Improved fast neutron detection using CNN-based pulse shape discrimination
3
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
The importance of fast neutron detection for nuclear safeguards purposes has increased due to its potential advantages such as reasonable cost and higher precision for larger sample masses of nuclear materials. Pulseshape discrimination (PSD) is inevitably used to discriminate neutron- and gamma-ray- induced signals from organic scintillators of very high gamma sensitivity. The light output (LO) threshold corresponding to several MeV of recoiled proton energy could be necessary to achieve fine PSD performance. However, this leads to neutron count losses and possible distortion of results obtained by neutron multiplicity counting (NMC)-based nuclear material accountancy (NMA). Moreover, conventional PSD techniques are not effective for counting of neutrons in a high-gamma-ray environment, even under a sufficiently high LO threshold. In the present work, PSD performance (figure-of-merit, FOM) according to LO bands was confirmed using a conventional charge comparison method (CCM) and compared with results obtained by convolution neural network (CNN)-based PSD algorithms. Also, it was attempted, for the first time ever, to reject fake neutron signals from distorted PSD regions where neutron-induced signals are normally detected. The overall results indicated that higher neutron detection efficiency with better accuracy could be achieved via CNN-based PSD algorithms.
Abstract
The importance of fast neutron detection for nuclear safeguards purposes has increased due to its potential advantages such as reasonable cost and higher precision for larger sample masses of nuclear materials. Pulseshape discrimination (PSD) is inevitably used to discriminate neutron- and gamma-ray- induced signals from organic scintillators of very high gamma sensitivity. The light output (LO) threshold corresponding to several MeV of recoiled proton energy could be necessary to achieve fine PSD performance. However, this leads to neutron count losses and possible distortion of results obtained by neutron multiplicity counting (NMC)-based nuclear material accountancy (NMA). Moreover, conventional PSD techniques are not effective for counting of neutrons in a high-gamma-ray environment, even under a sufficiently high LO threshold. In the present work, PSD performance (figure-of-merit, FOM) according to LO bands was confirmed using a conventional charge comparison method (CCM) and compared with results obtained by convolution neural network (CNN)-based PSD algorithms. Also, it was attempted, for the first time ever, to reject fake neutron signals from distorted PSD regions where neutron-induced signals are normally detected. The overall results indicated that higher neutron detection efficiency with better accuracy could be achieved via CNN-based PSD algorithms.
참고문헌 (24)
- F. D. Brooks, "A scintillation counter with neutron and gamma-ray discriminators", Nucl. Instrum. Methods, 4, pp.151~163 (1959)
- J. M. Adams, "A versatile pulse shape discriminator for charged particle separation and its application to fast neutron time-of-flight spectroscopy", Nucl. Instrum. Methods, 156, pp.459~476 (1978)
- B. D’Mellow, "Digital discrimination of neutrons and γ-rays in liquid scintillators using pulse gradient analysis", Nucl. Instrum. Methods Phys. Res. A, 578, pp.191~197 (2007)
- A. Haar, "Zur Theorie der orthogonalen Funktionensysteme", Math. Ann, 69, pp.331~371 (1910)
- K. H. Talukder, "Haar Wavelet-based approach for image compression and quality assessment of compressed image", International Journal of Applied Mathematics, 36, pp.1~9 (2010)
- G.F. Knoll, "Radiation Detection and Measurement" (2002), John Wiley & Sons
- J. M. Verbeke, "Neutron-neutron angular correlations in spontaneous fission of 252Cf and 240Pu", Phys. Rev. C, 97, pp.044601~ (2018)
- E. V. Ryabeva, "Calibration of EJ-276 plastic scintillator for neutron-gamma pulse shape discrimination experiments", Nucl. Instrum. Methods Phys. Res. A, 1010, pp.165495~ (2021)
- S. Yoon, "Energy-dependent characteristics of prompt neutron anisotropic emission by 244Cm and 240Pu according to Monte Carlo simulation", J. Radioanal. Nucl. Chem, 330, pp.481~491 (2021)
- Application Guide to Neutron Multiplicity Counting, "N. Ensslin", Los Alamos National Laboratory, ~, pp.LA-13422-M (1998)
- MPACT Fast Neutron Multiplicity System Prototype Development, "D. L. Chichester", Idaho National Laboratory, ~, pp.INL (2013), EXT-13-30279
- L. Holewa, "Using Neutron Angular Anisotropy Information to Dynamically Determine the Ratio of the (α,. n) Rate to spontaneous fission rate for coincidence counting applications", Nucl. Instrum. Methods Phys. Res. A, 701, pp.249~253 (2012)
- J. M. Mueller, "Using anisotropies in prompt fission neutron coincidences to assess the neutron multiplication of highly multiplying subcritical plutonium assemblies", Nucl. Instrum. Methods Phys. Res. A, 825, pp.87~92 (2016)
- T. H. Shin, "Prompt Fission Neutron Anisotropy in Low-Multiplying Subcritical Plutonium Metal Assemblies", 915, pp.110~115 (2019)
- S. Yoon, "Monte Carlo simulations of correlation between anisotropic emission characteristics of prompt fission neutrons and sample multiplication", Radiat. Phys. Chem, 181, pp.109328~ (2021)
- M. Verbeke, "Fission reaction event yield algorithm FREYA 2.0.2", Comput. Phys. Commun, 222, pp.263~266 (2018)
- Yoon Seonkwang, "Fast neutron-gamma discrimination in organic scintillators via convolution neural network", Journal of the Korean Physical Society, 80(5), pp.427~433 (2022), 한국물리학회[DOI]
- A. Krizhevsky, "ImageNet Classification with deep convolution neural networks", Commun. ACM, 60, pp.84~90 (2017)
- R. Yamashita, "Convolutional neural networks : an overview and application in radiology", Insights into Imaging, 9, pp.611~629 (2018)
- J. Gu, "Recent advances in convolutional neural networks", Pattern Recogn, 77, pp.354~377 (2018)
- I. Goodfellow, "Deep Learning" (2016), MIT Press
- F. Chollet, "Deep Learning with Python" (2017), Manning Publications
- L. Wijayasingha, "Robustness to noise for speech emotion classification using CNNs and attention mechanisms", Smart Health, 19, pp.100165~ (2021)
- H. Liu, "Anti-noise performance of the pulse coupled neural network applied in discrimination of neutron and gamma-ray", Nucl. Sci. Tech, 33 (2022)