Distinctive physical insights driven from machine learning modelling of nuclear power plant severe accident scenario propagation

Aug 5, 2026

Upload by Jiven

Severe accident scenario propagation in nuclear power plants can evolve as initiating events develop into multiple accident sub-scenarios, making time-updated scenario identification valuable for operators. The study demonstrates decision-tree machine learning applied to pressure vessel maximum external surface temperature at specific times, aiming to extract distinctive physical insights across four major, extensively studied accident scenario types. Results show reliable statistical confidence in classifying and distinguishing these scenarios, supporting improved mitigation understanding and analysis of severe accident progression.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages11

Reading Time28 min

AccessFree to download

Introduction

Severe accident scenario propagation and motivation

Machine learning in nuclear reactor safety

Method

Decision tree modelling based on temperature evolution

Related work

Fault detection, quantification, and prediction methods

Results and implications

Distinctive physical insights from scenario classification

PR IFYS GOL BANGOR / BANGOR Distinctive physical insights driven from machine learning modelling of nuclear power plant severe accident scenario propagation Hossny, Karim; Villanueva, Walter; Wang, Hongdi Scientific Reports DOI: 10.1038/s41598-023-28205-y Published: 17/01/2023 Publisher's PDF, also known as Version of record Cyswllt i'r cyhoeddiad / Link to publication Dyfyniad o'r fersiwn a gyhoeddwyd / Citation for published version (APA): Hossny, K. , Villanueva, W. , & Wang, H. (2023) . Distinctive physical insights driven from machine learning modelling of nuclear power plant severe accident scenario propagation. Scientific Reports, 13(1),[930] . [https://doi.org/10.1038/s41598-023-28205-y](https://doi.org/10.1038/s41598-023-28205-y) Hawliau Cyffredinol / General rights Copyright and moral rights for the publications made accessible in the public portal are retained by the authors and/or other copyright owners and it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights. • Users may download and print one copy of any publication from the public portal for the purpose of private study or research. • You may not further distribute the material or use it for any profit-making activity or commercial gain • You may freely distribute the URL identifying the publication in the public portal ? Take down policy If you believe that this document breaches copyright please contact us providing details, and we will remove access to the work immediately and investigate your claim. [www. nature.com/scientificreports](www. nature.com/scientificreports) OPEN Distinctive physical insights driven from machine learning modelling of nuclear power plant severe accident scenario propagation K. Hossny1*, W. Villanueva 1,2 & H. D. Wang1 The severe accident scenario propagation studies of nuclear power plants (NPPs) have been oneof the most critical factors in deploying nuclear power for decades. During an NPP accident, the accident scenario can change during its propagation from the initiating event to a series of accident sub-scenarios. Hence, having time-wise updated information about the current type of accident subscenario can help plant operators mitigate the accident propagation and underlying consequences. In this work, we demonstrate the capability of machine learning (Decision Tree) to help researchers and design engineers in finding distinctive physical insights between four different types of accident scenarios based on the pressure vessel’s maximum external surface temperature at a particular time. Although the four accidents we included in this study are considered some of the most extensively studied NPPs accident scenarios for decades, our findings shows that decision tree classification could define remarkable distinct differences between them with reliable statistical confidence. Nuclear reactor safety (NRS) is related to studying possible accident scenarios that can occur in a nuclear powerplant (NPP). The purpose of these studies and research is to ensure the safe operation of the NPP. The importance of this field comes from the fact that a single major accident can cause catastrophic damage to the environment, not to mention the risk of losses in personnel. Severe accident scenario propagation has been studied extensively since the dawn of nuclear power generation1–5. It has been studied from different points of view, including but not limited to; accidents initiating events and probabilities, instrumentation faults, initiating events propagation, neutronic, and thermal–hydraulic and materials behaviour during different accident scenarios. However, due to the sensitivity and complexity of the subject matter, most of the studies were performed computationally without the use of machine learning (ML) . Thanks to the massive advancement in computational power since the mid-2000s, ML applications in various fields

FAQs

Why is time-wise updated information important during severe accident scenario propagation?

Because the accident scenario can change during propagation, identifying the current sub-scenario type helps operators mitigate the accident progression and its consequences.

What data feature does the decision tree model use in this study?

It uses the pressure vessel’s maximum external surface temperature measured at particular times.

How does the study assess whether scenarios can be distinguished reliably?

It evaluates decision-tree classification performance and reports that the differences among four scenario types are defined with reliable statistical confidence.

Aug 5, 2026

Upload by Jiven