Advances in Automatic Disruption Classification in JET

The new full-metal ITER-like wall (ILW) at JET was found to have a deep impact on the physics of disruptions at JET. In order to develop disruption classification, the 10-dimensional operational space of JET with the new ILW has been explored using the Generative Topographic Mapping method (GTM). The 2-dimensional map has been exploited to develop an automatic disruption classification of several disruption classes manually identified. In particular, all the non-intentional disruptions have been considered, that occurred in the JET from 2011 to 2013 performed with the new wall (JET-ILW). A statistical analysis of the plasma parameters describing the operational spaces of JET with Carbon wall (JET-C) and JET-ILW has been performed and some physical considerations have been made on the difference of these two operational spaces and the disruption classes which can be identified. The performance of the JET-ILW GTM classifier is tested in a real-time fashion in conjunction with a disruption predictor presently operating at JET with good results (above 90%). Moreover, to validate and analyse the results another reference classifier has been developed, based on the k Nearest Neighbour technique. Finally, in order to verify the reliability of the performed classification, a conformal predictor has been developed which is based on non-conformity measures.
Name Size  
EFDP14016 1.60 Mb