Skip to main content
SpringerLink
Log in

Back propagation neural network analysis for the detection of explosives based on tagged neutron

  • Published:
Journal of Radioanalytical and Nuclear Chemistry Aims and scope Submit manuscript

Abstract

A system for detecting explosives in walls based on the tagged neutron method was established. An associated particle neutron generator ING-27 developed by the All-Russian Research Institute of Automatics (VNIIA) is used as the neutron source, two yttrium lutetium silicate (LYSO) detectors are used for the γ detector, and a silicon detector is used as the α detector. The α-γ coincidence spectra of 300 g ammonium nitrate and TNT samples placed behind 10 cm concrete wall were measured. A neural network algorithm was applied to analyze the data. Through fine selection of time windows of α-γ coincidence spectra, the counts of full-energy peak of N, C and O elements and their proportions are selected as the input eigenvectors. The neural network is trained by the experimental data obtained by this system. Through training, eight groups of test data consisting of 32 γ-ray spectra were identified, and a 98.7% of correct detection rate was achieved.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

References

  1. Liang Y, Huang Y, Niu X et al (2015) Research status and development of typical explosive detection technology. China Secur 22:80–84

    Google Scholar 

  2. Im HJ, Cho HJ, Song BC et al (2006) Analytical capability of an explosives detection by a prompt γ-ray neutron activation analysis. Nucl Instrum Methods Phys Res 566(2):442–447

    Article  CAS  Google Scholar 

  3. Dazhi J, Liang C (2009) Experimental study on the principle of neutron detection of explosives. Rev Nucl Phys 26(1):41–42

    Google Scholar 

  4. Shiwei J, Yong G, Yulai Z et al (2015) Detection of explosives in packages by tagged neutron method. Nucl Electron Detect Technol 35(07):721–725

    Google Scholar 

  5. Qiang W, Shiwei J, Yulai Z (2018) Detection of explosives in walls by tagged neutron method. Nucl Electron Detect Technol 38(01):1–4

    Google Scholar 

  6. Nunes WV, Da Silva AX, Crispim VR et al (2002) Explosives detection using prompt-gamma neutron activation and neural networks. Appl Radiat Isot 56(6):937–943

    Article  CAS  PubMed  Google Scholar 

  7. Bagdasaryan KE, Batyaev VF, Belichenko SG et al (2015) Parameters of explosives detection through tagged neutron method. Nucl Instrum Methods Phys Res Sect A 784:412–416

    Article  CAS  Google Scholar 

  8. Pesente S, Nebbia G, Lunardon M et al (2004) Detection of hidden explosives by using tagged neutron beams with sub-nanosecond time resolution. Nucl Instrum Methods Phys Res Sect A 531(3):657–667

    Article  CAS  Google Scholar 

  9. Perot B, Carasco C, Bernard S et al (2007) Development of the EURITRACK tagged neutron inspection system. Nucl Instrum Methods Phys Res Sect B Beam Interact Mater Atoms 261((1–2 SPEC. ISS.)):295–298

    Article  CAS  Google Scholar 

  10. Litvak ML, Barmakov YN, Belichenko SG et al (2020) 3-D imaging of subsurface structure in planetary missions. Nucl Instrum Methods Phys Res Sect A 963:163725

    Article  CAS  Google Scholar 

  11. Qian J (2013) γ spectra analysis based on genetic neural network. China Institute of Metrology

  12. Di Y, Xu W, Xu P et al (2006) A recognition method of γ-ray spectra based on BP neural network. Nucl Electron Detect Technol 413(04):397–399

    Google Scholar 

  13. Doostmohammadi V, Sardari D, Nasrabadi AM (2010) Combined application of Monte Carlo method and neural networks to simulate qualitative prompt gamma neutron activation analysis. J Radioanal Nucl Chem 283(2):403–407

    Article  CAS  Google Scholar 

  14. Ferreira FJO, Crispim VR, Silva AX (2010) Detection of drugs and explosives using neutron computerized tomography and artificial intelligence techniques. Appl Radiat Isot 68(6):1012–1017

    Article  CAS  PubMed  Google Scholar 

  15. Carasco C, Pérot B, Sardet A (2019) Measuring hydrogen with fast neutrons: application to organic materials identification in cargo containers. Nucl Instrum Methods Phys Res Sect A Accelerat Spect Detect Assoc Equip 951:163030

