Deep learning for safety assessment of nuclear power reactors: Reliability, explainability, and research opportunities

Ayodeji, Abiodun; Amidu, Muritala Alade; Olatubosun, Samuel Abiodun; Addad, Yacine; Ahmed, Hafiz

doi:10.1016/j.pnucene.2022.104339

Cited by 28 publications

(9 citation statements)

References 72 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Obiols-Sales and Vishnu [ 51 ] proposed a physics–DL coupled framework for accelerating the convergence of Reynolds-averaged Navier–Stokes (RANS) simulations. Ayodeji and Amidu [ 52 ] developed a surrogate model based on a deep feedforward neural network to predict the turbulent eddy viscosity in RANS simulations; the results closely matched those of an actual turbulent model. Jeon and Lee [ 53 ] constructed a neuron-network-based model to simulate the principles of the finite volume method (FVM) in fluid dynamics.…”

Section: Application Of Ai To Nuclear Reactor Design Optimizationmentioning

confidence: 89%

“…In the field of nuclear engineering, few researchers have shown sufficient interest in XAI. For example, Ayodeji and Amidu [ 52 ] adopted LIME and SHAP to calculate the importance of the input features in predicting the turbulent eddy viscosity in RANS simulations and their influence on the results. At present, the XAI methodology is yet to be widely embraced by nuclear engineering researchers, which would provide additional opportunities for the fusion of nuclear engineering and AI and introduce additional XAI methodologies to explore more robust, transparent, and accountable data-driven models for nuclear reactors.…”

Section: Future Directionsmentioning

confidence: 99%

See 1 more Smart Citation

A review of the application of artificial intelligence to nuclear reactors: Where we are and what's next

Huang

Peng

Deng

et al. 2023

Heliyon

View full text Add to dashboard Cite

Section: Application Of Ai To Nuclear Reactor Design Optimizationmentioning

confidence: 89%

Section: Future Directionsmentioning

confidence: 99%

A review of the application of artificial intelligence to nuclear reactors: Where we are and what's next

Huang

Peng

Deng

et al. 2023

Heliyon

View full text Add to dashboard Cite

“…Researchers have gathered numerous datasets over time while examining flow condensation heat transfer with varying fluids and geometric and flow parameters. By utilizing advanced ML models, it is now feasible to identify the connections between these input parameters and their respective significance in determining the output parameters [170]. For instance, Zhou et al [171] investigated the flow condensation heat transfer in mini/microchannels using a database of 4,882 data points.…”

Section: Steam Condensation Heat Transfer Based On Machinementioning

confidence: 99%

Steam Condensation Heat Transfer in the Presence of Noncondensable Gases (NCGs) in Nuclear Power Plants (NPPs): A Comprehensive Review of Fundamentals, Current Status, and Prospects for Future Research

Albdour,

Addad,

Alyammahi

et al. 2024

International Journal of Energy Research

Self Cite

View full text Add to dashboard Cite

Efficient steam condensation is crucial for safe nuclear power plant (NPP) operations, preventing pressure buildup, overheating, and the release of radioactive materials. However, the presence of noncondensable gases (NCGs), such as air, nitrogen, hydrogen, or helium, can hinder the condensation process by creating a thermal resistance layer that impedes steam diffusion and condensation on the system’s surface. Maximizing the efficiency of steam condensation requires a thorough grasp of the fundamental processes, theories, advancements, and technical hurdles. Therefore, this work thoroughly addresses these needs, with a particular emphasis on addressing the challenges posed by NCGs by dividing the work into four thematic areas. The first theme relates to a comprehensive examination of pure steam condensation phenomena, which includes an exploration of familiar condensation scenarios and various film condensation types. The second theme examines condensation in the presence of NCGs, their mixture properties, and related theories and modelling of heat and mass transfer. The third theme investigates condensation in NPP by exploring passive cooling systems and condensation phenomena under both natural and forced convection conditions during nuclear accidents, the origin of NCGs in NPP and their transportation aspects. This is followed by experimental work related to condensation scenarios and scale. Finally, the last theme looks upon the recent advancements in computational fluid dynamics (CFD) modelling of wall condensation, system analysis codes coupling with CFD, and the implementation of machine learning (ML) for predicting the condensation HTC. By bridging the gap between fundamental knowledge and practical applications, the four thematic areas presented in this work are aimed at providing a comprehensive foundation for researchers and experts in the field of steam condensation when NCGs are involved. The ultimate objective is to bolster the safety and efficacy of NPP operations by understanding the heat and mass transfer mechanisms while mitigating the risk of catastrophic events.

show abstract

“…While the majority of the publications on PWR control methods is of academic nature, some experimental studies report practical experience with load-following operation of nuclear power plants or discuss the control methods used in practice (Sipush et al, 1976;Meyer et al, 1978;Onoue et al, 2003;Franceschini and Petrovic, 2008;Wei and Zhao, 2015;Zhang et al, 2015;Lee et al, 2020;Park et al, 2022). In the last decade, modern deeplearning artificial intelligence approaches are gaining traction also in related fault-detection (Hu et al, 2021;Naimi et al, 2022a;Kollias et al, 2022), reactor design (Dzianisau et al, 2022), fuel management (Hassan et al, 2021;Che et al, 2022), and safety analysis (Demazière, Christophe et al, 2020;Gomez-Fernandez et al, 2020;Ayodeji et al, 2022;Racheal et al, 2022). The integration with renewable energy sources and the energy storage systems are additional important emerging research fields (Denholm et al, 2012;Borowiec et al, 2019;Bragg-Sitton et al, 2020;Kim and Alameri, 2020).…”

Section: Introductionmentioning

confidence: 99%

An overview of power reactor kinetics and control in load-following operation modes

et al. 2023

View full text Add to dashboard Cite

Previous work done on reactor kinetics and control in load-following operation modes available in open literature is reviewed. The analysis is focused on, however not limited to pressurized water reactors. Different approximations of the time-dependent neutron transport problem as well as different control algorithms are described in detail and compared. Due to lack of published information the majority of the comparisons was done on qualitative level. In order to facilitate future testing and intercomparisons of models and algorithms, two so-called reference scenarios with time-dependent power demand are defined: a scenario to test the limitations of the load-following capabilities of the nuclear facilities and a second, quasi-realistic scenario.

show abstract

Deep learning for safety assessment of nuclear power reactors: Reliability, explainability, and research opportunities

Cited by 28 publications

References 72 publications

A review of the application of artificial intelligence to nuclear reactors: Where we are and what's next

A review of the application of artificial intelligence to nuclear reactors: Where we are and what's next

Steam Condensation Heat Transfer in the Presence of Noncondensable Gases (NCGs) in Nuclear Power Plants (NPPs): A Comprehensive Review of Fundamentals, Current Status, and Prospects for Future Research

An overview of power reactor kinetics and control in load-following operation modes

Contact Info

Product

Resources

About