kth.sePublications KTH
Operational message
There are currently operational disruptions. Troubleshooting is in progress.
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Distinctive physical insights driven from machine learning modelling of nuclear power plant severe accident scenario propagation
KTH, School of Engineering Sciences (SCI), Physics, Nuclear Engineering.
KTH, School of Engineering Sciences (SCI), Physics, Nuclear Power Safety. Nuclear Futures Institute, School of Computer Science and Electronic Engineering, Bangor University, Bangor, LL57 1UT, UK.ORCID iD: 0000-0003-3132-7252
KTH, School of Engineering Sciences (SCI), Physics, Nuclear Power Safety.
2023 (English)In: Scientific Reports, E-ISSN 2045-2322, Vol. 13, no 1, article id 930Article in journal (Refereed) Published
Abstract [en]

The severe accident scenario propagation studies of nuclear power plants (NPPs) have been one of 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 sub-scenario 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.

Place, publisher, year, edition, pages
Springer Nature , 2023. Vol. 13, no 1, article id 930
National Category
Energy Systems
Identifiers
URN: urn:nbn:se:kth:diva-330064DOI: 10.1038/s41598-023-28205-yISI: 001001592100050PubMedID: 36650268Scopus ID: 2-s2.0-85146411271OAI: oai:DiVA.org:kth-330064DiVA, id: diva2:1775268
Note

QC 20230626

Available from: 2023-06-26 Created: 2023-06-26 Last updated: 2025-12-12Bibliographically approved
In thesis
1. Decision Tree Insights Analytics (DTIA): An Explainable AI Framework for Severe Accident Analysis
Open this publication in new window or tab >>Decision Tree Insights Analytics (DTIA): An Explainable AI Framework for Severe Accident Analysis
2025 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

In nuclear reactor safety analysis, we label an accident as severe once a partial core meltdown and material relocation begin. Researchers use simulation tools such as ANSYS and MELCOR to study these events safely, producing vast and complex datasets. In this work, we applied machine learning explainability and interpretability to extract insights from severe accident simulations for the Nordic boiling water reactor (BWR) through five iterative studies. First, we examined the explainability of the decision tree classification algorithm to distinguish between accident types using time-wise pressure vessel external temperature. Second, we generalised the model to create a more statistically robust and generic framework, introducing the open-source Decision Tree Insights Analytics (DTIA) framework (https://github.com/KHossny/DTIA), which combines explainability, interpretability, and statistical robustness. Third, we applied DTIA to high-dimensional MELCOR COR package data for a station blackout combined with a loss-of-coolant accident (SBO + LOCA) in a Nordic BWR, revealing new findings. Fourth, we used DTIA to compare structural variables of the reactor pressure vessel lower head under SBO and SBO + LOCA conditions. Finally, we coupled DTIA with K-Means clustering to address its need for labelled data, uncovering previously overlooked events such as canister melting. We concluded that the patterns identified by machine learning in mapping inputs to outputs can uncover insights that were previously overlooked, particularly in high-dimensional and complex datasets.

Abstract [sv]

Inom analysen av kärnreaktorsäkerhet betecknar vi en olycka som allvarlig när en partiell härdsmälta och materialomplacering inleds. Forskare använder simuleringsverktyg som ANSYS och MELCOR för att studera dessa händelser på ett säkert sätt, vilket genererar stora och komplexa datamängder. I detta arbete tillämpade vi maskininlärningens förklarbarhet och tolkbarhet för att utvinna insikter från simuleringar av allvarliga olyckor för den nordiska kokvattenreaktorn (BWR) genom fem iterativa studier. För det första undersökte vi förklarbarheten hos beslutsträdsklassificeringsalgoritmen för att skilja mellan olyckstyper baserat på tidsberoende yttre temperatur på reaktortanken. För det andra generaliserade vi modellen för att skapa ett mer statistiskt robust och generiskt ramverk och introducerade det öppna ramverket Decision Tree Insights (https://github.com/KHossny/DTIA), som Analytics (DTIA) kombinerar förklarbarhet, tolkbarhet och statistisk robusthet. För det tredje tillämpade vi DTIA på högdimensionella data från MELCOR:s COR-paket för ett totalt strömavbrott kombinerat med ett kylvätskeförlustscenario (SBO + LOCA) i en nordisk BWR, vilket avslöjade nya fynd. För det fjärde använde vi DTIA för att jämföra strukturella variabler i reaktortankens nedre del under SBO- och SBO + LOCAförhållanden. Slutligen kopplade vi DTIA till K-Means-klustring för att hantera behovet av märkta data, vilket avslöjade tidigare förbisedda händelser som smältning av kapseln. Vi drog slutsatsen att de mönster som identifieras av maskininlärning vid koppling mellan indata och utdata kan avslöja insikter som tidigare förbises, särskilt i högdimensionella och komplexa datamängder.

Place, publisher, year, edition, pages
Stockholm: KTH Royal Institute of Technology, 2025. p. 111
Series
TRITA-SCI-FOU ; 2025:78
Keywords
Explainable AI, Decision Tree Insights Analytics (DTIA), Nuclear Severe Accidents Analysis, Decision Tree Classification, Reactor Pressure Vessel Failure., Förklarbar AI, Decision Tree Insights Analytics (DTIA), Analys av allvarliga kärnkraftsolyckor, Beslutsträdsklassificering, Haveri av reaktortryckkärl.
National Category
Other Engineering and Technologies
Research subject
Energy Technology; Physics, Nuclear Engineering
Identifiers
urn:nbn:se:kth:diva-374074 (URN)978-91-8106-509-1 (ISBN)
Public defence
2026-01-16, FB51, Roslagstullsbacken 21, AlbaNova University Centrum, 114 21, Stockholm, Sweden., Stockholm, 10:00 (English)
Opponent
Supervisors
Funder
Swedish Radiation Safety Authority
Note

QC 2025-12-12

Available from: 2025-12-12 Created: 2025-12-12 Last updated: 2025-12-12Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textPubMedScopus

Authority records

Hossny, KarimVillanueva, WalterWang, Hongdi

Search in DiVA

By author/editor
Hossny, KarimVillanueva, WalterWang, Hongdi
By organisation
Nuclear EngineeringNuclear Power Safety
In the same journal
Scientific Reports
Energy Systems

Search outside of DiVA

GoogleGoogle Scholar

doi
pubmed
urn-nbn

Altmetric score

doi
pubmed
urn-nbn
Total: 135 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf