Simulation and Real-Time Replacement of Missing Plasma Signals for Disruption Prediction: An Implementation with APODIS

Abstract

So far, the best results for real-time disruption prediction on JET (Joint European Torus) have been

achieved with APODIS (Advanced Predictor Of DISruptions). APODIS is a data-driven system

whose last version has been implemented in JET’s real time-data network. It has been designed for

the real-time analysis of features (mean and frequency values) corresponding to 7 plasma signals

in order to foresee incoming disruptions.

In this article, non-linear regression techniques are applied to create (off-line) signal models. The

models are able to generate (in real-time) “synthetic” signals. Therefore, these “synthetic” signals

can be used to replace the original ones in the case they are in error or missing.

Under these conditions APODIS has been tested emulating real-time operation. The simulation

results demonstrate that once a signal in error is replaced by the generated “synthetic” one, APODIS

performances are considerably improved. The development of the regression models and the

implications of the results are detailed and discussed in this paper.