A First Analysis of JET Plasma Profile-Based Indicators for Disruption Prediction and Avoidance

Pau, A.; Fanni, Alessandra; Cannas, B.; Carcangiu, Sara; Pisano, Giada; Sias, Giuliana; Sparapani, P.; Baruzzo, M.; Murari, A.; Rimini, F.; Tsalas, M.; Vries, P. C. de

doi:10.1109/tps.2018.2841394

Cited by 39 publications

(76 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to effectively extract the information associated with multi-dimensional signal data, one-dimensional profiles describing the evolution in time of basic plasma quantities such as the electron temperature, the electron density and the radiation have been processed synthesizing physics-based indicators to be provided as input features to the disruption predictor. In particular, as described in [5], the so called "peaking factors"…”

Section: Diagnostics and Feature Engineeringmentioning

confidence: 99%

“…In [5], the peaking factors have been considered as features defined as a "core versus all" metric, i.e., they are defined as the ratio between the mean value of the considered radial profile (temperature, radiation, density) around the magnetic axis and the mean value of the measurements over the entire radius. The radial interval to define the "core" with respect to the magnetic axis has been empirically set to the 25% of the radial coordinate (the minor radius for poloidal mid-plane measurements) in the case of electron temperature and density profiles, and to the 10% of the vertical semi-axis of the poloidal cross section in the case of radiation profiles.…”

Section: Accepted Manuscriptmentioning

confidence: 99%

“…Regarding the peaking factor of the radiation, instead of considering a unique indicator to synthesize a peaking factor for the poloidal distribution of the radiation, as proposed in [5], two different indicators have been derived splitting the information carried out by the global radiation distribution according to the two main mechanisms involving a radiation collapse: the accumulation of high-Z impurities in the plasma core as opposed to edge-radiative collapse. As analyzed in [5], the main mechanisms with which the discharge is being destabilized are quite different, as well as the time scales involved in the corresponding chain of events. Nevertheless, although the initial version of the peaking factor was such that both the edge and core radiation collapse could be detected quite nicely, the two mechanisms are not mutually exclusive, and even if developing on different time scales, there are cases where both are simultaneously affecting the discharge.…”

Section: Accepted Manuscriptmentioning

confidence: 99%

See 2 more Smart Citations

A machine learning approach based on generative topographic mapping for disruption prevention and avoidance at JET

et al. 2019

Self Cite

View full text Add to dashboard Cite

Predictive capabilities better than 95%, and very limited false alarms, are demanding requirements for reliable disruption prediction systems in tokamaks such as JET or, in the near future, ITER. The prediction of an upcoming disruption has to be provided sufficiently in advance in order to apply effective disruption avoidance or mitigation actions preventing the machine to be damaged. In this paper, following the typical machine learning workflow, a Generative Topographic Mapping (GTM) of the operational space of JET has been built using a set of disrupted and regularly terminated discharges. In order to build the predictive model, a suitable set of dimensionless, machine-independent, physics-based features have been synthesized, which make use of 1D plasma profiles information, rather than simple zero-D time series. The use of such predicting features, together with the power of the GTM in fitting the model to the data, allows obtaining, in an unsupervised way, a 2-dimensional map of the multi-dimensional parameter space of JET, where it is possible to identify a boundary separating the region free from disruption from the disruption region. In addition to helping in operational boundaries studies, the GTM map can also be used for disruption prediction exploiting the potentiality of the developed GTM toolbox to monitor the discharge dynamics. Following the trajectory of a discharge on the map throughout the different regions, an alarm is triggered depending on the disruption risk of these regions. The proposed approach to predict disruptions has been evaluated on a training and an independent test set, allowing to achieve very good performance with only one tardive detection and a limited number of false detections. The warning times are suitable for avoidance purposes and, more important, the detections are consistent with physics causes and mechanisms that destabilize the plasma leading to disruptions.

show abstract

Section: Diagnostics and Feature Engineeringmentioning

confidence: 99%

Section: Accepted Manuscriptmentioning

confidence: 99%

Section: Accepted Manuscriptmentioning

confidence: 99%

See 1 more Smart Citation

A machine learning approach based on generative topographic mapping for disruption prevention and avoidance at JET

et al. 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…In recent works [67,68] the bolometer signals have been used to extract one or two peaking factors of the radiation profile, which were then combined with other global parameters for disruption prediction. An advantage of using deep learning is that, in principle, it should be possible to extract these and/or other relevant features directly from the raw signals.…”

Section: Prediction Accuracymentioning

confidence: 99%

Deep Learning for Plasma Tomography and Disruption Prediction From Bolometer Data

Ferreira

Carvalho

Fernandes

2020

IEEE Trans. Plasma Sci.

View full text Add to dashboard Cite

The use of deep learning is facilitating a wide range of data processing tasks in many areas. The analysis of fusion data is no exception, since there is a need to process large amounts of data collected from the diagnostic systems attached to a fusion device. Fusion data involves images and time series, and are a natural candidate for the use of convolutional and recurrent neural networks. In this work, we describe how CNNs can be used to reconstruct the plasma radiation profile, and we discuss the potential of using RNNs for disruption prediction based on the same input data. Both approaches have been applied at JET using data from a multi-channel diagnostic system. Similar approaches can be applied to other fusion devices and diagnostics.

show abstract

“…7, Random Forest algorithms can reveal the relative contributions of the various input data signals to the final disruption probability [51], [52]. Generative Topographic Mapping (GTM) reduces a complex multi-dimensional space of input data to a 2-D or 3-D space of safe and unstable regions, simplifying the tasks of classification, prediction, and control of instabilities [53], [54] (see Fig. 8).…”

mentioning

confidence: 99%

Progress in disruption prevention for ITER

Strait¹,

Barr²,

Baruzzo³

et al. 2019

Nucl. Fusion

Self Cite

View full text Add to dashboard Cite

Key plasma physics and real-time control elements needed for robustly stable operation of high fusion power discharges in ITER have been demonstrated in US fusion research. Optimization of the current density profile has enabled passively stable operation without n " 1 tearing modes in discharges simulating ITER's baseline scenario with zero external torque. Stable rampdown of the discharge has been achieved with ITER-like scaled current ramp rates, while maintaining an X-point configuration. Significant advances have been made toward real-time prediction of disruptions: machine learning techniques for prediction of disruptions have achieved 90% accuracy in offline analysis, and direct probing of ideal and resistive plasma stability using 3D magnetic perturbations has shown a rising plasma response before the onset of a tearing mode. Active stability control contributes to prevention of disruptions, including direct stabilization of resistive-wall kink modes in high-β discharges, forced rotation of magnetic islands to prevent wall locking, and localized heating/current drive to shrink the islands. These elements are being integrated into stable operating scenarios and a new event-handling system for off-normal events in order to develop the physics basis and techniques for robust control in ITER.

show abstract

A First Analysis of JET Plasma Profile-Based Indicators for Disruption Prediction and Avoidance

Cited by 39 publications

References 11 publications

A machine learning approach based on generative topographic mapping for disruption prevention and avoidance at JET

A machine learning approach based on generative topographic mapping for disruption prevention and avoidance at JET

Deep Learning for Plasma Tomography and Disruption Prediction From Bolometer Data

Progress in disruption prevention for ITER

Contact Info

Product

Resources

About