Refine your search:     
Report No.
 - 
Search Results: Records 1-20 displayed on this page of 83

Presentation/Publication Type

Initialising ...

Refine

Journal/Book Title

Initialising ...

Meeting title

Initialising ...

First Author

Initialising ...

Keyword

Initialising ...

Language

Initialising ...

Publication Year

Initialising ...

Held year of conference

Initialising ...

Save select records

Journal Articles

Evaluations with autoencoder whether the image used for image recognition is appropriate

Nomura, Masahiro; Okita, Hidefumi; Shimada, Taihei; Tamura, Fumihiko; Yamamoto, Masanobu; Furusawa, Masashi*; Sugiyama, Yasuyuki*; Hasegawa, Katsushi*; Hara, Keigo*; Omori, Chihiro*; et al.

Proceedings of 18th Annual Meeting of Particle Accelerator Society of Japan (Internet), p.80 - 82, 2021/10

no abstracts in English

Journal Articles

AMR-Net: Convolutional neural networks for multi-resolution steady flow prediction

Asahi, Yuichi; Hatayama, Sora*; Shimokawabe, Takashi*; Onodera, Naoyuki; Hasegawa, Yuta; Idomura, Yasuhiro

Proceedings of 2021 IEEE International Conference on Cluster Computing (IEEE Cluster 2021) (Internet), p.686 - 691, 2021/10

 Times Cited Count:0 Percentile:0.01

We develop a convolutional neural network model to predict the multi-resolution steady flow. Based on the state-of-the-art image-to-image translation model pix2pixHD, our model can predict the high resolution flow field from the set of patched signed distance functions. By patching the high resolution data, the memory requirements in our model is suppressed compared to pix2pixHD.

JAEA Reports

Annual report of Nuclear Human Resource Development Center (April 1, 2019 - March 31, 2020)

Nuclear Human Resource Development Center

JAEA-Review 2021-010, 70 Pages, 2021/09

JAEA-Review-2021-010.pdf:3.53MB

This annual report summarizes the activities of Nuclear Human Resource Development Center (NuHRDeC) of Japan Atomic Energy Agency (JAEA) in the fiscal year (FY) 2019.

Journal Articles

Data-driven derivation of partial differential equations using neural network model

Koyamada, Koji*; Yu, L.*; Kawamura, Takuma; Konishi, Katsumi*

International Journal of Modeling, Simulation, and Scientific Computing, 12(2), p.2140001_1 - 2140001_19, 2021/04

With the improvement of sensors technologies in various fields such as fluid dynamics, meteorology, and space observation, it is an important issue to derive explanatory models using partial differential equations (PDEs) for the big data obtained from them. In this paper, we propose a technique for estimating linear PDEs with higher-order derivatives for spatiotemporally discrete point cloud data. The technique calculates the time and space derivatives from a neural network (NN) trained on the point cloud data, and estimates the derivative term of the PDE using regression analysis techniques. In the experiment, we computed the error of the estimated PDEs for various meta-parameters for the PDEs with exact solutions. As a result, we found that increasing the hierarchy of NNs to match the order of the derivative terms in the exact solution PDEs and adopting L1 regularization with LASSO as the method of regression analysis increased the accuracy of the model.

JAEA Reports

Outline of Regional Workshops held in 2006 - 2017 by the International Atomic Energy Agency in the proposal of Nuclear Emergency Preparedness Group of the Asian Nuclear Safety Network

Okuno, Hiroshi; Yamamoto, Kazuya

JAEA-Review 2020-066, 32 Pages, 2021/02

JAEA-Review-2020-066.pdf:3.01MB

The International Atomic Energy Agency (abbreviated as IAEA) has been implementing the Asian Nuclear Safety Network (abbreviated as ANSN) activities since 2002. As part of this effort, Topical Group on Emergency Preparedness and Response (abbreviated as EPRTG) for nuclear or radiation disasters was established in 2006 under the umbrella of the ANSN. Based on the EPRTG proposal, the IAEA conducted 23 Asian regional workshops in the 12 years from 2006 to 2017. Typical topical fields of the regional workshops were nuclear emergency drills, emergency medical care, long-term response after nuclear/radiological emergency, international cooperation, national nuclear disaster prevention system. The Japan Atomic Energy Agency has produced coordinators for EPRTG since its establishment and has led its activities since then. This report summarizes the Asian regional workshops conducted by the IAEA based on the recommendations of the EPRTG.

