The mapping of the n-dimensional plasma parameter space of ASDEX Upgrade has been performed using a 2-dimensional Self Organizing Map, which reveals the map potentiality in data visualization. The proposed approach allows us the definition of simple displays capable of presenting meaningful information on the actual state of the plasma, but it also suggests to use the Self Organizing Map as a disruption predictor. In this paper, different criteria have been studied to associate the risk of disruption of each cluster in the map to a disruption alarm threshold. Data for this study comes from ASDEX Upgrade experiments executed between July 2002 and November 2009. The prediction performance of the proposed system has been evaluated on a set of discharges different from those used for the map training, obtaining a quite good prediction success rate. A deep analysis of the wrong predictions has been performed in order to identify possible common causes, and some criteria to increase prediction performance have been derived.

Mapping of the Asdex Upgrade Operational Space for Disruption Prediction

ALEDDA, RAFFAELE;CANNAS, BARBARA;FANNI, ALESSANDRA;SIAS, GIULIANA;
2011-01-01

Abstract

The mapping of the n-dimensional plasma parameter space of ASDEX Upgrade has been performed using a 2-dimensional Self Organizing Map, which reveals the map potentiality in data visualization. The proposed approach allows us the definition of simple displays capable of presenting meaningful information on the actual state of the plasma, but it also suggests to use the Self Organizing Map as a disruption predictor. In this paper, different criteria have been studied to associate the risk of disruption of each cluster in the map to a disruption alarm threshold. Data for this study comes from ASDEX Upgrade experiments executed between July 2002 and November 2009. The prediction performance of the proposed system has been evaluated on a set of discharges different from those used for the map training, obtaining a quite good prediction success rate. A deep analysis of the wrong predictions has been performed in order to identify possible common causes, and some criteria to increase prediction performance have been derived.
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11584/103110
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 2
  • ???jsp.display-item.citation.isi??? 0
social impact