Nuclear Engineering and Technology

Korean Nuclear Society (한국원자력학회)
권호 표지
DOI QR코드

DOI QR Code

Identification of Pb-Zn ore under the condition of low count rate detection of slim hole based on PGNAA technology

  • 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) ;
  • Wenbao Jia (Department of Nuclear Science and Technology, Nanjing University of Aeronautics and Astronautics) ;
  • Yan Zhang (Engineering Research Center of Nuclear Technology Application, Ministry of Education, East China University of Technology)
  • Received : 2022.09.02
  • Accepted : 2023.01.04
  • Published : 2023.05.25
Download PDF
⟨ Previous Next ⟩

Abstract

The grade analysis of lead-zinc ore is the basis for the optimal development and utilization of deposits. In this study, a method combining Prompt Gamma Neutron Activation Analysis (PGNAA) technology and machine learning is proposed for lead-zinc mine borehole logging, which can identify lead-zinc ores of different grades and gangue in the formation, providing real-time grade information qualitatively and semi-quantitatively. Firstly, Monte Carlo simulation is used to obtain a gamma-ray spectrum data set for training and testing machine learning classification algorithms. These spectra are broadened, normalized and separated into inelastic scattering and capture spectra, and then used to fit different classifier models. When the comprehensive grade boundary of high- and low-grade ores is set to 5%, the evaluation metrics calculated by the 5-fold cross-validation show that the SVM (Support Vector Machine), KNN (K-Nearest Neighbor), GNB (Gaussian Naive Bayes) and RF (Random Forest) models can effectively distinguish lead-zinc ore from gangue. At the same time, the GNB model has achieved the optimal accuracy of 91.45% when identifying high- and low-grade ores, and the F1 score for both types of ores is greater than 0.9.

Keywords

Acknowledgement

This work was supported by the NSAF (Grant No. U1930125), the National Natural Science Foundation of China (11975121 and 41904160).

