Score-based Bayesian network structure learning algorithms for modeling radioisotope levels in nuclear power plant reactors

Radioactive corrosion products released into the primary coolant loop dominate the final shutdown radiation fields of pressurized water reactors. Thus, reducing the concentration of these corrosion products is a paramount duty in the optimization process of the reactor performance. However, the comp...

Full description

Saved in:
Bibliographic Details
Published in:Chemometrics and intelligent laboratory systems 2023-06, Vol.237, p.104811, Article 104811
Main Authors: Ramirez-Hereza, Pablo, Ramos, Daniel, Toledano, Doroteo T., Gonzalez-Rodriguez, Joaquin, Ariza-Velazquez, Alicia, Doncel, Nuria
Format: Article
Language:English
Subjects:
Bayesian networks
Nuclear chemistry
Primary loop chemistry
Probabilistic machine learning
Structure learning
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Radioactive corrosion products released into the primary coolant loop dominate the final shutdown radiation fields of pressurized water reactors. Thus, reducing the concentration of these corrosion products is a paramount duty in the optimization process of the reactor performance. However, the complexity and uncertainty present in this process make it difficult to predict their evolution in a theoretical way. We propose the application of structural learning of Bayesian networks to discover the complex relations between the corrosion products and the most relevant variables in the primary loop, giving rise to probabilistic models that obtain accurate and reliable predictions of the corrosion products. Our analysis of 5 power plants demonstrates that our approach results in simpler and more reliable models. Additionally, we conclude that the learned structures may represent an interpretable tool for power plant technicians since they reveal useful information that can be directly employed to improve the reactor operation. •Radioactive corrosion products govern shutdown radiation fields of a PWR power plant.•BNs with a fixed structure are already in use to predict the corrosion products.•Conditional Independences of variables are found with Structure learning algorithms.•Structure learning algorithms give rise to simpler and more calibrated BNs.•Resulting models are more reliable than Bayesian Networks with a fixed structure.
ISSN:0169-7439
1873-3239
DOI:10.1016/j.chemolab.2023.104811