Artificial Neural Network and Dynamic Probabilistic Risk Assessment for passive safety systems

This research emphasizes the application of Artificial Neural Networks (ANNs) and Dynamic Probabilistic Risk Assessment (DPRA) as advanced methodologies for the safety assessment of passive safety systems, particularly in mitigating Loss of Coolant Accidents (LOCAs). While using the BWRX-300 SMR, the study highlights the broader applicability of these techniques to enhance traditional Probabilistic Safety Assessment (PSA). ANNs were employed to predict failure probabilities of critical components, enabling accurate modeling of nonlinear interactions and complex failure scenarios that traditional methods might overlook. DPRA, implemented using the EMRALD tool, provided dynamic, time-dependent analysis of system interactions and accident progression, offering a realistic and detailed evaluation of evolving risk scenarios. By integrating these approaches, the research not only identifies vulnerabilities but also provides actionable insights to improve the effectiveness of passive safety systems. The findings underscore the potential of ANNs and DPRA to revolutionize safety assessments in nuclear energy systems, paving the way for more resilient designs.

Name thesis:degree_name

Master of Applied Science (MASc)

Discipline thesis:degree_discipline

Nuclear Engineering

Grantor

University of Ontario Institute of Technology

Year dc:date.issued

2024

Author dc:creator

• Basak, Saikat

Advisor dc:contributor.advisor

• Lu, Lixuan

Language dc:language.iso

en

Handle dc:identifier.uri

https://hdl.handle.net/10155/2037

OAI identifier oai:identifier

oai:ontariotechu.scholaris.ca:10155/2037