Requirements for Triggering the ITER Disruption Mitigation System

Vries, P. C. de; Pautasso, G.; Humphreys, D. A.; Lehnen, M.; Maruyama, S.; Snipes, J. A.; Vergara, A.; Zabeo, L.

doi:10.13182/fst15-176

Cited by 46 publications

(38 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The The metric of accuracy reaches ∼94%, but more importantly the metric of F1-score reaches ∼91%, showing the neural network has learned to predict individual time slices of both disruptive and nondisruptive time slices very well. Current machine learning disruption predictors typically achieve a true-positive rate in the low 90% on shots [25,20,13,8], with the goal of >95% with a falsepositive rate of <5% [3]. The results presented here offer a promising path to overcome this gap.…”

Section: Resultsmentioning

confidence: 97%

“…At the base level, using the full dataset at full temporal resolution could give further improvement, though may require model parallelism to train. Further, combining multiple modalities (including more diagnostics) [5] can allow the disruption to be sensitive to the various physics which can trigger disruptions [3]. Also, interpretability of the network decisions is highly desired, especially to understand the physics and extend to future machines [14].…”

Section: Discussion and Future Workmentioning

confidence: 99%

“…Disruptions in tokamaks plasmas are a sudden loss of control which cause a termination of the plasma and potentially large destructive forces and/or heating on the containment vessel and protective wall materials. Next-step devices such as ITER and beyond will have a low tolerance for disruptions [3]. We need to ensure disruptions can be avoided by accurate prediction of oncoming disruptions and mitigation techniques if necessary.…”

Section: Deep Convolutional Neural Network With Dilated Convolutionsmentioning

confidence: 99%

See 2 more Smart Citations

Deep convolutional neural networks for multi-scale time-series classification and application to tokamak disruption prediction using raw, high temporal resolution diagnostic data

et al. 2020

View full text Add to dashboard Cite

The multi-scale, mutli-physics nature of fusion plasmas makes predicting plasma events challenging. Recent advances in deep convolutional neural network architectures (CNN) utilizing dilated convolutions enable accurate predictions on sequences which have long-range, multi-scale characteristics, such as the timeseries generated by diagnostic instruments observing fusion plasmas. Here we apply this neural network architecture to the popular problem of disruption prediction in fusion tokamaks, utilizing raw data from a single diagnostic, the Electron Cyclotron Emission imaging (ECEi) diagnostic from the DIII-D tokamak. ECEi measures a fundamental plasma quantity (electron temperature) with high temporal resolution over the entire plasma discharge, making it sensitive to a number of potential pre-disruptions markers with different temporal and spatial scales. Promising, initial disruption prediction results are obtained training a deep CNN with large receptive field (∼30k), achieving an F 1 -score of ∼91% on individual time-slices using only the ECEi data.

show abstract

Section: Resultsmentioning

confidence: 97%

Section: Discussion and Future Workmentioning

confidence: 99%

Section: Deep Convolutional Neural Network With Dilated Convolutionsmentioning

confidence: 99%

See 1 more Smart Citation

Deep convolutional neural networks for multi-scale time-series classification and application to tokamak disruption prediction using raw, high temporal resolution diagnostic data

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Finally, if avoidance is deemed untenable, a prediction of the impending disruption can be provided to a mitigation system to significantly reduce disruption ramifications. Designs for disruption mitigation systems for ITER are already under way [34,35,36]. Alternative disruption avoidance approaches also exist, including for example real-time plasma state estimation [37,38] or by compiling large databases of previous disruptive discharge data [39,40] and training various machine learning techniques [41,42,43,44,45] on them, including the previously mentioned neural networks or random forests.…”

Section: The Disruption Event Characterization and Forecasting (Decafmentioning

confidence: 99%

Physics-guided machine learning approaches to predict the ideal stability properties of fusion plasmas

et al. 2020

View full text Add to dashboard Cite

One of the biggest challenges to achieve the goal of producing fusion energy in tokamak devices is the necessity of avoiding disruptions of the plasma current due to instabilities. The Disruption Event Characterization and Forecasting (DECAF) framework has been developed in this purpose, integrating physics models of many causal events that can lead to a disruption. Two different machine learning approaches are proposed to improve the ideal magnetohydrodynamic (MHD) no-wall limit component of the kinetic stability model included in DECAF. First, a random forest regressor (RFR), was adopted to reproduce the DCON computed change in plasma potential energy without wall effects, δW n=1 no−wall , for a large database of equilibria from the National Spherical Torus Experiment (NSTX). This tree-based method provides an analysis of the contribution of each input feature, giving an insight into the underlying physics phenomena. Secondly, a fully-connected neural network has been trained on sets of calculations with the DCON code, to get an improved closed form equation of the no-wall β limit as a function of the relevant plasma parameters indicated by the RFR. The neural network has been guided by physics theory of ideal MHD in its extension outside the domain of the NSTX experimental data. The estimated value of β n=1 N,no−wall has been incorporated into the DECAF kinetic stability model and tested against a set of experimentally stable and unstable discharges. Moreover, the neural network results were used to simulate a real-time stability assessment using only quantities available in real-time. Finally, the portability of the model was investigated, showing encouraging results by testing the NSTX-trained algorithm on the Mega Ampere Spherical Tokamak (MAST).

show abstract

“…Up to now, disruption prediction systems for mitigation have been widely proposed on existing tokamaks. Physics basis for disruption prediction and detection have been discussed in [6], [7]. Several contributions have been proposed in the literature, aimed to develop disruption predictions using supervised data-based methods in JET [8], [9], ASDEX Upgrade [10], [11], J-TEXT [12], and DIII-D [13], only to quote some of them.…”

Section: Introductionmentioning

confidence: 99%

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

et al. 2019

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

Requirements for Triggering the ITER Disruption Mitigation System

Cited by 46 publications

References 0 publications

Deep convolutional neural networks for multi-scale time-series classification and application to tokamak disruption prediction using raw, high temporal resolution diagnostic data

Deep convolutional neural networks for multi-scale time-series classification and application to tokamak disruption prediction using raw, high temporal resolution diagnostic data

Physics-guided machine learning approaches to predict the ideal stability properties of fusion plasmas

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

Contact Info

Product

Resources

About