An Artificial Neural Network System for Photon-Based Active Interrogation Applications

Jinia, Abbas J.; Maurer, Tessa E.; Meert, Christopher A.; Hua, Michael Y.; Clarke, S. D.; Kim, Hun-Seok; Wentzloff, David D.; Pozzi, Sara A.

doi:10.1109/access.2021.3108406

Title: An Artificial Neural Network System for Photon-Based Active Interrogation Applications

Journal Article · Fri Aug 27 00:00:00 EDT 2021 · IEEE Access

DOI:https://doi.org/10.1109/access.2021.3108406· OSTI ID:1826368

Jinia, Abbas J. ^[1]; Maurer, Tessa E. ^[1]; Meert, Christopher A. ^[1]; Hua, Michael Y. ^[1]; Clarke, S. D. ^[1]; Kim, Hun-Seok ^[1]; Wentzloff, David D. ^[1]; Pozzi, Sara A. ^[1]

Univ. of Michigan, Ann Arbor, MI (United States)

Active interrogation (AI) is a promising technique to detect shielded special nuclear materials (SNMs). At the University of Michigan, we are developing a photon-based AI system that uses bremsstrahlung radiation from an electron linear accelerator (linac) as an ionizing source and stilbene organic scintillating detectors for neutron detection. Stilbene scintillators are sensitive to fast neutrons and photons and have excellent pulse shape discrimination (PSD) capabilities. The traditional charge integration (CI) method commonly used for PSD analysis eliminates piled-up pulses and relies on a particle discrimination line to separate neutrons and photons. The presence of the intense photon flux during AI creates a significant number of piled-up events in the stilbene scintillator, thereby posing a great challenge to the traditional CI method. Identifying true single neutron pulses becomes challenging due to the presence of a pile-up cloud and overlapping neutron, photon and pile-up clouds in the PSD analysis. To mitigate the effect of pulse pile up and identify true single neutron pulses from stilbene scintillators, an artificial neural network (ANN) system is developed. The developed ANN system identifies single neutron pulses and neutron-photon combinations from piled-up events. The results obtained from a 252Cf measurement in the presence of the intense photon flux show that the developed ANN system outperforms the traditional CI method. Since many piled-up events lie above the particle discrimination line, they get misclassified as neutrons by the traditional CI method resulting in 25% overestimation of the net neutron count rate during the linac pulse. The overall net neutron count rate (single and restored neutrons) during the linac pulse, estimated by the ANN system is 60% of the ground truth. Energy spectroscopy of the ANN attributed single neutron pulses further provides evidence on the detection of prompt fission neutrons from the 252Cf fission source.

View Accepted Manuscript (DOE)

Cite

Export

Save

Research Organization:: Univ. of Michigan, Ann Arbor, MI (United States)

Sponsoring Organization:: USDOE

Grant/Contract Number:: NA0003920

OSTI ID:: 1826368

Journal Information:: IEEE Access, Vol. 9; ISSN 2169-3536

Publisher:: IEEECopyright Statement

Country of Publication:: United States

Language:: English

References (19)

