A mobile dose prediction system based on artificial neural networks for NPP emergencies with radioactive material releases
Autor(a) principal: | |
---|---|
Data de Publicação: | 2017 |
Outros Autores: | , , , , |
Tipo de documento: | Artigo de conferência |
Idioma: | eng |
Título da fonte: | Repositório Institucional do IEN |
Texto Completo: | http://carpedien.ien.gov.br:8080/handle/ien/2153 |
Resumo: | This work presents the approach of a mobile dose prediction system for NPP emergencies with nuclear material release. The objective is to provide extra support to field teams decisions when plant information systems are not available. However, predicting doses due to atmospheric dispersion of radionuclide generally requires execution of complex and computationally intensive physical models. In order to allow such predictions to be made by using limited computational resources such as mobile phones, it is proposed the use of artificial neural networks (ANN) previously trained (offline) with data generated by precise simulations using the NPP atmospheric dispersion system. Typical situations for each postulated accident and respective source terms, as well as a wide range of meteorological conditions have been considered. As a first step, several ANN architectures have been investigated in order to evaluate their ability for dose prediction in hypothetical scenarios in the vicinity of CNAAA Brazilian NPP, in Angra dos Reis, Brazil. As a result, good generalization and a correlation coefficient of 0.99 was achieved for a validation data set (untrained patterns). Then, selected ANNs have been coded in Java programming language to run as an Android application aimed to plot the spatial dose distribution into a map.In this paper, the general architecture of the proposed system is described; numerical results and comparisons between investigated ANN architectures are discussed; performance and limitations of running the Application into a commercial mobile phone are evaluated and possible improvements and future works are pointed. |
id |
IEN_ecb83237088f5448a4c269c119229353 |
---|---|
oai_identifier_str |
oai:carpedien.ien.gov.br:ien/2153 |
network_acronym_str |
IEN |
network_name_str |
Repositório Institucional do IEN |
spelling |
PEREIRA, Claudio M. N. A.SCHIRRU, RobertoGOMES, Kelcio J.CUNHA, José LuizInstituto de Engenharia Nuclear (IEN)Universidade Federal do Rio de Janeiro - PEN/COPPE/UFRJInstituto de Engenharia Nuclear (IEN)Universidade Federal do Rio de Janeiro - PEN/COPPE/UFRJ2018-02-08T14:04:30Z2018-02-08T14:04:33Z2018-02-08T14:04:30Z2018-02-08T14:04:33Z2017-10http://carpedien.ien.gov.br:8080/handle/ien/2153Submitted by Vanessa Silva (vanessacapucho.uerj@gmail.com) on 2018-02-08T14:04:30Z No. of bitstreams: 1 ARTIGO INAC 9.pdf: 990102 bytes, checksum: 8a13d9ba66579c14f53daf78263a6509 (MD5)Made available in DSpace on 2018-02-08T14:04:30Z (GMT). No. of bitstreams: 1 ARTIGO INAC 9.pdf: 990102 bytes, checksum: 8a13d9ba66579c14f53daf78263a6509 (MD5) Previous issue date: 2017-10Submitted by Vanessa Silva (vanessacapucho.uerj@gmail.com) on 2018-02-08T14:04:33Z No. of bitstreams: 1 ARTIGO INAC 9.pdf: 990102 bytes, checksum: 8a13d9ba66579c14f53daf78263a6509 (MD5)Made available in DSpace on 2018-02-08T14:04:33Z (GMT). No. of bitstreams: 1 ARTIGO INAC 9.pdf: 990102 bytes, checksum: 8a13d9ba66579c14f53daf78263a6509 (MD5) Previous issue date: 2017-10This work presents the approach of a mobile dose prediction system for NPP emergencies with nuclear material release. The objective is to provide extra support to field teams decisions when plant information systems are not available. However, predicting doses due to atmospheric dispersion of radionuclide generally requires execution of complex and computationally intensive physical models. In order to allow such predictions to be made by using limited computational resources such as mobile phones, it is proposed the use of artificial neural networks (ANN) previously trained (offline) with data generated by precise simulations using the NPP atmospheric dispersion system. Typical situations for each postulated accident and respective source terms, as well as a wide range of meteorological conditions have been considered. As a first step, several ANN architectures have been investigated in order to evaluate their