Initialising ...
Initialising ...
Initialising ...
Initialising ...
Initialising ...
Initialising ...
Initialising ...
Zheng, X.; Tamaki, Hitoshi; Takahara, Shogo; Sugiyama, Tomoyuki; Maruyama, Yu
Proceedings of Probabilistic Safety Assessment and Management (PSAM16) (Internet), 10 Pages, 2022/09
Zheng, X.; Tamaki, Hitoshi; Sugiyama, Tomoyuki; Maruyama, Yu
Reliability Engineering & System Safety, 223, p.108503_1 - 108503_12, 2022/07
Times Cited Count：17 Percentile：91.72(Engineering, Industrial)Zheng, X.; Tamaki, Hitoshi; Sugiyama, Tomoyuki; Maruyama, Yu
no journal, ,
no abstracts in English
Zheng, X.; Takahara, Shogo; Tamaki, Hitoshi; Sugiyama, Tomoyuki; Maruyama, Yu
no journal, ,
no abstracts in English
Zheng, X.; Tamaki, Hitoshi; Shibamoto, Yasuteru; Takada, Tsuyoshi
no journal, ,
JAEA is constructing a dynamic probabilistic risk assessment (PRA) approach which integrates deterministic accident analysis and probabilistic reliability analysis, and developing an associated computational tool, RAPID. Taking the estimation of failure probability of machines as an example, this paper identifies latent sources of epistemic uncertainties in PRA. To reduce such epistemic uncertainties, authors have proposed to apply probabilistic physics-of-failure by dynamically modeling the interaction between operational conditions and failure probabilities of machines. Moreover, authors have implemented automatic coupling techniques between simulation codes in RAPID.
Zheng, X.; Tamaki, Hitoshi; Shibamoto, Yasuteru; Maruyama, Yu
no journal, ,
The nuclear industry is expressing a growing interest in the research and use of artificial intelligence and machine learning (AI/ML) technology to improve plant operational performance and reduce the risks associated with nuclear power generation. JAEA is applying the AI/ML technology to advancing researches on severe accidents and probabilistic risk assessment (PRA). To efficiently perform dynamic PRA and uncertainty quantification of source terms, both simulation-based, we are introducing surrogate models trained via machine learning to estimate core damage frequency (conditional core damage probability), to obtain information about the probability distribution of source terms and importance ranking of parameters. AI/ML can be expected to efficiently provide risk and uncertainty information to make rational decisions for the continuous improvement of nuclear safety.
