Machine learning framework for predicting uranium enrichments from M400 CZT gamma spectra

Bae, Jin Whan; Hu, Jianwei

doi:10.1016/j.nima.2024.169705

Machine learning framework for predicting uranium enrichments from M400 CZT gamma spectra

Journal Article · Thu Aug 08 00:00:00 EDT 2024 · Nuclear Instruments and Methods in Physics Research. Section A, Accelerators, Spectrometers, Detectors and Associated Equipment

DOI:https://doi.org/10.1016/j.nima.2024.169705· OSTI ID:2441108

^[1]; ^[1]

Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)

A machine learning framework was developed for predicting uranium enrichments from M400 CZT gamma spectra. This framework leverages the availability of a large amount of measured M400 gamma spectra and uses a recently updated version of Gamma Detector Response and Analysis Software (GADRAS) for gamma spectrum analysis and generation. It also leverages the existing machine learning modules in Python for gamma spectrum data processing, curation, model training, benchmarking, and optimization of the deep machine learning models. The framework is used to develop a deep learning model to analyze gamma spectra from a set of U₃O₈ samples with enrichments ranging from 0.31 to 93.17% and UF₆ cylinders with enrichments ranging from 0.2 to 4.95%, and the model performance is tested using a set of measured spectra and the respective declared enrichment values. Results show that the model can correctly classify 99.35% of the U₃O₈ sample enrichments, and can predict the samples’ enrichments within an average absolute error of 0.099% (in percentage points of enrichment). For the UF₆ cylinders, the average absolute error was approximately 0.03%, with an accuracy of 98% in classifying discrete enrichment values of UF₆ samples. Finally, the results also show that the model has performed significantly better in terms of predicting enrichments in UF₆ cylinders based on measured gamma spectra than the GEM code, with a standard deviation (of the relative errors) of 2.23% (compared with the 11.51% value for the GEM code) based on results from a set of test data.

Research Organization:: Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)

Sponsoring Organization:: USDOE National Nuclear Security Administration (NNSA)

Grant/Contract Number:: AC05-00OR22725

OSTI ID:: 2441108

Journal Information:: Nuclear Instruments and Methods in Physics Research. Section A, Accelerators, Spectrometers, Detectors and Associated Equipment, Journal Name: Nuclear Instruments and Methods in Physics Research. Section A, Accelerators, Spectrometers, Detectors and Associated Equipment Vol. 1068; ISSN 0168-9002

Publisher:: ElsevierCopyright Statement

Country of Publication:: United States

Language:: English

References (12)

Gamma-ray spectrometry analysis of pebble bed reactor fuel using Monte Carlo simulations Chen, Jianwei; Hawari, Ayman I.; Zhao, Zhongxiang Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 505, Issue 1-2 https://doi.org/10.1016/S0168-9002(03)01105-7	journal	June 2003
A comparative study of machine learning methods for automated identification of radioisotopes using NaI gamma-ray spectra Galib, S. M.; Bhowmik, P. K.; Avachat, A. V. Nuclear Engineering and Technology, Vol. 53, Issue 12 https://doi.org/10.1016/j.net.2021.06.020	journal	December 2021
PWR and BWR spent fuel assembly gamma spectra measurements Vaccaro, S.; Tobin, S. J.; Favalli, A. Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 833 https://doi.org/10.1016/j.nima.2016.07.032	journal	October 2016
A comparison of machine learning methods for automated gamma-ray spectroscopy Kamuda, Mark; Zhao, Jifu; Huff, Kathryn Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 954 https://doi.org/10.1016/j.nima.2018.10.063	journal	February 2020
Isotope identification using deep learning: An explanation Gomez-Fernandez, Mario; Wong, Weng-Keen; Tokuhiro, Akira Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 988 https://doi.org/10.1016/j.nima.2020.164925	journal	February 2021
Machine Learning technique for isotopic determination of radioisotopes using HPGe γ-ray spectra Khatiwada, Ajeeta; Klasky, Marc; Lombardi, Marcie Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 1054 https://doi.org/10.1016/j.nima.2023.168409	journal	September 2023
An automated isotope identification and quantification algorithm for isotope mixtures in low-resolution gamma-ray spectra Kamuda, Mark; Sullivan, Clair J. Radiation Physics and Chemistry, Vol. 155 https://doi.org/10.1016/j.radphyschem.2018.06.017	journal	February 2019
1D convolutional neural networks and applications: A survey Kiranyaz, Serkan; Avci, Onur; Abdeljaber, Osama Mechanical Systems and Signal Processing, Vol. 151 https://doi.org/10.1016/j.ymssp.2020.107398	journal	April 2021
Development of Neural Network Model With Explainable AI for Measuring Uranium Enrichment Ryu, Jichang; Park, Chanjun; Park, Jungsuk IEEE Transactions on Nuclear Science, Vol. 68, Issue 11 https://doi.org/10.1109/TNS.2021.3116090	journal	November 2021
A Continuous In-Line Monitor for UF₆Enrichment Reilly, T. D.; Martin, E. R.; Parker, J. L. Nuclear Technology, Vol. 23, Issue 3 https://doi.org/10.13182/NT74-A15924	journal	September 1974
Neural Network Approaches for Mobile Spectroscopic Gamma-Ray Source Detection Bilton, Kyle J.; Joshi, Tenzing H. Y.; Bandstra, Mark S. Journal of Nuclear Engineering, Vol. 2, Issue 2 https://doi.org/10.3390/jne2020018	journal	May 2021
Convolutional Neural Networks for Challenges in Automated Nuclide Identification Turner, Anthony; Wheldon, Carl; Wheldon, Tzany Sensors, Vol. 21, Issue 15 https://doi.org/10.3390/s21155238	journal	August 2021

Similar Records

Uranium measurements in the field using high-resolution cadmium zinc telluride detectors

Journal Article · Fri Apr 19 20:00:00 EDT 2024 · Nuclear Instruments and Methods in Physics Research. Section A, Accelerators, Spectrometers, Detectors and Associated Equipment · OSTI ID:2514355

Gamma-ray spectrum variations for surface measurements of uranium hexafluoride cylinders

Journal Article · Tue Feb 18 19:00:00 EST 2020 · Nuclear Instruments and Methods in Physics Research. Section A, Accelerators, Spectrometers, Detectors and Associated Equipment · OSTI ID:1616455

Related Subjects

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND TECHNOLOGY
convolutional neural network
enriched uranium
gamma spectroscopy

Machine learning framework for predicting uranium enrichments from M400 CZT gamma spectra

Citation Formats

References (12)

Similar Records

Related Subjects