Upsampling Monte Carlo reactor simulation tallies in depleted LWR assemblies fueled with LEU and HALEU using a convolutional neural network
Simulating nuclear reactor cores at the highest achievable spatial and energy resolution is critical in modeling these systems accurately. Increasing the resolution, however, can dramatically increase the memory and central processing unit time required to run simulations. A convolutional neural net...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
AIP Publishing LLC
2024-01-01
|
| Series: | AIP Advances |
| Online Access: | http://dx.doi.org/10.1063/5.0169833 |
| _version_ | 1797332081995415552 |
|---|---|
| author | Jessica Berry Paul Romano Andrew Osborne |
| author_facet | Jessica Berry Paul Romano Andrew Osborne |
| author_sort | Jessica Berry |
| collection | DOAJ |
| description | Simulating nuclear reactor cores at the highest achievable spatial and energy resolution is critical in modeling these systems accurately. Increasing the resolution, however, can dramatically increase the memory and central processing unit time required to run simulations. A convolutional neural network was shown previously to accurately upsample tally results of simulated light water reactor assemblies fueled with fresh, low enriched uranium. Here, we show that a convolutional neural network can be used to upsample tally results in assemblies containing fresh and depleted fuel enriched from 1.6 to 19.9 atom percent. The network was trained using neutron flux tallies from simulations of light water reactor assemblies with a range of fuel and coolant temperatures and a diverse selection of geometries. Accurate predictions of flux tallies are possible even on test assemblies with geometries and burnup levels well outside the range of those present in the training and validation data. The network improves the data density by a factor of 8 over a broad range of light water reactor assemblies while incurring insignificant additional computational cost to a Monte Carlo simulation. |
| first_indexed | 2024-03-08T07:44:30Z |
| format | Article |
| id | doaj.art-f5c34bbcf5294c089fc0306c9d106a08 |
| institution | Directory Open Access Journal |
| issn | 2158-3226 |
| language | English |
| last_indexed | 2024-03-08T07:44:30Z |
| publishDate | 2024-01-01 |
| publisher | AIP Publishing LLC |
| record_format | Article |
| series | AIP Advances |
| spelling | doaj.art-f5c34bbcf5294c089fc0306c9d106a082024-02-02T16:46:05ZengAIP Publishing LLCAIP Advances2158-32262024-01-01141015004015004-1410.1063/5.0169833Upsampling Monte Carlo reactor simulation tallies in depleted LWR assemblies fueled with LEU and HALEU using a convolutional neural networkJessica Berry0Paul Romano1Andrew Osborne2Nuclear Science and Engineering, The Colorado School of Mines, 1012 14th St., Golden, Colorado 80401, USAArgonne National Laboratory, 9700 S Cass Avenue, Lemont, Illinois 60439, USADepartment of Mechanical Engineering, The Colorado School of Mines, 1610, Illinois St., Golden, Colorado 80401, USASimulating nuclear reactor cores at the highest achievable spatial and energy resolution is critical in modeling these systems accurately. Increasing the resolution, however, can dramatically increase the memory and central processing unit time required to run simulations. A convolutional neural network was shown previously to accurately upsample tally results of simulated light water reactor assemblies fueled with fresh, low enriched uranium. Here, we show that a convolutional neural network can be used to upsample tally results in assemblies containing fresh and depleted fuel enriched from 1.6 to 19.9 atom percent. The network was trained using neutron flux tallies from simulations of light water reactor assemblies with a range of fuel and coolant temperatures and a diverse selection of geometries. Accurate predictions of flux tallies are possible even on test assemblies with geometries and burnup levels well outside the range of those present in the training and validation data. The network improves the data density by a factor of 8 over a broad range of light water reactor assemblies while incurring insignificant additional computational cost to a Monte Carlo simulation.http://dx.doi.org/10.1063/5.0169833 |
| spellingShingle | Jessica Berry Paul Romano Andrew Osborne Upsampling Monte Carlo reactor simulation tallies in depleted LWR assemblies fueled with LEU and HALEU using a convolutional neural network AIP Advances |
| title | Upsampling Monte Carlo reactor simulation tallies in depleted LWR assemblies fueled with LEU and HALEU using a convolutional neural network |
| title_full | Upsampling Monte Carlo reactor simulation tallies in depleted LWR assemblies fueled with LEU and HALEU using a convolutional neural network |
| title_fullStr | Upsampling Monte Carlo reactor simulation tallies in depleted LWR assemblies fueled with LEU and HALEU using a convolutional neural network |
| title_full_unstemmed | Upsampling Monte Carlo reactor simulation tallies in depleted LWR assemblies fueled with LEU and HALEU using a convolutional neural network |
| title_short | Upsampling Monte Carlo reactor simulation tallies in depleted LWR assemblies fueled with LEU and HALEU using a convolutional neural network |
| title_sort | upsampling monte carlo reactor simulation tallies in depleted lwr assemblies fueled with leu and haleu using a convolutional neural network |
| url | http://dx.doi.org/10.1063/5.0169833 |
| work_keys_str_mv | AT jessicaberry upsamplingmontecarloreactorsimulationtalliesindepletedlwrassembliesfueledwithleuandhaleuusingaconvolutionalneuralnetwork AT paulromano upsamplingmontecarloreactorsimulationtalliesindepletedlwrassembliesfueledwithleuandhaleuusingaconvolutionalneuralnetwork AT andrewosborne upsamplingmontecarloreactorsimulationtalliesindepletedlwrassembliesfueledwithleuandhaleuusingaconvolutionalneuralnetwork |