Nuclear Engineering and Technology

Korean Nuclear Society (한국원자력학회)
권호 표지
DOI QR코드

DOI QR Code

Online analysis of iron ore slurry using PGNAA technology with artificial neural network

  • Haolong Huang (Department of Nuclear Science and Technology, Nanjing University of Aeronautics and Astronautics) ;
  • Pingkun Cai (Department of Nuclear Science and Technology, Nanjing University of Aeronautics and Astronautics) ;
  • Xuwen Liang (Department of Nuclear Science and Technology, Nanjing University of Aeronautics and Astronautics) ;
  • Wenbao Jia (Department of Nuclear Science and Technology, Nanjing University of Aeronautics and Astronautics)
  • Received : 2023.06.05
  • Accepted : 2024.02.22
  • Published : 2024.07.25
Download PDF
⟨ Previous Next ⟩

Abstract

Real-time analysis of metallic mineral grade and slurry concentration is significant for improving flotation efficiency and product quality. This study proposes an online detection method of ore slurry combining the Prompt Gamma Neutron Activation Analysis (PGNAA) technology and artificial neural network (ANN), which can provide mineral information rapidly and accurately. Firstly, a PGNAA analyzer based on a D-T neutron generator and a BGO detector was used to obtain a gamma-ray spectrum dataset of ore slurry samples, which was used to construct and optimize the ANN model for adaptive analysis. The evaluation metrics calculated by leave-one-out cross-validation indicated that, compared with the weighted library least squares (WLLS) approach, ANN obtained more precise and stable results, with mean absolute percentage errors of 4.66% and 2.80% for Fe grade and slurry concentration, respectively, and the highest average standard deviation of only 0.0119. Meanwhile, the analytical errors of the samples most affected by matrix effects was reduced to 0.61 times and 0.56 times of the WLLS method, respectively.

Keywords

Acknowledgement

This work was supported by the National Natural Science Foundation of China (Grant No.11975121).

