A real-time neutron-gamma discriminator based on the support vector machine method for the time-of-fiight neutron spectrometer

Wei ZHANG (张伟); Tongyu WU (吴彤宇); Bowen ZHENG (郑博文); Shiping LI (李世平); Yipo ZHANG (张轶泼); Zejie YIN (阴泽杰)

doi:10.1088/2058-6272/aaaaa9

Plasma Science and Technology > 2018 > 20(4): 45601-045601. > DOI: 10.1088/2058-6272/aaaaa9

Wei ZHANG (张伟), Tongyu WU (吴彤宇), Bowen ZHENG (郑博文), Shiping LI (李世平), Yipo ZHANG (张轶泼), Zejie YIN (阴泽杰). A real-time neutron-gamma discriminator based on the support vector machine method for the time-of-fiight neutron spectrometer[J]. Plasma Science and Technology, 2018, 20(4): 45601-045601. DOI: 10.1088/2058-6272/aaaaa9

Citation:

PDF (1993 KB)

A real-time neutron-gamma discriminator based on the support vector machine method for the time-of-fiight neutron spectrometer

1 State Key Laboratory of Particle Detection and Electronics, University of Science and Technology of China, Hefei 230026, People’s Republic of China 2 Department of Modern Physics, University of Science and Technology of China, Hefei 230026, People’s Republic of China 3 Southwestern Institute of Physics, Chengdu 610041, People’s Republic of China

Funds: This work was partially supported by the National Science and Technology Major Project of Ministry of Science and Technology of China (Grant Nos. 2014GB109003 and 2015GB111002) and National Natural Science Foundation of China (Grant Nos. 11375195, 11575184, 11375004 and 11775068).

More Information

Received Date: August 30, 2017

Graphical Abstract

Abstract

Abstract

A new neutron-gamma discriminator based on the support vector machine (SVM) method is proposed to improve the performance of the time-of-fiight neutron spectrometer. The neutron detector is an EJ-299-33 plastic scintillator with pulse-shape discrimination (PSD) property. The SVM algorithm is implemented in field programmable gate array (FPGA) to carry out the real-time sifting of neutrons in neutron-gamma mixed radiation fields. This study compares the ability of the pulse gradient analysis method and the SVM method. The results show that this SVM discriminator can provide a better discrimination accuracy of 99.1%. The accuracy and performance of the SVM discriminator based on FPGA have been evaluated in the experiments. It can get a figure of merit of 1.30.
- plasma diagnosis,
- support vector machine,
- pulse-shape discrimination,
- TOF spectrometer

FullText(HTML)

References (26)

References

[1]	Jarvis O N 1994 Plasma Phys. Control. Fusion 36 209
[2]	Chen Y X and Wu Y C 2003 Plasma Sci. Technol. 5 1749
[3]	Xiong Y et al 2004 Plasma Sci. Technol. 6 2346
[4]	Yuan G L et al 2014 Plasma Sci. Technol. 16 168
[5]	Ericsson G et al 2001 Rev. Sci. Instrum. 72 759
[6]	Zhang X et al 2012 Plasma Sci. Technol. 14 675
[7]	Winyard R A and McBeth G W 1972 Nucl. Instrum. Methods 98 525
[8]	Lee J H and Lee C S 1998 Nucl. Instrum. Methods Phys. Res. A 402 147
[9]	Iwanowska-Hanke J et al 2014 J. Instrum. 9 P06014
[10]	Pozzi S A, Bourne M M and Clarke S D 2013 Nucl. Instrum. Methods Phys. Res. A 723 19
[11]	Takaku D, Oishi T and Baba M 2011 Prog. Nucl. Sci. Technol. 1 210
[12]	Zhang W et al 2017 Plasma Sci. Technol. 19 075603
[13]	Ding B G et al 2015 Plasma Sci. Technol. 17 797
[14]	Wu T Y, Zhang W and Yin Z J 2017 Rev. Sci. Instrum. 88 093501
[15]	Joyce M J et al 2010 IEEE Trans. Nucl. Sci. 57 2625
[16]	Aspinall M D et al 2007 Nucl. Instrum. Methods Phys. Res. A 578 261
[17]	Youse? S, Lucchese L and Aspinall M D 2009 Nucl. Instrum. Methods Phys. Res. A 598 551
[18]	Tambouratzis T, Chernikova D and Pzsit I 2013 J. Artif. Intell. Soft Comput. Res. 3 77
[19]	Vapnik V N 2006 Estimation of Dependences Based on Empirical Data (New York: Springer)(https://doi.org/ 10.1007/0-387-34239-7)
[20]	Cortes C and Vapnik V 1995 Mach. Learn. 20 273
[21]	Burges C J C 1998 Data Min. Knowl. Discovery 2 121
[22]	D’Mellow B et al 2007 Nucl. Instrum. Methods Phys. Res. A 578 191
[23]	Chang C C and Lin C J 2011 ACM Trans. Intell. Syst. Technol. 2 27
[24]	Ouyang X P et al 2005 High Energy Phys. Nucl. Phys. 29 399
[25]	Zaitseva N et al 2012 Nucl. Instrum. Methods Phys. Res. A 668 88
[26]	Liu G F et al 2010 IEEE Trans. Nucl. Sci. 57 1682