Improvement of a reinforcement learning model to assist operators in controlling a nuclear power plant under abnormal operating conditions

Yoshikawa, Masanori; Seki, Akiyuki*; Okita, Shoichiro; Takaya, Shigeru; Yan, X.

Nuclear Engineering and Design, 444, p.114350_1 - 114350_9, 2025/12

https://doi.org/10.1016/j.nucengdes.2025.114350

Development of a surrogate system of a plant dynamics simulation model and an abnormal situation identification system for nuclear power plants using deep neural networks

Seki, Akiyuki; Yoshikawa, Masanori; Nishinomiya, Ryota*; Okita, Shoichiro; Takaya, Shigeru; Yan, X.

Nuclear Technology, 210(6), p.1003 - 1014, 2024/06

https://doi.org/10.1080/00295450.2023.2273566

Two types of deep neural network (DNN) systems have been constructed with the intent to assist safety operation of a nuclear power plant. One is a surrogate system (SS) that can estimate physical quantities of a nuclear power plant in a computational time of several orders less than a physical simulation model. The other is an abnormal situation identification system (ASIS) that can estimate the state of the disturbance causing an anomaly from physical quantities of a nuclear power plant. Both systems are trained and tested using data obtained from the analytical code for incore and plant dynamics (ACCORD), which reproduces the steady and dynamic behavior of the actual high Temperature engineering test reactor (HTTR) under various scenarios. The DNN models are built by adjusting, the main hyperparameters. Through these procedures, these systems are shown able to perform with a high degree of accuracy.

Development of element functions and design optimization procedures for knowledge- and AI-aided advanced reactor lifecycle optimization method, ARKADIA

Tanaka, Masaaki; Enuma, Yasuhiro; Okano, Yasushi; Uchibori, Akihiro; Yokoyama, Kenji; Seki, Akiyuki; Wakai, Takashi; Asayama, Tai

Mechanical Engineering Journal (Internet), 11(2), p.23-00424_1 - 23-00424_13, 2024/04

https://doi.org/10.1299/mej.23-00424

The outline and development status of element functions and design optimization process in ARKADIA to transform advanced nuclear reactor design to meet expectations of a safe, economic, and sustainable carbon-free energy source are introduced. It is also briefly explained that ARKADIA will realize Artificial Intelligence (AI)-aided integrated numerical analysis to offer the best possible solutions for the design and operation of a nuclear plant including optimization of safety equipment, and merge state-of-the-art numerical simulation technologies and a knowledge base that stores data and insights from past nuclear reactor development projects and R&Ds with AI technologies.

ARKADIA; For the innovation of advanced nuclear reactor design

Ohshima, Hiroyuki; Asayama, Tai; Furukawa, Tomohiro; Tanaka, Masaaki; Uchibori, Akihiro; Takata, Takashi; Seki, Akiyuki; Enuma, Yasuhiro

Journal of Nuclear Engineering and Radiation Science, 9(2), p.025001_1 - 025001_12, 2023/04

https://doi.org/10.1115/1.4054726

This paper describes the outline and development plan for ARKADIA to transform advanced nuclear reactor design to meet expectations of a safe, economic, and sustainable carbon-free energy source. ARKADIA will realize Artificial Intelligence (AI)-aided integrated numerical analysis to offer the best possible solutions for the design and operation of a nuclear plant, including optimization of safety equipment. State-of-the-art numerical simulation technologies and a knowledge base that stores data and insights from past nuclear reactor development projects and R&D are integrated with AI. In the first phase of development, ARKADIA-Design and ARKADIA-Safety will be constructed individually, with the first target of sodium-cooled reactor. In a subsequent phase, everything will be integrated into a single entity applicable not only to advanced rectors with a variety of concepts, coolants, configurations, and output levels but also to existing light-water reactors.

A Weakly supervised time series analysis framework for anomaly detection in nuclear power plants

Dong, F.*; Chen, S.*; Demachi, Kazuyuki*; Yoshikawa, Masanori; Seki, Akiyuki; Takaya, Shigeru

Proceedings of 29th International Conference on Nuclear Engineering (ICONE 29) (Internet), 7 Pages, 2022/08

https://doi.org/10.1115/ICONE29-91609

Current status of the environmental monitoring database on the accident at Fukushima Daiichi Nuclear Power Plant

Seki, Akiyuki; Saito, Kimiaki; Takemiya, Hiroshi

Journal of Radiological Protection, 41(3), p.S89 - S98, 2021/09

https://doi.org/10.1088/1361-6498/abfbc1

An enormous amount of environmental monitoring data has been acquired by various organizations for evaluation and implementation of countermeasure to mitigate the effects of the accident at the Fukushima Daiichi Nuclear Power Plant. We established procedures to collect these data, convert them into a unified format, classify them according to categories, and make the data accessible on a web-based database system. The database system enabled us to spatially and temporally compare large volumes of monitoring data. By using the database functions, characteristics of some representative data in the database were clarified.

Estimation of air dose rate using measurement results of monitoring posts in Fukushima Prefecture

Seki, Akiyuki; Mayumi, Akie; Wainwright-Murakami, Haruko*; Saito, Kimiaki; Takemiya, Hiroshi; Idomura, Yasuhiro

Proceedings of Joint International Conference on Supercomputing in Nuclear Applications + Monte Carlo 2020 (SNA + MC 2020), p.158 - 164, 2020/10

We developed a method to estimate the temporal change of the air dose rate at the location with sparse (in time) measurements by using the continuous measurement data from the nearby monitoring post. This method determines an observation model from the correlation between sparse data at the target location and dense data at the monitoring post based on a hierarchical Bayesian model. The developed method was validated against the air dose rate measured at the monitoring posts in Fukushima prefecture from 2012 to 2017. The results showed that the developed method can predict the air dose rate at almost all target locations with an error rate of less than 10%.

Optimizing long-term monitoring of radiation air dose rates

Wainwright, Haruko*; Oroza, C.*; Sun, D.*; Seki, Akiyuki; Mikami, Satoshi; Saito, Kimiaki

45th Annual Waste Management Conference (WM 2019); Encouraging Young Men & Women to Achieve Their Goals in Radwaste Management, Vol.7, p.4346 - 4356, 2020/01

In this work, we have developed a methodology for optimizing the sampling locations of radiation air dose-rate monitoring. Three steps are taken in order to determine sampling locations in a systematic manner: (1) prioritizing the critical locations, such as schools or regulatory requirement locations, (2) diversifying locations across the key environmental controls that are known to influence contaminant mobility and distributions, and (3) capturing the heterogeneity of radiation air dose rates across the domain. Our results have shown that increasing the number of sampling locations can better capture the heterogeneity of dose rates, although the estimation error does not decrease further after a certain number of samples. We have also found that when there are restrictions such as pre-existing monitoring locations or the ones along roads, the spatial estimation becomes poor even with the same number of monitoring locations.

Temporal change in radiological environments on land after the Fukushima Daiichi Nuclear Power Plant accident

Saito, Kimiaki; Mikami, Satoshi; Ando, Masaki; Matsuda, Norihiro; Kinase, Sakae; Tsuda, Shuichi; Sato, Tetsuro*; Seki, Akiyuki; Sanada, Yukihisa; Wainwright-Murakami, Haruko*; et al.

Journal of Radiation Protection and Research, 44(4), p.128 - 148, 2019/12

https://doi.org/10.14407/jrpr.2019.44.4.128

Characterizing regional-scale temporal evolution of air dose rates after the Fukushima Daiichi Nuclear Power Plant accident

Wainwright, H. M.*; Seki, Akiyuki; Mikami, Satoshi; Saito, Kimiaki

Journal of Environmental Radioactivity, 189, p.213 - 220, 2018/09

https://doi.org/10.1016/j.jenvrad.2018.04.006

In this study, we quantify the temporal changes of air dose rates in the regional scale around the Fukushima Daiichi Nuclear Power Plant in Japan, and predict the spatial distribution of air dose rates in the future. We first apply the Bayesian geostatistical method developed by Wainwright et al. (2017) to integrate multiscale datasets including ground-based walk and car surveys, and airborne surveys, all of which have different scales, resolutions, spatial coverage, and accuracy. We apply this method to the datasets from three years: 2014 to 2016. The temporal changes among the three integrated maps enables us to characterize the spatiotemporal dynamics of radiation air dose rates.