An approach to constructing effective training data for a classification model to evaluate the reliability of a passive safety system

• Published in: Reliability engineering & system safety 2022-06, Vol.222, p.108446, Article 108446
• Main Authors: Jin, Kyungho, Kim, Hyeonmin, Ryu, Seunghyoung, Kim, Seunggeun, Park, Jinkyun
• Format: Article
• Language: English
• Subjects: Artificial intelligence; Class Imbalance; Classification; Computer applications; Deep Learning; Evaluation; Functional Failure; Functionals; Monte Carlo simulation; Nuclear accidents & safety; Nuclear Power Plant; Nuclear power plants; Nuclear safety; Passive safety system; Reliability analysis; Reliability engineering; Reliability evaluation; Safety; Safety systems; Training
• ISSN: 0951-8320; 1879-0836
• DOI: 10.1016/j.ress.2022.108446

•Passive system reliability is important for securing the safety of nuclear power plants.•Extensive computations are generally required to evaluate the passive system reliability.•Artificial intelligence (AI) models are useful for reducing the amount of computations but a lot of training data are necessary to develop them.•A method to obtain effective training data is proposed in this study with case studies to clarify its effectiveness. Although passive safety systems (PSSs) significantly contribute to the safety of nuclear power plants, evaluating the reliability of PSSs remains difficult due to a lack of data and insufficient understanding of a phenomenon on natural forces, which are driving forces of their safety functions. Within this context, approaches that evaluate functional failures of PSSs by combining Monte Carlo simulation with a thermal-hydraulic code have been proposed. In addition, several studies are trying to develop artificial intelligence models to reduce computational burdens in evaluating functional failures of PSSs. Despite such efforts, a large amount of training data is still required to train the model accurately: class imbalance between success/failure of PSSs exacerbates this problem. To address these issues, this paper proposes a method of obtaining effective training data by dealing with the data imbalance to reduce the number of data required. Case studies were performed to show the effectiveness of the proposed method and confirmed that classification models can be efficiently constructed through effective training data.