    Article  CAS  Google Scholar 

  16. Haidong W, Yuanjing Li, Youquan Y et al (2005) Recognition of explosives by pulsed fast thermal neutron analysis and neural network. Nucl Electron Detect Technol 04:384–387

    Google Scholar 

  17. Li An, Tie He, Haiping G et al (2010) Study on the measurement technology of instantaneous γ spectra by adjoint particle method. Atom Energy Sci Technol 44(S1):15–18

    Google Scholar 

  18. Dashi Xu, Weibin Z (1998) Associated particle imaging method for detecting explosives and drugs. Atom Energy Sci Technol 32(6):482–486

    Google Scholar 

  19. Haiping G, Zheng Pu, Li An et al (2013) Measurement of instantaneous γ spectra of typical samples in explosive detection. Intens Laser Part Beam 25(9):2429–2432

    Article  CAS  Google Scholar 

  20. Tie He, Yuan C, Li An et al (2010) Effect of α particle scattering on time resolution of explosive detection. High Power Laser Part Beam 10:207–210

    Google Scholar 

  21. Mitra S (2011) Identification of UXO using the associated particle neutron time-of-flight technique, final report, BNL Report No. 96489–2011

  22. Wang X, Hua ZY (2013) Research and development of equipment for detecting hidden explosives by particle method. Professional Group of Activation Analysis of China Nuclear Physics Society. Summary of papers of the 13th National Academic Exchange Conference on Activation Analysis Technology. Professional Group of Activation Analysis of China Nuclear Physics Society: China Nuclear Physics Society, 2013: 9

  23. Zhang Z (2011) γ spectra Analysis Based on RBF Neural Network. Liaoning Normal University

  24. Zhijie F, Xueyang Li, Jiangping Z et al (2012) Study on safety evaluation technology of infectious substance packaging. Packag Eng 01:23–27

    Google Scholar 

  25. Lianning Li (2015) Research on diagnostic mechanism and algorithms of severe diseases based on olfactory network transmission. Comput Sci S1:137–142

    Google Scholar 

  26. Agriculture as a whole, Wenbo. Short-term load forecasting based on improved BP neural network algorithm. Guizhou Electric Power Technology, 2015, (3): 4–4

  27. Junguo H et al (2013) Using an improved back propagation neural network to study spatial distribution of sunshine illumination from sensor network data. Ecol Model 266(1):86–96

    Article  Google Scholar 

  28. Han M-C, Jing S-W, Gao Y-D et al (2019) Experiment and MCNP simulation of a portable tagged neutron inspection system for detection of explosives in a concrete wall. Nucl Instrum Methods Phys Res Sect A 929:156–161

    Article  CAS  Google Scholar 

  29. Vniia, Neutron generators for elemental analysis of substances and materials. https://vniia.ru/eng/ng/element.html

Download references

Acknowledgements

This work was supported by the Science and Technology Development Project of Jilin Province of China [20190303101SF] and the Criminal Investigation Project in Key laboratory of Sichuan higher education- Criminal Science and Technology Laboratory (Sichuan Police College) [2018YB04].

Author information

Authors and Affiliations

  1. College of Physics, Northeast Normal University, No. 5268, People Street, Nanguan, Changchun, 130024, Jilin, People’s Republic of China

    Ke Gong, Shu-Jun Xiao & Shi-Wei Jing

  2. China Institute of Atomic Energy, Beijing, 121000, People’s Republic of China

    Shi-Wei Jing & Yu-Lai Zheng

  3. Key Laboratory of Sichuan Higher Education—Criminal Science and Technology Laboratory, Sichuan Police College, Luzhou, Sichuan, People’s Republic of China

    Shi-Wei Jing

Authors
  1. Ke Gong
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Shu-Jun Xiao
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Shi-Wei Jing
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yu-Lai Zheng
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Shi-Wei Jing.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Gong, K., Xiao, SJ., Jing, SW. et al. Back propagation neural network analysis for the detection of explosives based on tagged neutron. J Radioanal Nucl Chem 326, 329–336 (2020). https://doi.org/10.1007/s10967-020-07321-3

Download citation

  • Received:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10967-020-07321-3

Keywords

Search

Navigation