References

  1. H.Y. Chen, A.J. Li, D.E. Finlow, The lead and lead-acid battery industries during 2002 and 2007 in China, J. Power Sources 191 (2009) 22-27, https://doi.org/10.1016/j.jpowsour.2008.12.140.
  2. Z. Guo, Y. Ma, X. Dong, J. Huang, Y. Wang, Y. Xia, Environmentally friendly and flexible aqueous zinc battery using an organic cathode, Angew Chem. Int. Ed. Engl. 57 (2018) 11737-11741, https://doi.org/10.1002/anie.201807121.
  3. A. Verbic, M. Gorjanc, B. Simoncic, Zinc oxide for functional textile coatings: recent advances, Coatings 9 (2019), https://doi.org/10.3390/coatings9090550.
  4. K.S. Nair, M. Mittal, K. Lal, R. Mahanti, C. Sivaramakrishnan, Development of rapidly solidified (RS) magnesium-aluminium-zinc alloy, Mater. Sci. Eng., A 304 (2001) 520-523.
  5. J.P. McCaffrey, H. Shen, B. Downton, E. Mainegra-Hing, Radiation attenuation by lead and nonlead materials used in radiation shielding garments, Med. Phys. 34 (2007) 530-537, https://doi.org/10.1118/1.2426404.
  6. G.M. Mudd, S.M. Jowitt, T.T. Werner, The world's lead-zinc mineral resources: scarcity, data, issues and opportunities, Ore Geol. Rev. 80 (2017) 1160-1190, https://doi.org/10.1016/j.oregeorev.2016.08.010.
  7. J. Charbucinski, J. Malos, A. Rojc, C. Smith, Prompt gamma neutron activation analysis method and instrumentation for copper grade estimation in large diameter blast holes, Appl. Radiat. Isot. 59 (2003) 197-203, https://doi.org/10.1016/s0969-8043(03)00163-5.
  8. J. Charbucinski, O. Duran, R. Freraut, N. Heresi, I. Pineyro, The application of PGNAA borehole logging for copper grade estimation at Chuquicamata mine, Appl. Radiat. Isot. 60 (2004) 771-777, https://doi.org/10.1016/j.apradiso.2003.12.007.
  9. M. Borsaru Z.J, Application of PGNAA for bulk coal samples in a 4p geometry, Appl. Radiat. Isot. 54 (3) (2001) 519-526, https://doi.org/10.1016/S0969-8043(99)00276-6.
  10. A.A. Naqvi, M.M. Nagadi, S. Kidwai, R. Khateeb ur, M. Maslehuddin, Search of a prompt gamma ray for chlorine analysis in a Portland cement sample, Nucl. Instrum. Methods Phys. Res. Sect. A Accel. Spectrom. Detect. Assoc. Equip. 533 (2004) 591-597, https://doi.org/10.1016/j.nima.2004.06.132.
  11. K. Hossny, S. Magdi, A.Y. Soliman, A.H. Hossny, Detecting explosives by PGNAA using KNN Regressors and decision tree classifier: a proof of concept, Prog. Nucl. Energy 124 (2020), https://doi.org/10.1016/j.pnucene.2020.103332.
  12. K. Oh, Neutronic design of pulsed neutron facility (PNF) for PGNAA studies of biological samples, Nucl. Eng. Technol. (2022), https://doi.org/10.1016/j.net.2021.07.024.
  13. K. Trofimczyk, S. Saraswatibhatla, C. Smith, Spectrometric nuclear logging as a tool for real-time, downhole assay - case studies using SIROLOG PGNAA, in: 11th SAGA Biennial Technical Meeting and Exhibition, 2009, https://doi.org/10.3997/2214-4609-pdb.241.trofimczyk_paper2ples.
  14. 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 (2018) 51-56, https://doi.org/10.1007/s10967-017-5636-9.
  15. W. Nunes, A. Da Silva, V. Crispim, R. Schirru, Explosives detection using prompt-gamma neutron activation and neural networks, Appl. Radiat. Isot. 56 (2002) 937-943. https://doi.org/10.1016/S0969-8043(02)00059-3
  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. K. Mark, C.J. Sullivan, An automated isotope identification and quantification algorithm for isotope mixtures in low-resolution gamma-ray spectra, Radiat. Phys. Chem. 155 (2019) 281-286. https://doi.org/10.1016/j.radphyschem.2018.06.017
  18. F. Zhang, L. Tian, J. Liu, et al., Numerical simulation on scintillator detector response for determining element content in PGNAA system, J. Radioanal. Nucl. Chem. 311 (2017) 1309-1314, https://doi.org/10.1007/s10967-016-5034-8.
  19. W. Metwally, R. Gardner, A. Sood, Gaussian broadening of MCNP pulse height spectra, Trans. Am. Nucl. Soc. 91 (2004) 789-790.
  20. T. Ding, T. Tan, J. Wang, D. Ma, J. Lu, R. Zhang, B. Wu, Ore genesis of the Huangshaping skarn W-Mo-Pb-Zn deposit, southern Hunan Province, China: insights from in situ LA-MC-ICP-MS sulphur isotopic compositions, Geol. Mag. 159 (2022) 981-995, https://doi.org/10.1017/s0016756822000188.
  21. T. Ding, D. Ma, J. Lu, R. Zhang, S.S. Zhang, Pb, and Sr isotope geochemistry and genesis of Pb-Zn mineralization in the Huangshaping polymetallic ore deposit of southern Hunan Province, China, Ore Geol. Rev. 77 (2016) 117-132, https://doi.org/10.1016/j.oregeorev.2016.02.010.
  22. D. Ramyachitra, P. Manikandan, Imbalanced dataset classification and solutions: a review, Int. J. Comput. Bus. Res. (IJCBR) 5 (2014) 1-29.
  23. S. Qi, W. Zhao, Y. Chen, et al., Comparison of machine learning approaches for radioisotope identification using NaI (TI) gamma-ray spectrum, Appl. Radiat. Isot. 186 (2022), 110212, https://doi.org/10.1016/j.apradiso.2022.110212.
  24. C.W. Hsu, C.C. Chang, C.J. Lin, A Practical Guide to Support Vector Classification, 2003, pp. 1396-1440.
  25. N.S. Altman, An introduction to kernel and nearest-neighbor nonparametric regression, Am. Statistician 46 (1992) 175-185, https://doi.org/10.1080/00031305.1992.10475879.
  26. M. Scutari, Naive bayes classifiers, in: ICC 2022 - IEEE International Conference on Communications, 2022.
  27. L. Ali, S.U. Khan, N.A. Golilarz, et al., A feature-driven decision support system for heart failure prediction based on statistical model and Gaussian naive bayes, Comput. Math. Methods Med. (2019), https://doi.org/10.1155/2019/6314328.
  28. L. Breiman, Random forests, Mach. Learn. 45 (2001) 5-32. https://doi.org/10.1023/A:1010933404324
  29. A. Tharwat, Classification assessment methods, Appl. Comput. Info. 17 (2021) 168-192, https://doi.org/10.1016/j.aci.2018.08.003.
  30. D. Chicco, G. Jurman, The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation, BMC Genom. 21 (2020) 6, https://doi.org/10.1186/s12864-019-6413-7.
  31. P. Refaeilzadeh, L. Tang, H. Liu, Cross-Validation, Encyclopedia of Database Systems, 2016, pp. 1-7.