Publicación:
Adaptive predictors based on probabilistic SVM for real time disruption mitigation on JET

Vista sencilla de ítem
dc.contributor.authorMurari, A.
dc.contributor.authorLungaroni, M.
dc.contributor.authorPeluso, E.
dc.contributor.authorGaudio, P.
dc.contributor.authorVega, J.
dc.contributor.authorBaruzzo, M.
dc.contributor.authorGelfusa, Michela
dc.contributor.authorContributors, JET.
dc.contributor.authorDormido Canto, Sebastián
dc.date.accessioned2024-05-20T11:34:36Z
dc.date.available2024-05-20T11:34:36Z
dc.date.issued2018-03-02
dc.description.abstractDetecting disruptions with sufficient anticipation time is essential to undertake any form of remedial strategy, mitigation or avoidance. Traditional predictors based on machine learning techniques can be very performing, if properly optimised, but do not provide a natural estimate of the quality of their outputs and they typically age very quickly. In this paper a new set of tools, based on probabilistic extensions of support vector machines (SVM), are introduced and applied for the first time to JET data. The probabilistic output constitutes a natural qualification of the prediction quality and provides additional flexibility. An adaptive training strategy 'from scratch' has also been devised, which allows preserving the performance even when the experimental conditions change significantly. Large JET databases of disruptions, covering entire campaigns and thousands of discharges, have been analysed, both for the case of the graphite and the ITER Like Wall. Performance significantly better than any previous predictor using adaptive training has been achieved, satisfying even the requirements of the next generation of devices. The adaptive approach to the training has also provided unique information about the evolution of the operational space. The fact that the developed tools give the probability of disruption improves the interpretability of the results, provides an estimate of the predictor quality and gives new insights into the physics. Moreover, the probabilistic treatment permits to insert more easily these classifiers into general decision support and control systems.en
dc.description.versionversión final
dc.identifier.doi10.1088/1741-4326/aaaf9c
dc.identifier.issn1741-4326
dc.identifier.urihttps://hdl.handle.net/20.500.14468/12248
dc.journal.titleNuclear Fusion
dc.journal.volume58
dc.language.isoen
dc.publisherIOP Publishing
dc.relation.centerE.T.S. de Ingeniería Informática
dc.relation.departmentInformática y Automática
dc.rightsAtribución-NoComercial-SinDerivadas 4.0 Internacional
dc.rightsinfo:eu-repo/semantics/openAccess
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0
dc.subject.keywordsdisruptions
dc.subject.keywordsprobabilistic SVM
dc.subject.keywordsmachine learning predictors
dc.subject.keywordsdecision support systems
dc.titleAdaptive predictors based on probabilistic SVM for real time disruption mitigation on JETes
dc.typeartículoes
dc.typejournal articleen
dspace.entity.typePublication
relation.isAuthorOfPublicationf5f57d8a-f3c0-40a1-a93c-80d6237a2bcb
relation.isAuthorOfPublication.latestForDiscoveryf5f57d8a-f3c0-40a1-a93c-80d6237a2bcb
Archivos
Bloque original
Mostrando 1 - 1 de 1
Miniatura
Nombre:
n04_Dormido_Canto_Sebastian_Adaptive_Predictors.pdf
Tamaño:
1.98 MB
Formato:
Adobe Portable Document Format
Descargar
Colecciones
Artículos y papers