yu, C. Chen, C.J. Wang, H. Yu, S.Z. Wei, Prediction of mechanical properties of 16Mn large tube plates based on machine learning, Materials Today Communications, 49 (2025) 113712. https://doi.org/10.1016/j.mtcomm.2025.113712
Y.F. Wen, C.Z. Cai, X.H. Liu, J.F. Pei, X.J. Zhu, T.T. Xiao, Corrosion rate prediction of 3C steel under different seawater environment by using support vector regression, Corrosion Science, 51 (2009) 349-355. https://doi.org/10.1016/j.corsci.2008.10.038
X. Li, Q.M. Jiang, X.G. Zhou, S.W. Wu, G.M. Cao, Z.Y. Liu, Machine learning interphase precipitation behavior of Ti micro-alloyed steel guided by physical metallurgy principle, Journal of Materials Research and Technology, 25 (2023) 2641–2653. https://doi.org/10.1016/j.jmrt.2023.06.077
L. Wu, F. Han, G. Liu, Magnesium smelting via the Pidgeon process, Springer, Singapore, 2021, p.45-68.
Authors retain copyright of the published papers and grant to the publisher the non-exclusive right to publish the article, to be cited as its original publisher in case of reuse, and to distribute it in all forms and media.
The Author(s) warrant that their manuscript is their original work that has not been published before; that it is not under consideration for publication elsewhere; and that its publication has been approved by all co-authors, if any, as well as tacitly or explicitly by the responsible authorities at the institution where the work was carried out. The Author(s) affirm that the article contains no unfounded or unlawful statements and does not violate the rights of others. The author(s) also affirm that they hold no conflict of interest that may affect the integrity of the Manuscript and the validity of the findings presented in it. The Corresponding author, as the signing author, warrants that he/she has full power to make this grant on behalf of the Author(s). Any software contained in the Supplemental Materials is free from viruses, contaminants or worms.The published articles will be distributed under the Creative Commons Attribution ShareAlike 4.0 International license (CC BY-SA).
Authors are permitted to deposit publisher's version (PDF) of their work in an institutional repository, subject-based repository, author's personal website (including social networking sites, such as ResearchGate, Academia.edu, etc.), and/or departmental website at any time after publication.
Upon receiving the proofs, the Author(s) agree to promptly check the proofs carefully, correct any typographical errors, and authorize the publication of the corrected proofs.
The Corresponding author agrees to inform his/her co-authors, of any of the above terms.