Development of Neural Network Model With Explainable AI for Measuring Uranium Enrichment
- 28 September 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Nuclear Science
- Vol. 68 (11), 2670-2681
- https://doi.org/10.1109/tns.2021.3116090
Abstract
In this work, we have developed a neural network (NN) model that can analyze enrichment from depleted (0.2%) to low enriched uranium (4.5%) when UO 2 waste with very low radioactivity was contained in a 1-L Marinelli beaker, even when the measurement time is as short as 10 s using a low-resolution detector. The average count rate was about 3800 cps. Measurement of uranium enrichment is necessary for quantitative analysis of uranium radioactivity for disposal of uranium waste. Previously studied uranium enrichment methods (infinite thickness (IT) method, peak ratio (PR) method, and relative-efficiency (RE) method) are difficult to use for field measurement due to many limitations of the algorithms. Among existing methods, the RE method is accurate but requires a long measurement time; there is also a limitation in which a high-resolution detector is essential. In this work, we proposed a model to predict uranium enrichment using a low-resolution detector and an artificial NN model. Furthermore, we validated the results of the NN models using an explainable AI algorithm and principal component analysis (PCA). When the measurement time was less than 60 s, the existing method failed to analyze uranium enrichment, but the proposed model can predict enrichment of uranium within 5% of relative error when 5 g of uranium powder was mixed with various waste (ash, soil, and concrete).Keywords
Funding Information
- KEPCO Nuclear Fuel Company Ltd
This publication has 29 references indexed in Scilit:
- Application of neural network method to detect type of uranium contamination by estimation of activity ratio in environmental alpha spectraJournal of Environmental Radioactivity, 2016
- On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance PropagationPLOS ONE, 2015
- Study Partners Recommendation for xMOOCs LearnersComputational Intelligence and Neuroscience, 2015
- Efficient mini-batch training for stochastic optimizationPublished by Association for Computing Machinery (ACM) ,2014
- Artificial intelligence methods applied for quantitative analysis of natural radioactive sourcesAnnals of Nuclear Energy, 2012
- Chapter 4 Nonuniform Random Variate GenerationPublished by Elsevier BV ,2006
- Application of neural networks for the analysis of gamma-ray spectra measured with a Ge spectrometerNuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, 2002
- Use of the 1001keV peak of 234mPa daughter of 238U in measurement of uranium concentration by HPGe gamma-ray spectrometryNuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, 1998
- PC/FRAM: a code for the nondestructive measurement of the isotopic composition of actinides for safeguards applicationsApplied Radiation and Isotopes, 1997
- Efficient Backpropagation Learning Using Optimal Learning Rate and MomentumNeural Networks, 1997