ability for dose prediction in hypothetical scenarios in the vicinity of CNAAA Brazilian NPP, in Angra dos Reis, Brazil. As a result, good generalization and a correlation coefficient of 0.99 was achieved for a validation data set (untrained patterns). Then, selected ANNs have been coded in Java programming language to run as an Android application aimed to plot the spatial dose distribution into a map.In this paper, the general architecture of the proposed system is described; numerical results and comparisons between investigated ANN architectures are discussed; performance and limitations of running the Application into a commercial mobile phone are evaluated and possible improvements and future works are pointed.engInstituto de Engenharia NuclearIENBrasilDose predictionAtmospheric dispersion of radionuclideMobileA mobile dose prediction system based on artificial neural networks for NPP emergencies with radioactive material releasesinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/conferenceObject2017info:eu-repo/semantics/openAccessreponame:Repositório Institucional do IENinstname:Instituto de Engenharia Nuclearinstacron:IENLICENSElicense.txtlicense.txttext/plain; charset=utf-81748http://carpedien.ien.gov.br:8080/xmlui/bitstream/ien/2153/2/license.txt8a4605be74aa9ea9d79846c1fba20a33MD52ORIGINALARTIGO INAC 9.pdfARTIGO INAC 9.pdfapplication/pdf990102http://carpedien.ien.gov.br:8080/xmlui/bitstream/ien/2153/1/ARTIGO+INAC+9.pdf8a13d9ba66579c14f53daf78263a6509MD51ien/2153oai:carpedien.ien.gov.br:ien/21532018-02-08 12:04:33.271Dspace IENlsales@ien.gov.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 |
dc.title.pt_BR.fl_str_mv |
A mobile dose prediction system based on artificial neural networks for NPP emergencies with radioactive material releases |
title |
A mobile dose prediction system based on artificial neural networks for NPP emergencies with radioactive material releases |
spellingShingle |
A mobile dose prediction system based on artificial neural networks for NPP emergencies with radioactive material releases PEREIRA, Claudio M. N. A. Dose prediction Atmospheric dispersion of radionuclide Mobile |
title_short |
A mobile dose prediction system based on artificial neural networks for NPP emergencies with radioactive material releases |
title_full |
A mobile dose prediction system based on artificial neural networks for NPP emergencies with radioactive material releases |
title_fullStr |
A mobile dose prediction system based on artificial neural networks for NPP emergencies with radioactive material releases |
title_full_unstemmed |
A mobile dose prediction system based on artificial neural networks for NPP emergencies with radioactive material releases |
title_sort |
A mobile dose prediction system based on artificial neural networks for NPP emergencies with radioactive material releases |
author |
PEREIRA, Claudio M. N. A. |
author_facet |
PEREIRA, Claudio M. N. A. SCHIRRU, Roberto GOMES, Kelcio J. CUNHA, José Luiz Instituto de Engenharia Nuclear (IEN) Universidade Federal do Rio de Janeiro - PEN/COPPE/UFRJ |
author_role |
author |
author2 |
SCHIRRU, Roberto GOMES, Kelcio J. CUNHA, José Luiz Instituto de Engenharia Nuclear (IEN) Universidade Federal do Rio de Janeiro - PEN/COPPE/UFRJ |
author2_role |
author author author author author |
dc.contributor.author.fl_str_mv |
PEREIRA, Claudio M. N. A. SCHIRRU, Roberto GOMES, Kelcio J. CUNHA, José Luiz Instituto de Engenharia Nuclear (IEN) Universidade Federal do Rio de Janeiro - PEN/COPPE/UFRJ Instituto de Engenharia Nuclear (IEN) Universidade Federal do Rio de Janeiro - PEN/COPPE/UFRJ |
dc.subject.por.fl_str_mv |
Dose prediction Atmospheric dispersion of radionuclide Mobile |
topic |
Dose prediction Atmospheric dispersion of radionuclide Mobile |
dc.description.abstract.por.fl_txt_mv |
This work presents the approach of a mobile dose prediction system for NPP emergencies with nuclear material release. The objective is to provide extra support to field teams decisions when plant information systems are not available. However, predicting doses due to atmospheric dispersion of radionuclide generally requires execution of complex and computationally intensive physical models. In order to allow such predictions to be made by using limited computational resources such as mobile phones, it is proposed the use of artificial neural networks (ANN) previously trained (offline) with data generated by precise simulations using the NPP atmospheric dispersion system. Typical situations for each postulated accident and respective source terms, as well as a wide range of meteorological conditions have been considered. As a first step, several ANN architectures have been investigated in order to evaluate their ability for dose prediction in hypothetical scenarios in the vicinity of CNAAA Brazilian NPP, in Angra dos Reis, Brazil. As a result, good generalization and a correlation coefficient of 0.99 was achieved for a validation data set (untrained patterns). Then, selected ANNs have been coded in Java programming language to run as an Android application aimed to plot the spatial dose distribution into a map.In this paper, the general architecture of the proposed system is described; numerical results and comparisons between investigated ANN architectures are discussed; performance and limitations of running the Application into a commercial mobile phone are evaluated and possible improvements and future works are pointed. |
description |
This work presents the approach of a mobile dose prediction system for NPP emergencies with nuclear material release. The objective is to provide extra support to field teams decisions when plant information systems are not available. However, predicting doses due to atmospheric dispersion of radionuclide generally requires execution of complex and computationally intensive physical models. In order to allow such predictions to be made by using limited computational resources such as mobile phones, it is proposed the use of artificial neural networks (ANN) previously trained (offline) with data generated by precise simulations using the NPP atmospheric dispersion system. Typical situations for each postulated accident and respective source terms, as well as a wide range of meteorological conditions have been considered. As a first step, several ANN architectures have been investigated in order to evaluate their ability for dose prediction in hypothetical scenarios in the vicinity of CNAAA Brazilian NPP, in Angra dos Reis, Brazil. As a result, good generalization and a correlation coefficient of 0.99 was achieved for a validation data set (untrained patterns). Then, selected ANNs have been coded in Java programming language to run as an Android application aimed to plot the spatial dose distribution into a map.In this paper, the general architecture of the proposed system is described; numerical results and comparisons between investigated ANN architectures are discussed; performance and limitations of running the Application into a commercial mobile phone are evaluated and possible improvements and future works are pointed. |
publishDate |
2017 |
dc.date.issued.fl_str_mv |
2017-10 |
dc.date.accessioned.fl_str_mv |
2018-02-08T14:04:30Z 2018-02-08T14:04:33Z |
dc.date.available.fl_str_mv |
2018-02-08T14:04:30Z 2018-02-08T14:04:33Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/conferenceObject |
status_str |
publishedVersion |
format |
conferenceObject |
dc.identifier.uri.fl_str_mv |
http://carpedien.ien.gov.br:8080/handle/ien/2153 |
url |
http://carpedien.ien.gov.br:8080/handle/ien/2153 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.publisher.none.fl_str_mv |
Instituto de Engenharia Nuclear |
dc.publisher.initials.fl_str_mv |
IEN |
dc.publisher.country.fl_str_mv |
Brasil |
publisher.none.fl_str_mv |
Instituto de Engenharia Nuclear |
dc.source.none.fl_str_mv |
reponame:Repositório Institucional do IEN instname:Instituto de Engenharia Nuclear instacron:IEN |
reponame_str |
Repositório Institucional do IEN |
collection |
Repositório Institucional do IEN |
instname_str |
Instituto de Engenharia Nuclear |
instacron_str |
IEN |
institution |
IEN |
bitstream.url.fl_str_mv |
http://carpedien.ien.gov.br:8080/xmlui/bitstream/ien/2153/2/license.txt http://carpedien.ien.gov.br:8080/xmlui/bitstream/ien/2153/1/ARTIGO+INAC+9.pdf |
bitstream.checksum.fl_str_mv |
8a4605be74aa9ea9d79846c1fba20a33 8a13d9ba66579c14f53daf78263a6509 |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 |
repository.name.fl_str_mv |
Dspace IEN |
repository.mail.fl_str_mv |
lsales@ien.gov.br |
_version_ |
1656026990450311168 |