uu.seUppsala University Publications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Adaptive learning for disruption prediction in non-stationary conditions
Uppsala University, Disciplinary Domain of Science and Technology, Physics, Department of Physics and Astronomy, Applied Nuclear Physics.
Uppsala University, Disciplinary Domain of Science and Technology, Physics, Department of Physics and Astronomy, Applied Nuclear Physics.
Uppsala University, Disciplinary Domain of Science and Technology, Physics, Department of Physics and Astronomy, Applied Nuclear Physics.
Show others and affiliations
Number of Authors: 12502019 (English)In: Nuclear Fusion, ISSN 0029-5515, E-ISSN 1741-4326, Vol. 59, no 8, article id 086037Article in journal (Refereed) Published
Abstract [en]

For many years, machine learning tools have proved to be very powerful disruption predictors in tokamaks. On the other hand, the vast majority of the techniques deployed assume that the input data is independent and is sampled from exactly the same probability distribution for the training set, the test set and the final real time deployment. This hypothesis is certainly not verified in practice, since the experimental programmes evolve quite rapidly, resulting typically in ageing of the predictors and consequent suboptimal performance. This paper describes various adaptive training strategies that have been tested to maintain the performance of disruption predictors in non-stationary conditions. The proposed approaches have been implemented using new ensembles of classifiers, explicitly developed for the present application. The improvements in performance are unquestionable and, given the difficulties encountered so far in translating predictors from one device to another, the proposed adaptive methods from scratch can therefore be considered a useful option in the arsenal of alternatives envisaged for the next generation of devices, particularly at the very beginning of their operation.

Place, publisher, year, edition, pages
2019. Vol. 59, no 8, article id 086037
Keywords [en]
disruptions, machine learning predictors, adaptive training, de-learning, obsolescence, ensembles of classifiers
National Category
Fusion, Plasma and Space Physics
Identifiers
URN: urn:nbn:se:uu:diva-398830DOI: 10.1088/1741-4326/ab1eccISI: 000474298800006OAI: oai:DiVA.org:uu-398830DiVA, id: diva2:1378296
Note

For complete list of authors see http://dx.doi.org/10.1088/1741-4326/ab1ecc

Available from: 2019-12-13 Created: 2019-12-13 Last updated: 2019-12-13Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full text

Authority records BETA

Andersson Sundén, ErikBinda, FedericoCecconello, MarcoConroy, SeanEricsson, GöranEriksson, JacobHellesen, CarlHjalmarsson, AndersPossnert, GöranPrimetzhofer, DanielSahlberg, ArneSjöstrand, HenrikSkiba, MateuszWeiszflog, Matthias

Search in DiVA

By author/editor
Andersson Sundén, ErikBinda, FedericoCecconello, MarcoConroy, SeanEricsson, GöranEriksson, JacobHellesen, CarlHjalmarsson, AndersPossnert, GöranPrimetzhofer, DanielSahlberg, ArneSjöstrand, HenrikSkiba, MateuszWeiszflog, Matthias
By organisation
Applied Nuclear Physics
In the same journal
Nuclear Fusion
Fusion, Plasma and Space Physics

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf