Investigating the possibility of predicting iron recovery in iron ore processing plants based on feed grade using artificial intelligence

Document Type : Research paper

Authors

1 Faculty of Engineering, Shahid Bahonar University of Kerman, Kerman, Iran

2 Faculty of Mining Engineering, Isfahan University of Technology, Isfahan, Iran

Abstract

Objective: The aim of processing iron ore in processing plants is to achieve a product with an appropriate grade and maximum iron recovery. The amount of iron recovery in processing systems depends on several parameters, and its determination through weighing and laboratory tests is time-consuming and costly. With the development of the use of artificial intelligence for predicting and optimizing the performance of industrial systems, it seems that this technology could address many of the issues faced in mineral processing industries, including iron ore processing plants. Therefore, the objective of this research is to assess the feasibility of using artificial intelligence to predict iron recovery based on iron (Fe) and iron oxide (FeO) grades as the first step towards developing the application of this technology in the mining industry.
Materials and methods:  For this study, daily data on the Fe and FeO grades in the feed as well as iron recovery from the Central Iron Ore Concentrate Plant, which includes two production lines (Choghart and Sechahun), were collected. Iron recovery modeling was performed using two neural network models: MLP (Multilayer Perceptron Neural Network) and CFNN (Cascade Forward Neural Network). In this modeling, the Fe and FeO grades of the feed were treated as the model inputs, while iron recovery was considered the output.
Results: The results showed that both models performed relatively similarly, but CFNN exhibited better statistical parameters. The R² value for the CFNN model was obtained as 0.831 for the Choghart production line and 0.837 for the Sechahun line, while the RMSE for these models was calculated as 1.655 and 1.823, respectively. The analysis indicated that the CFNN model could confidently predict iron recovery with a relative error of less than 5% at a 95% confidence level for both production lines.
Conclusions: Using Fe and FeO grades alone as inputs for the models cannot lead to a comprehensive model that can replace conventional calculations. Therefore, the influence of other effective parameters will be thoroughly identified in this study. Additionally, sensitivity analysis revealed a direct relationship between iron recovery and both input parameters, with the Fe grade having a greater impact on iron recovery. The results of this study show that using artificial intelligence to predict iron recovery is very promising. By increasing model accuracy through the addition of data and input parameters, it is possible to develop models that can reduce the costs and time required for grade assessment in the plant.

Keywords

Main Subjects

References

[1] Mcnab, B., et al. Processing of magnetite iron ores-comparing grinding options. in Proceedings of the AusIMM Iron Ore Conference. 2009.
 
[2] Rovenskikh, M. and A. Kobzeva, Analysis of iron ore reserves in Russia and worldwide. Tsifrovaya ekonomika. Problemy i perspektivy razvitiya, 2019: p. 318-323.
 
[3] Hicyilmaz, C., et al., Mineral Processing on the Verge of the 21st Century: Proceedings of the 8th International Mineral Processing Symposium, Antalya, Turkey, 16-18 October 2000. 2017: Routledge.
 
[4] Xiong, D., L. Lu, and R. Holmes, Developments in the physical separation of iron ore: magnetic separation, in Iron ore. 2015, Elsevier. p. 283-307. https://doi.org/10.1016/B978-1-78242-156-6.00009-5.
 
[5] Karmazin, V., M. Bikbov, and A. Bikbov, The energy saving technology of beneficiation of iron ore. Physical Separation in Science and Engineering, 2002. 11(4): p. 211-224. https://doi.org/10.1080/1055691021000062813.
 
[6] Wang, F., et al., Investigation of the magnetic separation performance of a low-intensity magnetic separator embedded with auxiliary permanent magnets. Minerals Engineering, 2022. 178: p. 107399. https://doi.org/10.1016/j.mineng.2022.107399.
 
[7] Wang, F., et al., Performance assessment of an innovative precise low-intensity magnetic separator. Minerals Engineering, 2022. 187: p. 107774. https://doi.org/10.1016/j.mineng.2022.107774.
 
[8] Karimi, P., Z. Mansourpour, and A. Khodadadi Darban, Simulation of magnetic separation process in wet low intensity magnetic separator using DPM-CFD Method. Journal of Advanced Environmental Research and Technology, 2023. 1(1): p. 59-73. http://dx.doi.org/10.22034/jaert.1.1.59.
 
[9] Schulz, N.F., Determination of the magnetic separation characteristics with the Davis Magnetic Tube. Trans. SME-AIME, 1964. 229: p. 211-216.
 
[10] Makhula, M., et al., Statistical analysis and concentration of iron ore using Longi LGS 500 WHIMS. International Journal of Mining Science and Technology, 2016. 26(5): p. 769-775.https://doi.org/10.1016/j.ijmst.2016.05.052.
 
[11] Ren, L., S. Zeng, and Y. Zhang, Magnetic field characteristics analysis of a single assembled magnetic medium using ANSYS software. International Journal of Mining Science and Technology, 2015. 25(3): p. 479-487. https://doi.org/10.1016/j.ijmst.2015.03.024.
 
[12] Li, W., et al., A preliminary investigation into separating performance and magnetic field characteristic analysis based on a novel matrix. Minerals, 2018. 8(3): p. 94. https://www.mdpi.com/2075-163X/8/3/94#.
 
[13] Dobbins, M., J. Domenico, and P. Dunn. A discussion of magnetic separation techniques for concentrating ilmenite and chromite ores. in The 6th international heavy minerals conference “back to basics”, The Southern African Institute of Mining and Metallurgy. 2007.
 
[14] Guarin, C., et al., The K Deeps magnetite mineralisation at Koolyanobbing, Western Australia. Applied Earth Science, 2010. 119(3): p. 143-153. https://doi.org/10.1179/1743275811Y.0000000009.
 
[15] Wills, B.A. and J. Finch, Wills' mineral processing technology: an introduction to the practical aspects of ore treatment and mineral recovery. 2015: Butterworth-heinemann. https://doi.org/10.2138/am.2008.502.
 
[16] Shahcheraghi, S.H., et al., A simple model for predicting optimal weight recovery of industrial iron ore processing–case study: Iranian iron ore mines. Canadian Metallurgical Quarterly, 2023. 62(2): p. 295-300. https://doi.org/10.1080/00084433.2022.2075074.
 
[17] Tahami, M., et al., Integration of experimental study and neural network modeling for estimating iron recovery in Davis tube tests. Scientific Reports, 2024. 14(1): p. 22578. https://doi.org/10.1038/s41598-024-72850-w.
 
[18] Paledi, U., et al., Selectivity index and separation efficiency prediction in industrial magnetic separation process using a hybrid neural genetic algorithm. SN Applied Sciences, 2021. 3(3): p. 351. https://doi.org/10.1007/s42452-021-04361-6.
 
[19] Izadi-Yazdan Abadi, M., R. Shokrizadeh, and F. Heydari, Development of a model for iron concentrate tonnage with least angle regressions–An industrial trial. Canadian Metallurgical Quarterly, 2024: p. 1-10. https://doi.org/10.1080/00084433.2024.2366715.
 
[20] Technical Operation Manual for Choghart Production Line, Volume 1 of 2. 1999.
 
[21] Lashkarbolooki, M., A.Z. Hezave, and S. Ayatollahi, Artificial neural network as an applicable tool to predict the binary heat capacity of mixtures containing ionic liquids. Fluid Phase Equilibria, 2012. 324: p. 102-107.
https://doi.org/10.1016/j.fluid.2012.03.015.
 
[22] Hemmati-Sarapardeh, A., et al., On the evaluation of the viscosity of nanofluid systems: Modeling and data assessment. Renewable and Sustainable Energy Reviews, 2018. 81: p. 313-329.
https://doi.org/10.1016/j.rser.2017.07.049.
 
[23] Hemmati‐Sarapardeh, A., et al., Accurate determination of the CO2‐crude oil minimum miscibility pressure of pure and impure CO2 streams: a robust modelling approach. The Canadian Journal of Chemical Engineering, 2016. 94(2): p. 253-261.https://doi.org/10.1002/cjce.22387.
 
[24] De Jesus, O. and M.T. Hagan, Backpropagation algorithms for a broad class of dynamic networks. IEEE Transactions on Neural Networks, 2007. 18(1): p. 14-27. https://doi.org/10.1109/TNN.2006.882371.
 
[25] Nami, F. and F. Deyhimi, Prediction of activity coefficients at infinite dilution for organic solutes in ionic liquids by artificial neural network. The Journal of Chemical Thermodynamics, 2011. 43(1): p. 22-27. https://doi.org/10.1016/j.jct.2010.07.011.
 
[26] Hemmati-Sarapardeh, A., et al., Applications of artificial intelligence techniques in the petroleum industry. 2020: Gulf Professional Publishing. https://doi.org/10.1016/C2018-0-04421-7.
 
Journal of Separation Science and Engineering
Volume 16, Issue 2
December 2024
Pages 92-107

Files

Share

How to cite

Statistics