※ 半角英数字
 年 ~ 
検索結果: 16 件中 1件目~16件目を表示
  • 1


Initialising ...



Initialising ...


Initialising ...


Initialising ...


Initialising ...


Initialising ...


Initialising ...


Initialising ...



Estimation of continuous distribution of iterated fission probability using an artificial neural network with Monte Carlo-based training data

Tuya, D.; 長家 康展

Journal of Nuclear Engineering (Internet), 4(4), p.691 - 710, 2023/11



Insights into machine-learning modeling for Cr(VI) removal from contaminated water using nano-nickel hydroxide

Maamoun, I.; Rushdi, M.*; Falyouna, O.*; Eljamal, R.*; Eljamal, O.*

Separation and Purification Technology, 308, p.122863_1 - 122863_16, 2023/03

 被引用回数:2 パーセンタイル:46.28(Engineering, Chemical)

The aim of this study is to employ machine learning (ML) in providing high-accuracy prediction of Cr(VI) removal efficiency by nickel hydroxide ($$n$$-Ni(OH)$$_{2}$$) unconventional sorbent, towards the new era of artificial intelligence (AI) applications in (waste) water treatment. Hence, a reliable ML modeling was conducted based on the experimental investigation, considering different reaction parameters, including $$n$$-Ni(OH)$$_{2}$$ dosage, initial pH, reaction temperature, and initial Cr(VI) concentration. Linear regression model was selected as the suitable regression model with respect to the obtained reasonable correlation and the less training time and evaluation time, comparing to other considered regression techniques. The adopted linear regression model, for the time corresponding Cr(VI) removal efficiencies, exhibited satisfactory prediction accuracy. Furthermore, the importance of models coefficients was determined and implied the high importance of the dosage feature. The contributive effect of the investigated features was mainly concentrated at the early stage of the reaction (5 to 10 min), with an average range of 50 to 80 %, which was in agreement with the experimental findings of the rapid and full removal of Cr(VI) by $$n$$-Ni(OH)$$_{2}$$. The elucidated insights into the effects of different factors that influence Cr(VI) removal process by $$n$$-Ni(OH)$$_{2}$$ revealed the underlying interactions and removal pathways, which shall benefit other researchers in the preliminary design of pilot-scale applications and anticipating the predicted performance.


New approach to understanding the experimental $$^{133}$$Cs NMR chemical shift of clay minerals via machine learning and DFT-GIPAW calculations

大窪 貴洋*; 武井 滉洋*; 舘 幸男; 深津 勇太; 出口 健三*; 大木 忍*; 清水 禎*

Journal of Physical Chemistry A, 127(4), p.973 - 986, 2023/02

 被引用回数:0 パーセンタイル:0.01(Chemistry, Physical)



Uncertainty analysis of dynamic PRA using nested Monte Carlo simulations and multi-fidelity models

Zheng, X.; 玉置 等史; 高原 省五; 杉山 智之; 丸山 結

Proceedings of Probabilistic Safety Assessment and Management (PSAM16) (Internet), 10 Pages, 2022/09

Uncertainty gives rise to the risk. For nuclear power plants, probabilistic risk assessment (PRA) systematically concludes what people know to estimate the uncertainty in the form of, for example, risk triplet. Capable of developing a definite risk profile for decision-making under uncertainty, dynamic PRA widely applies explicit modeling techniques such as simulation to scenario generation as well as the estimation of likelihood/probability and consequences. When quantifying risk, however, epistemic uncertainties exist in both PRA and dynamic PRA, as a result of the lack of knowledge and model simplification. The paper aims to propose a practical approach for the treatment of uncertainty associated with dynamic PRA. The main idea is to perform the uncertainty analysis by using a two-stage nested Monte Carlo method, and to alleviate the computational burden of the nested Monte Carlo simulation, multi-fidelity models are introduced to the dynamic PRA. Multi-fidelity models include a mechanistic severe accident code MELCOR2.2 and machine learning models. A simplified station blackout (SBO) scenario was chosen as an example to show practicability of the proposed approach. As a result, while successfully calculating the probability of large early release, the analysis is also capable to provide uncertainty information in the form probability distributions. The approach can be expected to clarify questions such as how reliable are results of dynamic PRA.


Dynamic probabilistic risk assessment of nuclear power plants using multi-fidelity simulations

Zheng, X.; 玉置 等史; 杉山 智之; 丸山 結

Reliability Engineering & System Safety, 223, p.108503_1 - 108503_12, 2022/07

 被引用回数:9 パーセンタイル:88.92(Engineering, Industrial)

Dynamic probabilistic risk assessment (PRA) more explicitly treats timing issues and stochastic elements of risk models. It extensively resorts to iterative simulations of accident progressions for the quantification of risk triplets including accident scenarios, probabilities and consequences. Dynamic PRA leverages the level of detail for risk modeling while intricately increases computational complexities, which result in heavy computational cost. This paper proposes to apply multi-fidelity simulations for a cost- effective dynamic PRA. It applies and improves the multi-fidelity importance sampling (MFIS) algorithm to generate cost-effective samples of nuclear reactor accident sequences. Sampled accident sequences are paralleled simulated by using mechanistic codes, which is treated as a high-fidelity model. Adaptively trained by using the high-fidelity data, low-fidelity model is used to predicting simulation results. Interested predictions with reactor core damages are sorted out to build the density function of the biased distribution for importance sampling. After when collect enough number of high-fidelity data, risk triplets can be estimated. By solving a demonstration problem and a practical PRA problem by using MELCOR 2.2, the approach has been proven to be effective for risk assessment. Comparing with previous studies, the proposed multi-fidelity approach provides comparative estimation of risk triplets, while significantly reduces computational cost.


ラドンを代表としたアルファ核種の吸入による内部被ばくの横断的生体影響評価(委託研究); 令和2年度英知を結集した原子力科学技術・人材育成推進事業

廃炉環境国際共同研究センター; 岡山大学*

JAEA-Review 2021-028, 57 Pages, 2021/11




ラドンを代表としたアルファ核種の吸入による内部被ばくの横断的生体影響(委託研究); 令和元年度英知を結集した原子力科学技術・人材育成推進事業

廃炉環境国際共同研究センター; 岡山大学*

JAEA-Review 2020-029, 55 Pages, 2020/12




Optimizing long-term monitoring of radiation air-dose rates after the Fukushima Daiichi Nuclear Power Plant

Sun, D.*; Wainwright-Murakami, Haruko*; Oroza, C. A.*; 関 暁之; 三上 智; 武宮 博; 斎藤 公明

Journal of Environmental Radioactivity, 220-221, p.106281_1 - 106281_8, 2020/09

 被引用回数:9 パーセンタイル:47.16(Environmental Sciences)



ラドンを代表としたアルファ核種の吸入による内部被ばくの横断的生体影響評価(委託研究); 平成30年度英知を結集した原子力科学技術・人材育成推進事業

廃炉国際共同研究センター; 岡山大学*

JAEA-Review 2019-024, 61 Pages, 2020/01




Global continuous optimization with error bound and fast convergence

川口 賢司*; 丸山 結; Zheng, X.

Journal of Artificial Intelligence Research, 56, p.153 - 195, 2016/06

 被引用回数:11 パーセンタイル:55.15(Computer Science, Artificial Intelligence)

This paper considers global optimization with a black-box unknown objective function that can be non-convex and partly non-smooth. Such a difficult optimization problem arises in many real-world applications, such as parameter tuning in machine learning, engineering design problem, and planning with a complex physics simulator. This paper proposes a new global optimization algorithm, called Locally Oriented Global Optimization (LOGO), to achieve both fast convergence in practice and finite-time error bound in theory. The advantage and usage of the new algorithm are illustrated via theoretical analysis and an experiment conducted with 10 bench-mark test functions. Further, we modify the LOGO algorithm to specifically solve a planning problem with continuous state/action space and long time horizon while maintaining its finite-time error bound. We apply the proposed planning method to severe accident management of a nuclear power plant. The result of the application study demonstrates the practical utility of our method.



神崎 訓枝; 迫田 晃弘; 田中 裕史; 片岡 隆浩*; 石田 毅; 山岡 聖典*

no journal, , 

これまで我々は、抗酸化物質でもありイオウ代謝物でもあるグルタチオンがラドン吸入により増加することを明らかにしてきたが、どのような経路でグルタチオンが誘導されるのかはまだわかっていない。そこで、本研究では、抗酸化物質を含むイオウ代謝物に注目したメタボローム解析を行って、ラドン吸入よって変化するマウス脳中イオウ代謝物の探索を行った。バックグランドレベル、1000Bq/m$$^{3}$$, 10000Bq/m$$^{3}$$のラドンを24時間吸入したオスのBLAB/cマウスの脳を摘出し、イオウ代謝関連物質を網羅的に調べた。その結果、55種類中27種類の物質が検出され、特に、ラドン1000Bq/m$$^{3}$$や10000Bq/m$$^{3}$$でグルタチオンの前駆体であるシステインやシスタチオニンが増加していることがわかった。この結果から、ラドン吸入によるグルタチオンの増加はトランススルフレーション経路によるものであることが示唆された。加えて、機械学習の一種である自己組織化マップを用いた27種のイオウ代謝物の変化特性に基づく総合的なデータ解析を行った。クラスタリングの結果から、被ばくのバイオマーカーとして有用な代謝物の探索の可能性について報告する。



大場 正規

no journal, , 



化学組成を用いた機械学習による破砕帯活動性評価; 取り組み事例の紹介

島田 耕史; 立石 良*

no journal, , 

破砕帯の活動性評価では、上載地層法の適用が一般的であるが、地下坑道やボーリングで遭遇する破砕帯はその地表への延長部が不明な場合が多く、別の手法が必要である。開発すべき手法は、専門的判断の助けとなるような、結果が人に依存せず客観的に導き出されるものであり、実施, 普及, 検証を一般的な地質技術者が実行可能である必要がある。この目標に照らして、破砕帯中軸部の断層ガウジの全岩化学組成は魅力的である。活断層と非活断層で断層岩の化学組成に違いがあるか、という問題に対し、化学組成を用いた機械学習(多変量解析)が解決手段になり得ると考え、活動性が既知である断層の断層ガウジの化学組成の文献値を収集し、多変量解析によって活断層と非活断層を判別する一次式の探索を2018年から開始した。花崗岩質岩を対象とした検討結果は、活断層と非活断層の2群を判別率100%で分ける判別式が複数存在することを示している。発表では、過去の検討事例も含め、現在の取り組み状況を紹介する。



大場 正規; 宮部 昌文; 赤岡 克昭; 若井田 育夫

no journal, , 



Prediction of the operating control rod position of the HTTR with supervised machine learning

Ho, H. Q.; 長住 達; 島崎 洋祐; 濱本 真平; 飯垣 和彦; 後藤 実; Simanullang, I. L.*; 藤本 望*; 石塚 悦男

no journal, , 

During operation of the HTTR, hundreds of technical signals and operating conditions must be observed and evaluated to ensure safe operation of the reactor, for example reactor power, control rod position, coolant flow rate inlet/outlet, coolant temperature inlet/outlet, etc. The accumulated experiment data of the HTTR is not only important for the HTTR operation, but also for the basic development of the HTGR in general. Artificial intelligence (AI) and particularly machine learning (ML) are increasingly being used in various fields of research in modern science. They give the ability to make predictions as well as allow the extraction of key information about physical process from large datasets. Hence, there is a lot of potentials to apply AI and ML to predict the operating and safety parameters of the HTTR, and finally, a reactor simulator system for the HTTR could be expected by using the AI and ML algorithm. In this study, the control rod position of the HTTR is predicted based on ML without using the conventional neutronic codes. With the large accumulated data from operation history of the HTTR, the supervised ML with a linear regression algorithm was used. The linear regression algorithm finds a functional relationship between the input dataset (reactor power, burnup, etc.) and a reference dataset (control rod position), constructing a function that predicts control rod position from the other operation conditions. As result, the ML gives a good prediction of the HTTR control rod position with less than 5 difference compared to that in the experiment. This study is the initial step towards machine learning for research and analysis at the HTTR facility. With increasingly complicated experiments that create a large amount of data, ML is also expected to improve the design and safety analysis of the HTTR in the future.



朝比 祐一; 前山 伸也*; Bigot, J.*; Garbet, X.*; Grandgirard, V.*; 藤井 恵介*; 下川辺 隆史*; 渡邉 智彦*; 井戸村 泰宏; 小野寺 直幸; et al.

no journal, , 

大規模流体シミュレーションのためのin-situデータ解析手法およびdeep learningによる流体シミュレーション結果の代理モデルを開発した。新たに開発したin-situデータ処理手法では、MPIアプリとpythonのポスト処理スクリプトが弱結合される。この手法によってファイルを経由しないポスト処理が可能となり、最大2.7倍の性能向上が見られた。また、多重解像度の流れ場予測を可能にするdeep learning代理モデルを開発した。本モデルでは、十分な予測精度と数値シミュレーションに対する大幅な速度向上を実現した。

16 件中 1件目~16件目を表示
  • 1