Advertisement

Development of a data-driven classification algorithm for fresh nuclear fuel forensics

  • Gayeon Ha
  • Gyunyoung HeoEmail author
  • Hana Seo
  • Yujeong Choi
Article
  • 15 Downloads

Abstract

According to the Incident and Trafficking Database of the International Atomic Energy Agency, incidents involving illegal transactions or malicious acts with nuclear and other radioactive materials have been reported since 1993. Nuclear forensics is a series of processes that analyze the materials found in these incidents and identify their sources. In this study, we aimed to develop a classification algorithm that identifies the sources of unidentified fresh nuclear fuels, particularly for pellet-type fresh fuels. To do this, a variety of methods has been used to investigate signatures that can serve as a basis for identification. Based on this, we have analyzed the distribution characteristics of signature data and propose a fresh nuclear fuel identification algorithm using data-driven classification methods, such as statistical control charts, principal component analysis, and a one-class support vector machine. The data-driven approaches can be applied to develop empirical models for complex or unknown physical systems and their accuracy can be improved as the sizes of the signature datasets increase.

Keywords

Nuclear forensics Fresh nuclear fuel Physicochemical signatures Data-driven classification 

Notes

Acknowledgements

This work was supported by the Nuclear Safety Research Program through the Korea Foundation of Nuclear Safety (KoFONS), granted financial resource from the Nuclear Safety and Security Commission (NSSC), Republic of Korea.

