Feature extraction for improved disruption prediction analysis at JET
- 1 October 2008
- journal article
- research article
- Published by AIP Publishing in Review of Scientific Instruments
- Vol. 79 (10), 10F328
- https://doi.org/10.1063/1.2965020
Abstract
Disruptions are major instabilities and remain one of the main problems in tokomaks. Using Joint European Torus database, a disruption predictor is developed by computational methods including supervised learning techniques. The main objectives of the work are to develop accurate automatic classifiers, to test their performances, and to determine how much in advance of the disruption they can operate with acceptable reliability.This publication has 4 references indexed in Scilit:
- Prototype of an adaptive disruption predictor for JET based on fuzzy logic and regression treesNuclear Fusion, 2008
- Support vector machines for disruption prediction and novelty detection at JETFusion Engineering and Design, 2007
- Automatic disruption classification at JET: comparison of different pattern recognition techniquesNuclear Fusion, 2006
- Support-vector networksMachine Learning, 1995