A systematic investigation of radiation collapse for disruption avoidance and prevention on JET tokamak

Abstract

To produce fusion reactions efficiently, thermonuclear plasmas have to reach extremely high temperatures, which is incompatible with their coming into contact with material surfaces. Confinement of plasmas using magnetic fields has progressed significantly in the last years, particularly in the tokamak configuration. Unfortunately, all tokamak devices, and particularly metallic ones, are plagued by catastrophic events called disruptions. Many disruptions are preceded by anomalies in the radiation patterns, particularly in ITER-relevant scenarios. These specific forms of radiation emission either directly cause or reveal the approaching collapse of the configuration. Detecting the localization of these radiation anomalies in real time requires an innovative and specific elaboration of bolometric measurements, confirmed by visible cameras and the inversion of sophisticated tomographic algorithms. The information derived from these measurements can be interpreted in terms of local power balances, which suggest a new quantity, the radiated power divided by the plasma internal energy, to determine the criticality of the plasma state. Combined with robust indicators of the temperature profile shape, the identified anomalous radiation patterns allow determination of the sequence of macroscopic events leading to disruptions. A systematic analysis of JET campaigns at high power in deuterium, full tritium, and DT, for a total of almost 2000 discharges, proves the effectiveness of the approach. The warning times are such that, depending on the radiation anomaly and the available actuators, the control system of future devices is expected to provide enough notice to enable deployment of effective prevention and avoidance strategies.

Parsimonious statistical techniques for the detection of drifts toward dangerous operational conditions in tokamaks

“…Also, the line integrated density could provide competitive results if the signal was not affected by the fringe jump problem [66]. The two methods deployed with the same signals provide very similar results, with missed alarms of the order of a few percent and the false alarms of the order of 10 radiation anomalies [67]. It would be interesting to deploy them with bolometric and spectroscopic signals as inputs [68,69].…”

A hybrid physics/data-driven logic to detect, classify, and predict anomalies and disruptions in tokamak plasmas

“…The alternative adopted in the present work consists of trading space resolution for time resolution. The emission is calculated for macro-pixels derived by macro-views, obtained by summing the corresponding lines of sight of the bolometers [58,61]. Given the topology of JET bolometric cameras, it is possible to divide the projections into three vertical and three horizontal macro views, whose intersections identify the eight regions reported in figure 1.…”

Real-time disruption prediction in multi-dimensional spaces leveraging diagnostic information not available at execution time

“…Coming back to the feature vectors and the physics quantities from which the features are defined, it is important to mention that there is a certain consensus on which datasets of signals to adopt for each type of predictors. Some of the typical signals are the mode lock, the internal inductance, the total input power, radiated power, density and radiation monitors among others [32,33]. Probably, the most important one is the mode lock as explained in the next paragraph.…”