Learning Deep Architectures for AI Bengio, Y. Foundations and Trends® in Machine Learning, Vol. 2, Issue 1 https://doi.org/10.1561/2200000006	journal	January 2009
An artificial neural network based neutron–gamma discrimination and pile-up rejection framework for the BC-501 liquid scintillation detector Ronchi, E.; Söderström, P. -A.; Nyberg, J. Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 610, Issue 2 https://doi.org/10.1016/j.nima.2009.08.064	journal	November 2009
An investigation of the digital discrimination of neutrons and γ rays with organic scintillation detectors using an artificial neural network Liu, G.; Aspinall, M. D.; Ma, X. Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 607, Issue 3 https://doi.org/10.1016/j.nima.2009.06.027	journal	August 2009
Comparison of Artificial Intelligence Algorithms and Traditional Algorithms in Detector Neutron/Gamma Discrimination Ma, Tongda; Song, Haisheng; Lyu, Boyang 2020 International Conference on Artificial Intelligence and Computer Engineering (ICAICE) https://doi.org/10.1109/ICAICE51518.2020.00040	conference	October 2020
NEDA—NEutron Detector Array Valiente-Dobón, J. J.; Jaworski, G.; Goasduff, A. Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 927 https://doi.org/10.1016/j.nima.2019.02.021	journal	May 2019
Artificial neural networks for neutron/γ discrimination in the neutron detectors of NEDA Fabian, X.; Baulieu, G.; Ducroux, L. Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 986 https://doi.org/10.1016/j.nima.2020.164750	journal	January 2021
A comparison of artificial neural network performance: The case of neutron/gamma pulse shape discrimination Tambouratzis, Tatiana; Chernikova, Dina; Pazsit, Imre 2013 IEEE Symposium on Computational Intelligence for Security and Defense Applications (CISDA) https://doi.org/10.1109/CISDA.2013.6595432	conference	April 2013
A method for digital processing of pile-up events in organic scintillators Belli, F.; Esposito, B.; Marocco, D. Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 595, Issue 2 https://doi.org/10.1016/j.nima.2008.06.045	journal	October 2008
Artificial neural network algorithms for pulse shape discrimination and recovery of piled-up pulses in organic scintillators Fu, C.; Di Fulvio, A.; Clarke, S. D. Annals of Nuclear Energy, Vol. 120 https://doi.org/10.1016/j.anucene.2018.05.054	journal	October 2018
X-ray transition energies: new approach to a comprehensive evaluation Deslattes, Richard D.; Kessler, Ernest G.; Indelicato, P. Reviews of Modern Physics, Vol. 75, Issue 1 https://doi.org/10.1103/RevModPhys.75.35	journal	January 2003
Enhancing the performance of a tensioned metastable fluid detector based active interrogation system for the detection of SNM in <1 m3 containers using a D–D neutron interrogation source in moderated/reflected geometries Grimes, T. F.; Hagen, A. R.; Archambault, B. C. Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 884 https://doi.org/10.1016/j.nima.2017.10.085	journal	March 2018
Portable active interrogation system Moss, C. E.; Brener, M. W.; Hollas, C. L. Nuclear Instruments and Methods in Physics Research Section B: Beam Interactions with Materials and Atoms, Vol. 241, Issue 1-4 https://doi.org/10.1016/j.nimb.2005.07.134	journal	December 2005
Identification and Imaging of Special Nuclear Materials and Contraband using Active x-ray Interrogation Van Liew, Seth; Bertozzi, William; D’Olympia, Nathan Physics Procedia, Vol. 90 https://doi.org/10.1016/j.phpro.2017.09.023	journal	January 2017
An algorithm for charge-integration, pulse-shape discrimination and estimation of neutron/photon misclassification in organic scintillators Polack, J. K.; Flaska, M.; Enqvist, A. Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 795 https://doi.org/10.1016/j.nima.2015.05.048	journal	September 2015
Rattling nucleons: New developments in active interrogation of special nuclear material Runkle, Robert C.; Chichester, David L.; Thompson, Scott J. Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 663, Issue 1 https://doi.org/10.1016/j.nima.2011.09.052	journal	January 2012
Learning and development in neural networks: the importance of starting small Elman, Jeffrey L. Cognition, Vol. 48, Issue 1 https://doi.org/10.1016/0010-0277(93)90058-4	journal	July 1993
A scaled conjugate gradient algorithm for fast supervised learning Møller, Martin Fodslette Neural Networks, Vol. 6, Issue 4 https://doi.org/10.1016/S0893-6080(05)80056-5	journal	January 1993
EJ-309 pulse shape discrimination performance with a high gamma-ray-to-neutron ratio and low threshold Kaplan, A. C.; Flaska, M.; Enqvist, A. Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 729 https://doi.org/10.1016/j.nima.2013.07.081	journal	November 2013
ENDF/B-VII.1 Nuclear Data for Science and Technology: Cross Sections, Covariances, Fission Product Yields and Decay Data Chadwick, M. B.; Herman, M.; Obložinský, P. Nuclear Data Sheets, Vol. 112, Issue 12 https://doi.org/10.1016/j.nds.2011.11.002	journal	December 2011

Similar Records

Measurement of Photoneutrons from Depleted Uranium and Comparison Study Using MCNPX-PoliMi

Journal Article · Tue Mar 14 00:00:00 EDT 2023 · Nuclear Science and Engineering · OSTI ID:1826368

Jinia, Abbas J.; Maurer, Tessa E.; Meert, Christopher A.; +4 more

Development of Fast Measurement System of Neutron Emission Profile Using a Digital Signal Processing Technique in JT-60U

Journal Article · Wed Mar 12 00:00:00 EDT 2008 · AIP Conference Proceedings · OSTI ID:1826368

Ishikawa, M; Shinohara, K; Itoga, T; +4 more

Comparison of pulse shape discrimination performance of stilbene and liquid scintillator under high count-rate active interrogation conditions

Journal Article · Mon Sep 17 00:00:00 EDT 2018 · Nuclear Instruments and Methods in Physics Research. Section A, Accelerators, Spectrometers, Detectors and Associated Equipment · OSTI ID:1826368

Langeveld, Willem G.J.; Glenn, Andrew M.; Sheets, Steven A.; +2 more

Related Subjects

42 ENGINEERING
Artificial neural network
high photon flux
linac
pile-up recovery
trans-stilbene

Title: An Artificial Neural Network System for Photon-Based Active Interrogation Applications

Citation Formats

References (19)

Similar Records

Related Subjects