JAEA Reports

Registration and related activities of the Japan Atomic Energy Agency for the response and assistance network of the International Atomic Energy Agency

Togawa, Orihiko; Hayakawa, Tsuyoshi; Tanaka, Tadao; Yamamoto, Kazuya; Okuno, Hiroshi

JAEA-Review 2020-017, 36 Pages, 2020/09

JAEA-Review-2020-017.pdf:2.24MB

In 2010, the government of Japan joined the Response and Assistance Network (RANET) of the International Atomic Energy Agency (IAEA), in order to contribute to offering international assistance in the case of a nuclear accident or radiological emergency. At that occasion, the Japan Atomic Energy Agency (JAEA) was registered as the National Assistance Capability (NAC) having resources capable of the External Based Support (EBS) in the following seven areas: (1) aerial survey, (2) radiation monitoring, (3) environmental measurements, (4) assessment and advice, (5) internal dose assessment, (6) bioassay and (7) dose reconstruction. After the registration, three inquiries were directed to the JAEA about a possibility of its support. However, the JAEA's assistance has not eventually been realized. On the other hand, the JAEA participated almost every year in the international Convention Exercise (ConvEx) carried out by the IAEA in connection with RANET. This report describes an outline of the RANET and related activities of the JAEA for RANET registration and participation in the ConvEx.

Journal Articles

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

Sun, D.*; Wainwright-Murakami, Haruko*; Oroza, C. A.*; Seki, Akiyuki; Mikami, Satoshi; Takemiya, Hiroshi; Saito, Kimiaki

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

 Times Cited Count:6 Percentile:54.31(Environmental Sciences)

We have developed a methodology for optimizing the monitoring locations of radiation air dose-rate monitoring. For the method, we use a Gaussian mixture model to identify the representative locations among multiple environmental variables, such as elevation and land-cover types. Next, we use a Gaussian process model to capture and estimate the heterogeneity of air-dose rates across the domain. Our results have shown that this approach allows us to select monitoring locations in a systematic manner such that the heterogeneity of air dose rates is captured by the minimal number of monitoring locations.

JAEA Reports

Annual report of Nuclear Human Resource Development Center (April 1, 2018 - March 31, 2019)

Nuclear Human Resource Development Center

JAEA-Review 2020-008, 74 Pages, 2020/06

JAEA-Review-2020-008.pdf:3.5MB

This annual report summarizes the activities of Nuclear Human Resource Development Center (NuHRDeC) of Japan Atomic Energy Agency (JAEA) in the fiscal year (FY) 2018.

JAEA Reports

Annual report of Nuclear Human Resource Development Center (April 1, 2017 - March 31, 2018)

Nuclear Human Resource Development Center

JAEA-Review 2019-009, 65 Pages, 2019/09

JAEA-Review-2019-009.pdf:5.56MB

This annual report summarizes the activities of Nuclear Human Resource Development Center (NuHRDeC) of Japan Atomic Energy Agency (JAEA) in the fiscal year (FY) 2017.

JAEA Reports

Annual report of Nuclear Human Resource Development Center (April 1, 2016 - March 31, 2017)

Nuclear Human Resource Development Center

JAEA-Review 2018-009, 69 Pages, 2018/09

JAEA-Review-2018-009.pdf:2.67MB
JAEA-Review-2018-009(errata).pdf:0.16MB

This annual report summarizes the activities of Nuclear Human Resource Development Center (NuHRDeC) of Japan Atomic Energy Agency (JAEA) in the fiscal year (FY) 2016.

Journal Articles

Determination of reactivity and neutron flux using modified neural network for HTGR

Subekti, M.*; Kudo, Kazuhiko*; Nabeshima, Kunihiko; Takamatsu, Kuniyoshi

Atom Indonesia, 43(2), p.93 - 102, 2017/08

Reactor kinetics based on point kinetic model have been generally applied as the standard method for neutronics codes. As the central control rod (C-CR) withdrawal test has demonstrated in a prismatic core of HTTR, the transient calculation of kinetic parameter, such as reactivity and neutron fluxes, requires a new method to shorten calculation-process time. Development of neural network method was applied to point kinetic model as the necessity of real-time calculation that could work in parallel with the digital reactivity meter. The combination of TDNN and Jordan RNN, such as TD-Jordan RNN, was the result of the modeling approach. The application of TD-Jordan RNN with adequate learning, tested offline, determined results accurately even when signal inputs were noisy. Furthermore, the preprocessing for neural network input utilized noise reduction as one of the equations to transform two of twelve time-delayed inputs into power corrected inputs.

