Abstract | ||
---|---|---|
This article shows a conformal prediction application to disruption prediction from scratch. Considering data from ILW experimental campaigns both hydrogen and deuterium campaigns, a one-layer disruption predictor has been tested from scratch. The results show a relevant improvement where the success rate rate of disruptions predicted correctly increases and the false alarm rate rate of non-disruptive discharges misclassified decreases, using conformal prediction CP rather than conventional methodology from scratch. CP from scratch achieves a success rate of $$100\\,\\%$$ with the first model and only one disruptive discharge. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1007/978-3-319-33395-3_5 | COPA |
DocType | Citations | PageRank |
Conference | 0 | 0.34 |
References | Authors | |
1 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Raúl Moreno | 1 | 0 | 0.34 |
Jesús Vega | 2 | 0 | 1.35 |
Sebastián Dormido | 3 | 337 | 55.36 |