Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

AI Enabled Neutron Flux Measurement and Virtual Calibration in Boiling Water Reactors

Anirudh Tunga, Jordan Heim, Michael Mueterthies, Thomas Gruenwald, Jonathan Nistor

Abstract

Accurately capturing the three dimensional power distribution within a reactor core is vital for ensuring the safe and economical operation of the reactor, compliance with Technical Specifications, and fuel cycle planning (safety, control, and performance evaluation). Offline (that is, during cycle planning and core design), a three dimensional neutronics simulator is used to estimate the reactor's power, moderator, void, and flow distributions, from which margin to thermal limits and fuel exposures can be approximated. Online, this is accomplished with a system of local power range monitors (LPRMs) designed to capture enough neutron flux information to infer the full nodal power distribution. Certain problems with this process, ranging from measurement and calibration to the power adaption process, pose challenges to operators and limit the ability to design reload cores economically (e.g., engineering in insufficient margin or more margin than required). Artificial intelligence (AI) and machine learning (ML) are being used to solve the problems to reduce maintenance costs, improve the accuracy of online local power measurements, and decrease the bias between offline and online power distributions, thereby leading to a greater ability to design safe and economical reload cores. We present ML models trained from two deep neural network (DNN) architectures, SurrogateNet and LPRMNet, that demonstrate a testing error of 1 percent and 3 percent, respectively. Applications of these models can include virtual sensing capability for bypassed or malfunctioning LPRMs, on demand virtual calibration of detectors between successive calibrations, highly accurate nuclear end of life determinations for LPRMs, and reduced bias between measured and predicted power distributions within the core.

AI Enabled Neutron Flux Measurement and Virtual Calibration in Boiling Water Reactors

Abstract

Accurately capturing the three dimensional power distribution within a reactor core is vital for ensuring the safe and economical operation of the reactor, compliance with Technical Specifications, and fuel cycle planning (safety, control, and performance evaluation). Offline (that is, during cycle planning and core design), a three dimensional neutronics simulator is used to estimate the reactor's power, moderator, void, and flow distributions, from which margin to thermal limits and fuel exposures can be approximated. Online, this is accomplished with a system of local power range monitors (LPRMs) designed to capture enough neutron flux information to infer the full nodal power distribution. Certain problems with this process, ranging from measurement and calibration to the power adaption process, pose challenges to operators and limit the ability to design reload cores economically (e.g., engineering in insufficient margin or more margin than required). Artificial intelligence (AI) and machine learning (ML) are being used to solve the problems to reduce maintenance costs, improve the accuracy of online local power measurements, and decrease the bias between offline and online power distributions, thereby leading to a greater ability to design safe and economical reload cores. We present ML models trained from two deep neural network (DNN) architectures, SurrogateNet and LPRMNet, that demonstrate a testing error of 1 percent and 3 percent, respectively. Applications of these models can include virtual sensing capability for bypassed or malfunctioning LPRMs, on demand virtual calibration of detectors between successive calibrations, highly accurate nuclear end of life determinations for LPRMs, and reduced bias between measured and predicted power distributions within the core.
Paper Structure (18 sections, 2 equations, 5 figures, 1 table)

This paper contains 18 sections, 2 equations, 5 figures, 1 table.

Table of Contents

  1. INTRODUCTION
  2. BACKGROUND
  3. LPRM
  4. DEEP LEARNING
  5. Fully connected networks
  6. Convolutional neural networks
  7. Attention
  8. DATA
  9. PROPOSED ARCHITECTURE
  10. SurrogateNet
  11. LPRMNet
  12. IMPLEMENTATION DETAILS
  13. EXPERIMENTS AND RESULTS
  14. DATA SPLITS
  15. SurrogateNet data split
  16. ...and 3 more sections

Figures (5)

  • Figure 1: Distribution of LPRMs. All the LPRMs in sets $\mathcal{A}$ and $\mathcal{B}$ have symmetric partners, a few of them are indicated by the dashed arrows. The LPRMs in the set $\mathcal{C}$ do not have symmetrical partners.
  • Figure 2: SurrogateNet and arrangement of LPRM assembly. The number of neurons in the six fully connected layers has been scaled down for illustration.
  • Figure 3: Overview of the data.
  • Figure 4: Overview of the proposed LPRMNet.
  • Figure 5: Visualization of few results from LPRMNet. The values in blue are the measured LPRM values and the values in red are the model predictions. The $y$-axis represents the LPRM values.