Journal Articles

Info session on human networking held in Japan-IAEA Joint Nuclear Energy Management School; Aiming to develop human network among nuclear young generation in the world

Nishiyama, Jun*; Ohgama, Kazuya; Sakamoto, Tatsujiro*; Watanabe, Rin*

Nihon Genshiryoku Gakkai-Shi ATOMO$$Sigma$$, 57(2), p.123 - 125, 2015/02

no abstracts in English

Journal Articles

Socio-economic effects of the material science in JAERI

Yanagisawa, Kazuaki; Takahashi, Shoji*

Scientometrics, 78(3), p.505 - 524, 2008/10

 Times Cited Count:1 Percentile:25.54(Computer Science, Interdisciplinary Applications)

A socio-economic evaluation of Material Science (MS) of JAERI was made. The goal was to reveal the emphasized basic research fields (EBRF) of MS and to observe its socio-economic networking. High ranked keywords for the former and the number of co-authored papers for the latter were used along with many MS related papers. The obtained results are: (1) The EBRF of MS of JAERI were typically represented by the keywords of ion irradiation, actinides, etc., i.e., those having a strong relation to the nuclear field. Regarding actinides, the socio-economic networking between JAERI and PS occurred at the growth rate of 3-4% per 25 years, but 8% during the past 5 years. This implies that the research cooperation between the two was markedly enhanced. (2) The EBRF of MS between JAERI and 5 selected research bodies (SRB) represented by Tokyo University was directly compared and revealed that only 7 keywords as typically represented by neutron and accelerators. After overlapping, JAERI and SRB seem to be raising the national standard level.

Journal Articles

Neural-net predictor for beta limit disruptions in JT-60U

Yoshino, Ryuji

Nuclear Fusion, 45(11), p.1232 - 1246, 2005/11

 Times Cited Count:36 Percentile:74.89(Physics, Fluids & Plasmas)

Prediction of major disruptions observed at the $$beta$$-limit for tokamak plasmas has been investigated in JT-60U with developing neural networks. A sub-neural network is trained to output a value of the $$beta$$$$_{N}$$ limit every 2 ms. The target $$beta$$$$_{N}$$ limit is artificially set by the operator in the first step training and is modified in the second step training using the output $$beta$$$$_{N}$$ limit from the trained network. To improve the prediction performance further, the difference between the estimated $$beta$$$$_{N}$$ limit and the measured $$beta$$$$_{N}$$ and the other 11 parameters are inputted to a main neural network to calculate the stability level. Major disruptions have been predicted with a prediction success rate of 80% at 10 ms prior to the disruption while the false alarm rate is lower than 4%. This 80% is much higher than about 10% previously obtained. A prediction success rate of 90% has been also obtained with a false alarm rate of 12% at 10 ms prior to the disruption. This 12% is about a half of previously obtained one.

Journal Articles

Development of a quake-proof information inference system by using data mining technology

Shu, Y.; Nakajima, Norihiro

Proceedings of 11th International Conference on Human-Computer Interaction (HCI International 2005) (CD-ROM), 9 Pages, 2005/07

To understand the behavior of NPP (nuclear power plant) under different operating environment, JAERI is carrying out full-scaled plant simulation. As one part of full scaled plant simulation, our ongoing work is to develop an information inference system to manage and interpret NPP quake-proof data. In this paper, we proposed a hybrid data mining approach, which integrates human cognitive model in a data mining loop. Rule-based mining control agent emulated human analysts directly interacts with the data miner, analyzing and verifying the output of data miner and controlling data mining process. In additional, artificial neural network method, which is adopted as a core component of the proposed hybrid data mining method, is evolved by adding the retraining facility and explaining function for handling complicated nuclear power plant quake-proof data. To demonstrate how the method can be used as a powerful tool for extracting information relevant to plant safety and reliability, plant quake-proof testing data have been applied to the inference system.