References

  1. J. Wu, J. Yang, L. Ma, Z. Li, X. Shen, A system analysis of the development strategy of iron ore in China, Resour. Pol. 48 (2016) 32-40, https://doi.org/10.1016/j.resourpol.2016.01.010.
  2. M. Yellishetty, P.G. Ranjith, A. Tharumarajah, Iron ore and steel production trends and material flows in the world: is this really sustainable? Resour. Conserv. Recycl. 54 (2010) 1084-1094, https://doi.org/10.1016/j.resconrec.2010.03.003.
  3. X. Luo, B. Feng, C. Wong, J. Miao, B. Ma, H. Zhou, The critical importance of pulp concentration on the flotation of galena from a low grade lead-zinc ore, J. Mater. Res. Technol. 5 (2016) 131-135, https://doi.org/10.1016/j.jmrt.2015.10.002.
  4. H. Li, Z. Xu, W. Wang, Y. Liu, S. Zhang, A novel technique for online slurry grade detection based on EDXRF, Miner. Eng. 131 (2019) 14-22, https://doi.org/10.1016/j.mineng.2018.11.004.
  5. X. Cheng, X. Yang, Z. Zhu, L. Guo, X. Li, Y. Lu, X. Zeng, On-stream analysis of iron ore slurry using laser-induced breakdown spectroscopy, Appl. Opt. 56 (2017) 9144, https://doi.org/10.1364/ao.56.009144.
  6. N. Khajehzadeh, O. Haavisto, L. Koresaar, On-stream mineral identification of tailing slurries of an iron ore concentrator using data fusion of LIBS, reflectance spectroscopy and XRF measurement techniques, Miner. Eng. 113 (2017) 83-94, https://doi.org/10.1016/j.mineng.2017.08.007.
  7. A.A. Naqvi, M. Maslehuddin, Z. Kalakada, O.S.B. Al-Amoudi, Prompt gamma ray evaluation for chlorine analysis in blended cement concrete, Appl. Radiat. Isot. 94 (2014) 8-13, https://doi.org/10.1016/j.apradiso.2014.06.011.
  8. A.A. Naqvi, M. Maslehuddin, M.A. Garwan, M.M. Nagadi, O.S.B. Al-Amoudi, M. Raashid, Khateeb-ur-Rehman, Effect of silica fume addition on the PGNAA measurement of chlorine in concrete, Appl. Radiat. Isot. 68 (2010) 412-417, https://doi.org/10.1016/j.apradiso.2009.11.044.
  9. L. Tian, F. Zhang, J. Liu, X. Wang, Y. Ti, Monte Carlo simulation of Cu, Ni and Fe grade determination in borehole by PGNAA technique, J. Radioanal. Nucl. Chem. 315 (2017) 51-56, https://doi.org/10.1007/s10967-017-5636-9.
  10. J. Li, W. Jia, D. Hei, Y. Tang, C. Cheng, P. Cai, A. Sun, D. Zhao, Q. Hu, Design of the explosion-proof detection integrated system based on PGNAA technology, J. Radioanal. Nucl. Chem. 322 (2019) 1719-1728, https://doi.org/10.1007/s10967-019-06837-7.
  11. K.-X. Peng, J.-B. Yang, X.-G. Tuo, H. Du, R.-X. Zhang, Research on PGNAA adaptive analysis method with BP neural network, Mod. Phys. Lett. B 30 (2016) 1650386, https://doi.org/10.1142/s0217984916503863.
  12. I.A. Reyhancan, B. Untuc, M.N. Erduran, MCNP5 element library least squares method for on-line coal analysis, J. Nucl. Sci. (Seoul) 3 (2016) 27-34, https://doi.org/10.1501/nuclear_0000000017.
  13. R.P. Gardner, L. Xu, Status of the Monte Carlo library least-squares (MCLLS) approach for non-linear radiation analyzer problems, Radiat. Phys. Chem. 78 (2009) 843-851, https://doi.org/10.1016/j.radphyschem.2009.04.023.
  14. A. Sun, W. Jia, D. Hei, M. Qiu, C. Cheng, J. Li, A full spectral analysis method for the gamma spectrum: weighted library least squares, Anal. Methods 13 (2021) 4718-4723, https://doi.org/10.1039/d1ay01319j.
  15. M. Kamuda, J. Zhao, K. Huff, A comparison of machine learning methods for automated gamma-ray spectroscopy, Nucl. Instrum. Methods Phys. Res. Sect. A Accel. Spectrom. Detect. Assoc. Equip. 954 (2020) 161385, https://doi.org/10.1016/j.nima.2018.10.063.
  16. S.M. Galib, P.K. Bhowmik, A.V. Avachat, H.K. Lee, A comparative study of machine learning methods for automated identification of radioisotopes using NaI gamma-ray spectra, Nucl. Eng. Technol. 53 (2021) 4072-4079, https://doi.org/10.1016/j.net.2021.06.020.
  17. H. Shahabinejad, N. Vosoughi, Analysis of complex gamma-ray spectra using particle swarm optimization, Nucl. Instrum. Methods Phys. Res. Sect. A Accel. Spectrom. Detect. Assoc. Equip. 911 (2018) 123-130, https://doi.org/10.1016/j.nima.2018.09.156.
  18. A. Ghalehasadi, S. Ashrafi, D. Alizadeh, N. Meric, Gamma ray interactions based optimization algorithm: application in radioisotope identification, Nucl. Eng. Technol. 53 (2021) 3772-3783, https://doi.org/10.1016/j.net.2021.05.018.
  19. K. Wang, X. Bian, X. Tan, H. Wang, Y. Li, A new ensemble modeling method for multivariate calibration of near infrared spectra, Anal. Methods 13 (2021) 1374-1380, https://doi.org/10.1039/d1ay00017a.
  20. P. Cai, D. Hei, J. Chen, W. Jia, C. Cheng, A. Sun, D. Zhao, Design of a DT neutron source based PGNAA facility for element determination in aqueous solution, Appl. Radiat. Isot. 188 (2022) 110394, https://doi.org/10.1016/j.apradiso.2022.110394.
  21. N.J. Beukes, J. Gutzmer, J. Mukhopadhyay, The geology and genesis of high-grade hematite iron ore deposits, B. Appl. Earth Sci. 112 (2003) 18-25, https://doi.org/10.1179/037174503225011243.
  22. S. Qi, S. Wang, Y. Chen, K. Zhang, X. Ai, J. Li, H. Fan, H. Zhao, Radionuclide identification method for NaI low-count gamma-ray spectra using artificial neural network, Nucl. Eng. Technol. 54 (2022) 269-274, https://doi.org/10.1016/j.net.2021.07.025.
  23. D.P. Kingma, J.L. Ba, Adam: a method for stochastic optimization, in: ICLR 2015 : International Conference on Learning Representations 2015, 2015.
  24. G. Aksu, C.O. Guzeller, M.T. Eser, The effect of the normalization method used in different sample sizes on the success of artificial neural network model, International Journal of Assessment Tools in Education 6 (2019) 170-192, https://doi.org/10.21449/ijate.479404.
  25. H. Ide, T. Kurita, Improvement of learning for CNN with ReLU activation by sparse regularization, in: 2017 International Joint Conference on Neural Networks (IJCNN), IEEE, 2017, pp. 2684-2691.
  26. P. Refaeilzadeh, L. Tang, H. Liu, Cross-Validation, Encyclopedia of Database Systems, 2016, pp. 1-7, https://doi.org/10.1007/978-1-4899-7993-3_565-2.
  27. W. Jia, C. Cheng, D. Hei, Y. Ling, H. Wang, D. Chen, Method for correcting thermal neutron self-shielding effect for aqueous bulk sample analysis by PGNAA technique, J. Radioanal. Nucl. Chem. 304 (2015) 1133-1137, https://doi.org/10.1007/s10967-015-3962-3.