An uncertainty-aware machine learning framework for predicting cable and cabinet damage in switchgear room fire scenarios
Authors:
- Van Tuan HoVHVan Tuan Ho
- Saerin LimSLSaerin Lim
- Seoung Bum KimSKSeoung Bum Kim
- Weon Gyu ShinWSWeon Gyu Shin
Open Access
- 3 August 2026
- journal article
- Published by Elsevier in Nuclear Engineering and Technology
- Vol. 59 (1)
Abstract
No abstract availableFunding Information
- National Research Foundation of Korea
This publication has 15 references indexed in Scilit:
- Inverse uncertainty quantification in nuclear thermal–hydraulics: A Bootstrap–ARIMA approachNuclear Engineering and Design, 2026
- Leveraging explainable AI for reliable prediction of nuclear power plant severe accident progressionReliability Engineering & System Safety, 2025
- Failure dependence and cascading failures: A literature review and research opportunitiesReliability Engineering & System Safety, 2024
- Assuring fire safety in nuclear plants with international standardsNuclear Engineering and Design, 2024
- Identification of primary input parameters affecting evacuation in ventilated main control room through CFAST simulations and application of a machine learning algorithm to replace CFAST modelNuclear Engineering and Technology, 2024
- Experimental study in open atmosphere and confined conditions of fire spread between adjacent electrical cabinets connected by cable traysFire Safety Journal, 2023
- Modelling the heat release rate of PRISME experimental cable fires in a confined, ventilation controlled, environment using FLASH-CAT and FDSFire Safety Journal, 2023
- Real-time forecast of compartment fire and flashover based on deep learningFire Safety Journal, 2022
- Compartment fire predictions using transpose convolutional neural networksFire Safety Journal, 2019
- Machine learning of fire hazard model simulations for use in probabilistic safety assessments at nuclear power plantsReliability Engineering & System Safety, 2019