Journal Articles

Pre-test analysis method using a neural network for control-rod withdrawal tests of HTTR

Ono, Tomio*; Subekti, M.*; Kudo, Kazuhiko*; Takamatsu, Kuniyoshi; Nakagawa, Shigeaki; Nabeshima, Kunihiko

Nihon Genshiryoku Gakkai Wabun Rombunshi, 4(2), p.115 - 126, 2005/06

Control-rod withdrawal tests simulating reactivity insertion are carried out in the HTTR to verify the inherent safety features of HTGRs. This paper describes pre-test analysis method using artificial neural networks to predict the changes of reactor power and reactivity. The network model applied in this study is based on recurrent neural networks. The inputs of the network are the changes of the central control rods position and other significant core parameters, and the outputs are the changes of reactor power and reactivity. Furthermore, Time Synchronizing Signal(TSS) is added to input to improve the modeling of time series data. The actual tests data, which were previously carried out in the HTTR, were used for learning the model of the plant dynamics. After the learning, the network can predict the changes of reactor power and reactivity in the following tests.

Journal Articles

Building plant quake-proof information inference system based on hybrid data mining approach

Shu, Y.; Nakajima, Norihiro

Proceedings of 1st International Workshop on Risk Management System with Intelligent Data Analysis (RMDA 2005) in Conjunction with 19th Annual Conference of the Japanese Society for Artificial Intelligence (JSAI 2005), p.35 - 44, 2005/06

This paper presents an intelligent information inference system based on a hybrid data mining approach, which integrates human cognitive model in a data mining loop. In the proposed system, the mining control agent emulated human analysts interacts directly with the data miner, analyzing and verifying the output of the data miner and controlling the data mining process. In additional, the neural network method, which is adopted as a core component of the proposed hybrid data mining method, is evolved by adding the retraining facility and explaining function for handling complicated quake-proof data of nuclear power plant. To demonstrate how the method can be used as a powerful tool for extracting information relevant to plant safety and reliability, plant quake-proof testing data have been applied to the inference system.

Journal Articles

Expectations of JAERI on INIS from a viewpoint of socio-economic evaluation

Yanagisawa, Kazuaki; Takahashi, Shoji; Narita, Osamu; Yonezawa, Minoru

IAEA-CN-123/03/P/18 (CD-ROM), 9 Pages, 2004/10

To understand a socio-economic effect of basic research in JAERI, the stimulation and promotion of social interrelations through a formation of networking was studied quantitatively. (1)Worldwide trend of MS was studied by INIS by means of top {100} keywords as input. Research activity of MS in JAERI represented by top {100} keywords is not much different from that of other nuclear advanced countries participated to INIS. (2)Emphasized basic research fields (EBRF) of MS in JAERI can be clarified by selected keywords of "ion irradiation" and "actinides", those have a strong relation to nuclear. For actinides, the growth rate of networking between JAERI and PS was of order of 3-4% per 25 years and 8% per recent 5 years. The rate of networking formation is markedly increased recently. (3)Between JAERI and the other 5 selected research bodies, only 7 out of over 110 keywords such as "neutron" and "accelerators" were overlapped. In the overlapped region the two compensated and uplifted the national standard level each other.

JAEA Reports

Standard of radiation monitor based on LAN and PLC technology for J-PARC

Miyamoto, Yukihiro; Sakamaki, Tsuyoshi*; Maekawa, Osamu*; Nakashima, Hiroshi

JAERI-Tech 2004-054, 72 Pages, 2004/08

JAERI-Tech-2004-054.pdf:7.3MB

A standard is provided for the radiation monitor based on LAN (Local Area Network) and PLC (Programmable Logic Controller) technology at the introduction to the Japan Proton Accelerator Research Complex (J-PARC). The monitor consists of radiation measurement equipments and the central monitoring panel. The formers are installed in the radiation field, and the latter is installed in the control room and composed of PLC, which are connected with LAN. Extension of the existing standard and the conformity to the international standard were thought as important in providing the standard. The standard is expected to improve the compatibility, maintenancability and productivity of the components.

83 (Records 1-20 displayed on this page)