Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Full-Pulse Tomographic Reconstruction with Deep Neural Networks
Culham Sci Ctr, JET, EUROfus Consortium, Abingdon OX14 3DB, Oxon, England.;Univ Lisbon, Inst Super Tecn, Inst Plasmas & Fusao Nucl, P-1049001 Lisbon, Portugal..ORCID-id: 0000-0001-5818-9406
KTH, Skolan för elektroteknik och datavetenskap (EECS), Elektroteknik, Fusionsplasmafysik.
KTH, Skolan för elektroteknik och datavetenskap (EECS), Elektroteknik, Fusionsplasmafysik.ORCID-id: 0000-0002-9546-4494
Vise andre og tillknytning
Rekke forfattare: 12252018 (engelsk)Inngår i: Fusion science and technology, ISSN 1536-1055, E-ISSN 1943-7641, Vol. 74, nr 1-2, s. 47-56Artikkel i tidsskrift (Fagfellevurdert) Published
Abstract [en]

Plasma tomography consists of reconstructing a two-dimensional radiation profile of a poloidal cross section of a fusion device based on line-integrated measurements along several lines of sight. The reconstruction process is computationally intensive, and in practice, only a few reconstructions are usually computed per pulse. In this work, we trained a deep neural network based on a large collection of sample tomograms that have been produced at JET over several years. Once trained, the network is able to reproduce those results with high accuracy. More importantly, it can compute all the tomographic reconstructions for a given pulse in just a few seconds. This makes it possible to visualize several phenomena-such as plasma heating, disruptions, and impurity transport-over the course of the entire pulse.

sted, utgiver, år, opplag, sider
TAYLOR & FRANCIS INC , 2018. Vol. 74, nr 1-2, s. 47-56
Emneord [en]
Plasma tomography, deep learning, convolutional neural networks
HSV kategori
Identifikatorer
URN: urn:nbn:se:kth:diva-270533DOI: 10.1080/15361055.2017.1390386ISI: 000436997000006Scopus ID: 2-s2.0-85048073739OAI: oai:DiVA.org:kth-270533DiVA, id: diva2:1415105
Konferanse
2nd International Atomic Energy Agency (IAEA) Technical Meeting (TM) on Fusion Data Processing, Validation, and Analysis (IAEA-TM), MAY 30-JUN 02, 2017, Massachusetts Inst Technol Campus, Samberg Conf Ctr, Cambridge, MA
Merknad

QC 20200317

Tilgjengelig fra: 2020-03-17 Laget: 2020-03-17 Sist oppdatert: 2020-05-11bibliografisk kontrollert

Open Access i DiVA

Fulltekst mangler i DiVA

Andre lenker

Forlagets fulltekstScopus

Søk i DiVA

Av forfatter/redaktør
Ferreira, Diogo R.Bykov, IgorFrassinetti, LorenzoGarcia-Carrasco, AlvaroHellsten, TorbjörnJohnson, ThomasMenmuir, SheenaPetersson, PerRachlew, ElisabethRatynskaia, SvetlanaRubel, MarekStefanikova, EsteraStröm, PetterTholerus, EmmiTolias, PanagiotisOlivares, Pablo VallejosWeckmann, ArminZhou, Yushun
Av organisasjonen
I samme tidsskrift
Fusion science and technology

Søk utenfor DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric

doi
urn-nbn
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf