Discrete-Time Bayesian Networks Applied to Flexible Coping Strategies of Nuclear Power Plant Systems

Sahin, Elvan; Leite, Victor Coppo; Kim, Kyung Mi; Burns, Nick; Duarte, Juliana P.

doi:10.1080/00295639.2022.2151300

Cited by 2 publications

(2 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The research explores how data-driven probabilistic models can be utilized to predict potential risks and failure scenarios in nuclear reactors. The results show that integrating these AI-driven models with conventional safety systems improves overall safety performance (Guo & Wu, 2022) (Sahin et al, 2023) (Capra et al, 2007).…”

Section: Introductionmentioning

confidence: 95%

AI-Driven approach for enhancing nuclear reactor safety predictive anomaly detection and risk assessment

Russell,

Linzi

2023

Vertex

View full text Add to dashboard Cite

Nuclear power plays a vital role in meeting global energy demands, but ensuring the safety of nuclear reactors remains a paramount challenge. In recent years, the emergence of artificial intelligence (AI) technologies has opened new avenues to significantly enhance nuclear reactor safety through predictive anomaly detection and risk assessment. This research proposes an innovative AI-driven approach that integrates machine learning techniques and data analytics to monitor, detect, and assess potential anomalies in nuclear reactors. The research begins with a comprehensive literature review on nuclear reactor safety and the application of AI in various industrial domains, emphasizing predictive maintenance and anomaly detection. It highlights the need for an AI-driven approach to enhance nuclear reactor safety proactively. In conclusion, this research establishes the transformative potential of AI in enhancing nuclear reactor safety. The proposed AI-driven approach empowers operators with powerful tools to ensure the safe and efficient operation of nuclear power plants. As AI technologies continue to advance, the research opens doors for further exploration and development, paving the way for a more sustainable and secure future in nuclear energy production.

show abstract

Section: Introductionmentioning

confidence: 95%

AI-Driven approach for enhancing nuclear reactor safety predictive anomaly detection and risk assessment

Russell,

Linzi

2023

Vertex

View full text Add to dashboard Cite

show abstract

“…Some discrete time reliability models for Markov multi-state systems are presented in literatures [35][36][37][38]. Furthermore, the reliability analysis of discrete time multi-state systems for Semi-Markov models have been investigated in [39][40][41]. However, all the reported works for power grid system reliability mainly focus on the issues of steady/dynamic state reliability assessment for continuous time multi-state systems.…”

Section: Introductionmentioning

confidence: 99%

Reliability analysis of discrete-time multi-state star configuration power grid systems with performance sharing

Su,

Zhang,

Shi

2024

Preprint

View full text Add to dashboard Cite

This paper studies an assessment method for dynamic reliability of a discrete time multi-state star configuration power grid system with performance sharing. The proposed star configuration power grid system consists of n power generation subsystems fixed in star-terminal and one central collection and redistribution subsystem. All-star-terminal power generation subsystems are connected to the central subsystem in a point-to-point manner through their intermediate transmission links. It is assumed that the electric power of each generator and the demand of each star-terminal subsystem are random variables. The star-terminal subsystems with sufficient electric power can first transmit the surplus electric power to the central subsystem, and then the collected electric power in central subsystem is further redistributed to the star-terminal subsystems which are experiencing electric power deficiency through the corresponded transmission links. This paper investigates the dynamic reliability of the proposed power grid system when the demands of all star-terminal subsystems are satisfied after performance sharing. An algorithm based on the universal generating function (UGF) technique is presented to evaluate the dynamic reliability of the proposed power grid system with performance sharing. Finally, a numerical example and a case study are used to illustrate the accuracy of the proposed model and method.

show abstract

Discrete-Time Bayesian Networks Applied to Flexible Coping Strategies of Nuclear Power Plant Systems

Cited by 2 publications

References 19 publications

AI-Driven approach for enhancing nuclear reactor safety predictive anomaly detection and risk assessment

AI-Driven approach for enhancing nuclear reactor safety predictive anomaly detection and risk assessment

Reliability analysis of discrete-time multi-state star configuration power grid systems with performance sharing

Contact Info

Product

Resources

About