Predicting and forecasting reactivity and flux using long short-term memory models in pebble bed reactors during run-in

2025/11/07 by Kolaja, Ian, Jantzen, Ludovic, Siaraferas, Tatiana +1
Engineering · #Computational Physics (physics.comp-ph) #FOS: Electrical engineering #FOS: Physical sciences #Heat and Mass Transfer in Porous Media #Heat transfer and supercritical fluids #Nuclear reactor physics and engineering #Systems and Control (eess.SY) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.2511.05118

openalex publication_date 2025/11/07 · openalex created_date 2025/11/11 · openalex updated_date 2026/07/28

Abstract

Pebble bed reactor (PBR) operation presents unique advantages and challenges due to the ability to continuously change the fuel mixture and excess reactivity. Each operation parameter affects reactivity on a different timescale. For example, fuel insertion changes may take months to fully propagate, whereas control rod movements have immediate effects. In-core measurements are further limited by the high temperatures, intense neutron flux, and dynamic motion of the fuel bed. In this study, long short-term memory (LSTM) networks are trained to predict reactivity, flux profiles, and power profiles as functions of operating history and synthetic batch-level pebble measurements, such as discharge burnup distributions. The model's performance is evaluated using unseen temporal data, achieving an R² of 0.9914 on the testing set. The capability of the network to forecast reactivity responses to future operational changes is also examined, and its application for optimizing reactor running-in procedures is explored.

Citations

• PCA-Boosted Autoencoders for Nonlinear Dimensionality Reduction in Low Data Regimes
• A Critical Review of Recurrent Neural Networks for Sequence Learning
• Recurrent Neural Network Regularization

Related

• Machine learning-assisted surrogate construction for full-core fuel performance analysis
• Prediction of the evolution of the nuclear reactor core parameters using artificial neural network
• Digital Twin-Centered Hybrid Data-Driven Multi-Stage Deep Learning Framework for Enhanced Nuclear Reactor Power Prediction
• Data-Driven Prediction and Uncertainty Quantification of PWR Crud-Induced Power Shift Using Convolutional Neural Networks
• Toward Developing Machine-Learning-Aided Tools for the Thermomechanical Monitoring of Nuclear Reactor Components