References

  1. 1.
    IAEA (2017) Incidents of nuclear and other radioactive material out of regulatory control. 2017 Fact Sheet. Incident and Trafficking Database (ITDB)Google Scholar
  2. 2.
    Keegan E et al (2016) Nuclear forensics: Scientific analysis supporting law enforcement and nuclear security investigations. Anal Chem 88(3):1496–1505CrossRefGoogle Scholar
  3. 3.
    Mayer K et al (2007) Nuclear forensic science—from cradle to maturity. J Alloys Compd 444:50–56CrossRefGoogle Scholar
  4. 4.
    Kristo MJ et al (2016) Nuclear forensic science: Analysis of nuclear material out of regulatory control. Annu Rev Earth Planet Sci 44:555–579CrossRefGoogle Scholar
  5. 5.
    Hutcheon I et al (2013) Nonproliferation nuclear forensics. Mineral Assoc Can 43:377–394Google Scholar
  6. 6.
    Han S et al (2014) Overview of the nuclear forensics process and characterization for radioactive materials. Korean J Sci Crim Investig 8(2):73–84Google Scholar
  7. 7.
    Mayer K et al (2006) Tracing the origin of diverted or stolen nuclear material through nuclear forensic investigations. Verifying Treaty Compliance. Springer, Berlin, pp 389–408Google Scholar
  8. 8.
    IAEA (2015) Nuclear Forensics in Support of Investigations, IAEA Nuclear Security Series No. 2-G (Rev. 1), IAEA, ViennaGoogle Scholar
  9. 9.
    KINAC (2016) Development of data-mining methodology for nuclear spent fuel forensic, KINAC/CR-010/2016Google Scholar
  10. 10.
    Lee S et al (2016) Classification methodologies for nuclear spent fuel forensic. In: International conference Pacific basin nuclear conference, Springer, Singapore, pp 711–721Google Scholar
  11. 11.
    Lee S et al (2017) Development of a data-mining methodology for spent nuclear fuel forensics. J Radioanal Nucl Chem 312:495–505CrossRefGoogle Scholar
  12. 12.
    Jin K et al (2017) Development of nuclear forensic models using kernel regression. Prog Nucl Energy 94:55–63CrossRefGoogle Scholar
  13. 13.
    KINAC (2017) Feasibility study on fresh nuclear fuel characteristics for the nuclear forensic signature selection, NSTAR-17PS52-06Google Scholar
  14. 14.
    KINAC (2018) Development of comparative analysis algorithm using nuclear fuel characteristics, KINAC/CR-008/2018Google Scholar
  15. 15.
    Ha G et al (2018) Development of domestic fresh fuel identification algorithm through comparative analysis of nuclear fuel signatures. Transactions of the Korean Nuclear Society Spring Meeting, Jeju, KoreaGoogle Scholar
  16. 16.
    Ha G et al (2019) Development of data-driven classification methods for nuclear fuel forensic. In: 11th nuclear plant instrumentation, control and human–machine interface technologies (NPIC&HMIT), Orlando, FLGoogle Scholar
  17. 17.
    ITWG (2016) ITWG guideline on characteristic parameters of uranium dioxide fuel pellets. ITWG-INFL:-UOFP-v1_2016_09Google Scholar
  18. 18.
    IAEA (2017) Identification of high confidence nuclear forensics signatures. TECDOC-1820Google Scholar
  19. 19.
    Mayer K et al (2005) Nuclear forensics—a methodology providing clues on the origin of illicitly trafficked nuclear materials. R Soc Chem 130(4):433–441Google Scholar
  20. 20.
    Palheiros F et al (2009) Comparative study of the different industrial manufacturing routes for UO2 pellet specification through the wet process. In: International Nuclear Atlantic Conference, Rio de JaneiroGoogle Scholar
  21. 21.
    Rhee YW et al (2010) Fabrication of sintered annular fuel pellet for HANARO irradiation test. J Nucl Sci Technol 47(4):345–350CrossRefGoogle Scholar
  22. 22.
    Ohai D (2003) Large grain size UO2 sintered pellets obtaining used for burn up extension. In: Transactions of the 17th international conference on structural mechanics in reactor technology, PragueGoogle Scholar
  23. 23.
    KINAC (2017) A study on domestic and foreign nuclear fuel manufacture process-dependent physicochemical nuclear materials identification methodology, KINAC/CR-008/2017Google Scholar
  24. 24.
    Pajo L (2001) UO2 Fuel pellet impurities, pellet surface roughness and n(18O)/n(16O) ratios, applied to nuclear forensic science. Thesis, University of HelsinkiGoogle Scholar
  25. 25.
    Reading DG et al (2016) Applying multivariate statistics to discriminate uranium ore concentrate geolocations using (radio) chemical data in support of nuclear forensic investigations. J Environ Radioact 162:172–181CrossRefGoogle Scholar
  26. 26.
    Lin M et al (2015) Tracing origins of uranium ore concentrates (UOCs) by multidimensional statistical analysis of rare-earth impurities. J Anal At Spectrom 30(2):396–402CrossRefGoogle Scholar
  27. 27.
    Varga Z et al (2017) Identification of uranium signatures relevant for nuclear safeguards and forensics. J Radioanal Nucl Chem 312(3):639–654CrossRefGoogle Scholar
  28. 28.
    Chorokov N (2001) Identification of unknown nuclear fuel by impurities and physical parameters. J Radioanal Nucl Chem 250(1):79–84CrossRefGoogle Scholar
  29. 29.
    Robel M et al (2009) Nuclear forensic inferences using iterative multidimensional statistics (No. LLNL-CONF-414001)Google Scholar
  30. 30.
    Shewhart WA, Deming WE (1986) Statistical method from the viewpoint of quality control. Courier Corporation, ChelmsfordGoogle Scholar
  31. 31.
    Smith G (1998) Statistical process control and quality improvement, vol 576. Prentice Hall, ColumbusGoogle Scholar
  32. 32.
    Caulcutt R (1996) Statistical process control (SPC). Assem Autom 16(4):10–14CrossRefGoogle Scholar
  33. 33.
    Fodor IK (2002) A survey of dimension reduction techniques. Neoplasia 9:1–18Google Scholar
  34. 34.
    Abdi H, Williams LJ (2010) Principal component analysis. Wiley Interdiscip Rev Comput Stat 2(4):433–459CrossRefGoogle Scholar
  35. 35.
    Jolliffe IT (2011) Principal component analysis. International encyclopedia of statistical science. Springer, Berlin, pp 1094–1096CrossRefGoogle Scholar
  36. 36.
    Shlens J (2014) A tutorial on principal component analysis. arXiv preprint arXiv:1404.1100
  37. 37.
    Manevitz LM, Yousef M (2001) One-class SVMs for document classification. J Mach Learn Res 2(1):139–154Google Scholar
  38. 38.
    Han J et al (2011) Data mining: concepts and techniques. Elsevier, AmsterdamGoogle Scholar
  39. 39.
    Vapnik V (2013) The nature of statistical learning theory. Springer, New YorkGoogle Scholar
  40. 40.
    Burges CJ (1998) A tutorial on support vector machines for pattern recognition. Data Min Knowl Disc 2(2):121–167CrossRefGoogle Scholar
  41. 41.
    Hsu CW et al (2003) A practical guide to support vector classification. http://www.csie.ntu.edu.tw/~cjlin

Copyright information

© Akadémiai Kiadó, Budapest, Hungary 2019

Authors and Affiliations

  1. 1.Kyung Hee UniversityYongin-siRepublic of Korea
  2. 2.Korea Institute of Nuclear Nonproliferation and ControlDaejeon-siRepublic of Korea

Personalised recommendations