Abstract
To obtain more accurate results of probabilistic safety assessment (PSA), it is necessary to reflect more complete dynamics of nuclear power plants. In analyzing these more realistic PSA models, numerous thermal-hydraulic code runs should be performed that typically take from a few minutes to several hours. This paper proposes a fast running model using deep learning techniques to obtain plausible accident scenarios while reducing the resources required to conduct PSA. The developed model is built from a conditional autoencoder, and an analysis of its performance is carried out under both trained and untrained ranges. Taking about one second per scenario, the developed model shows about 0.4% and 1.6% error in the trained and untrained ranges, respectively. As a feasibility study, the aggressive cooldown operation under a small break loss-of-coolant accident in the APR1400 plant was considered. The proposed method can reduce uncertainty in PSA and contribute a key technique to dynamic PSA.
Highlights
According to the ‘‘Operating Experience with Nuclear Power Stations in Member States’’ annual report published by the International Atomic Energy Agency (IAEA), 450 nuclear power plants (NPPs) are in commercial operation as of December 31, 2018 [1]
Though there are many advantages of this event trees (ETs)/fault trees (FTs) methodology, it is natural to anticipate that the traditional probabilistic safety assessment (PSA) technique based on ETs and FTs intrinsically involves sources of high uncertainties, such as parameter uncertainty and model uncertainty [3]–[6]
Data generation was conducted using Multi-Dimensional Analysis of Reactor Safety (MARS)-KS code, which was developed by the Korea Atomic Energy Research Institute (KAERI) based on the RELAP5/MOD3 and COBRA-TF codes [43]
Summary
According to the ‘‘Operating Experience with Nuclear Power Stations in Member States’’ annual report published by the International Atomic Energy Agency (IAEA), 450 nuclear power plants (NPPs) are in commercial operation as of December 31, 2018 [1]. Though there are many advantages of this ET/FT methodology, it is natural to anticipate that the traditional PSA technique based on ETs and FTs intrinsically involves sources of high uncertainties, such as parameter uncertainty and model uncertainty [3]–[6] For this reason, in order to reduce the uncertainty of PSA results, many researchers have proposed diverse methodologies, whether using ET/FT or not [7]–[18], and which usually adopt a two-stage approach: (1) generating a list of plausible scenarios from an ET by considering the source of parameter and model uncertainty, and (2) determining the consequence of each plausible scenario by running precise TH codes.
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call