2016
DOI: 10.13182/fst15-176
|View full text |Cite
|
Sign up to set email alerts
|

Requirements for Triggering the ITER Disruption Mitigation System

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
38
0

Year Published

2019
2019
2025
2025

Publication Types

Select...
7
1

Relationship

0
8

Authors

Journals

citations
Cited by 46 publications
(38 citation statements)
references
References 0 publications
0
38
0
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%
See 2 more Smart Citations
“…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%
See 1 more Smart Citation
“…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%
“…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%