Journal of Nuclear Science, Engineering and Technology (JONSAT)
In cooperation with the Iranian Nuclear Society

Using an artificial neural network in the generation of macroscopic cross-sections for the VVER-1000 reactor core calculations

Document Type : Research Paper

Authors

J. Vosoughi
N. Vosoughi
A.K. Salehi

Department of Nuclear Engineering, Faculty of Energy Engineering, Sharif University of Technology, P.O.BOX: 11365-8639, Tehran - Iran

https://doi.org/10.24200/nst.2023.1593
Abstract
When performing reactor core neutron calculations, the main cost lies in cell calculations to generate macroscopic cross-sections of fuel assemblies (FAs). The development and utilization of a cross-section library based on the reactor type is the primary procedure to reduce calculation costs. In some cases, when there is no library available for specific analyses, it becomes necessary to conduct cell calculations. Examples of such cases include investigating FAs vibration neutron noise or coolant asymmetric distribution around FAs due to bowing. In this study, an Artificial Neural Network (ANN) was used instead of high-volume cell calculations to significantly reduce the time required for calculations in the VVER-1000 reactor. For criticality calculations at Beginning of Cycle (BOC), the calculation time was reduced from 42 minutes using 32 computational cores to just 1.3 minutes. Additionally, the results achieved were of acceptable accuracy, with the difference in the critical boric acid value obtained using ANN compared to cell calculation as a reference being less than 1%, and the power difference being less than 5%.

Highlights

  1. Duderstadt J, Hamilton L. Nuclear Reactor Analysis. John Wiley & Sons. 1976.

 

  1. CASMO5 A Fuel Assembly Burn-up Program User’s Manual. Studsvik Scandpower. 2016.

 

  1. SIMULATE-3 Advanced Three-Dimensional Two-Group Reactor Analysis Code User’s Manual. Studsvik Scandpower. 2005.

 

  1. Hébert A. DRAGON5 and DONJON5 the contribution of École Polytechnique de Montréal to the SALOME platform. Annals of Nuclear Energy. 2015.

 

  1. Avramova M. Developments in thermal-hydraulic sub-channel modeling for whole core multi-physics simulations. Nuclear Engineering and Design. 2020.

 

  1. Spent nuclear fuel assay data for isotopic validation. Nuclear Energy Agency. 2011.

 

  1. Li Y, Gao S, Cao L, Shen W. Analysis, PWR few-group constants parameterization. Progress in Nuclear Energy. 2016.

 

  1. Downar T. PARCS v3.0 U.S. NRC Core Neutronics Simulator. University of Michigan. 2009.

 

  1. Chionis D, Dokhane A. Development and verification of a methodology for neutron noise response to fuel assembly vibrations. Annals of Nuclear Energy. 2020.

 

  1. Vosoughi J, Vosoughi N, Salehi AA. Development of a calculation model to simulate the effect of bowing of the VVER-1000 reactor fuel assembly on power distribution. Annals of Nuclear Energy. 2023.

 

  1. Berger J, Mühle A, Haendel K. Empiric Calculation of the Power Increase Caused by Fuel Assembly Bowing in Siemens/KWU-PWR. Nuclear Science and Engineering. 2020.

 

  1. Li Z, Sun J, Wei C, Sui Z, Qian X. A new Cross-section calculation method in HTGR engineering simulator system based on Machine learning methods. Annals of Nuclear Energy. 2020.

 

  1. Dzianisau S, Choe J, Cherezov A, Lee D. Macroscopic Cross-Section Generation for Nodal Code RAST-K Using Artificial Neural. Transactions of the Korean Nuclear Society Virtual Autumn Meetin. 2021.

 

  1. Dzianisau S, Korawit D. Optimization of Training Dataset Size for Predicting Homogenized Macroscopic CrossSections using Deep Neural Network. Transactions of the Korean Nuclear Society Virtual Autumn Meeting. 2021.

 

  1. Szames E, Ammar K, Tomatis D, Martinez J. Few-group cross sections modeling by artificial neural networks. EPJ Web of Conferences. 2021.

 

  1. Haykin S. Neural Network Comprehensive Foundation. Prentice Hall. 2009.

 

  1. Final Safety Analysis Report of BNPP-1. 2014.

 

  1. Marleu G. Dragon Theory Manual. Ecole Polytechnique de Montreal. 2001.

 

  1. COBRA-EN code system for Thermal-Hydraulic Transient Analysis of Light Water Reactor Fuel Assemblies and Core. Oak Ridge National Laboratoty. 2001.

Keywords

Artificial neural network
Macroscopic cross-sections
Neutron calculations
  1. Duderstadt J, Hamilton L. Nuclear Reactor Analysis. John Wiley & Sons. 1976.

 

  1. CASMO5 A Fuel Assembly Burn-up Program User’s Manual. Studsvik Scandpower. 2016.

 

  1. SIMULATE-3 Advanced Three-Dimensional Two-Group Reactor Analysis Code User’s Manual. Studsvik Scandpower. 2005.

 

  1. Hébert A. DRAGON5 and DONJON5 the contribution of École Polytechnique de Montréal to the SALOME platform. Annals of Nuclear Energy. 2015.

 

  1. Avramova M. Developments in thermal-hydraulic sub-channel modeling for whole core multi-physics simulations. Nuclear Engineering and Design. 2020.

 

  1. Spent nuclear fuel assay data for isotopic validation. Nuclear Energy Agency. 2011.

 

  1. Li Y, Gao S, Cao L, Shen W. Analysis, PWR few-group constants parameterization. Progress in Nuclear Energy. 2016.

 

  1. Downar T. PARCS v3.0 U.S. NRC Core Neutronics Simulator. University of Michigan. 2009.

 

  1. Chionis D, Dokhane A. Development and verification of a methodology for neutron noise response to fuel assembly vibrations. Annals of Nuclear Energy. 2020.

 

  1. Vosoughi J, Vosoughi N, Salehi AA. Development of a calculation model to simulate the effect of bowing of the VVER-1000 reactor fuel assembly on power distribution. Annals of Nuclear Energy. 2023.

 

  1. Berger J, Mühle A, Haendel K. Empiric Calculation of the Power Increase Caused by Fuel Assembly Bowing in Siemens/KWU-PWR. Nuclear Science and Engineering. 2020.

 

  1. Li Z, Sun J, Wei C, Sui Z, Qian X. A new Cross-section calculation method in HTGR engineering simulator system based on Machine learning methods. Annals of Nuclear Energy. 2020.

 

  1. Dzianisau S, Choe J, Cherezov A, Lee D. Macroscopic Cross-Section Generation for Nodal Code RAST-K Using Artificial Neural. Transactions of the Korean Nuclear Society Virtual Autumn Meetin. 2021.

 

  1. Dzianisau S, Korawit D. Optimization of Training Dataset Size for Predicting Homogenized Macroscopic CrossSections using Deep Neural Network. Transactions of the Korean Nuclear Society Virtual Autumn Meeting. 2021.

 

  1. Szames E, Ammar K, Tomatis D, Martinez J. Few-group cross sections modeling by artificial neural networks. EPJ Web of Conferences. 2021.

 

  1. Haykin S. Neural Network Comprehensive Foundation. Prentice Hall. 2009.

 

  1. Final Safety Analysis Report of BNPP-1. 2014.

 

  1. Marleu G. Dragon Theory Manual. Ecole Polytechnique de Montreal. 2001.

 

  1. COBRA-EN code system for Thermal-Hydraulic Transient Analysis of Light Water Reactor Fuel Assemblies and Core. Oak Ridge National Laboratoty. 2001.

Home