Interpretability analysis and real-time prediction of locked mode-induced disruptions in EAST
- 26 June 2025
- journal article
- Published by IOP Publishing in Plasma Physics and Controlled Fusion
- Vol. 67 (7) , 075013
Abstract
Locked mode-induced disruptions (LMiDs) are investigated using an interpretable machine learning approach in EAST. The experimental data of LM come from error field penetration experiments conducted between 2015 and 2022. Decision tree ensembles, known for their strong interpretability and accuracy, were selected as the machine learning algorithm to analyze and predict LMiDs. Two prediction models were developed: an interpretable predictor and a real-time predictor. The interpretable predictor, which employs physics-guided feature extraction, achieved exceptional performance on the test set (AUC = 0.997). This model identified the distance between the outer boundary of the magnetic island and the last closed surface of the plasma, denoted as d edge , as the most important feature for LMiDs. Other important features include stored energy W MHD , radial force V loop × B p , total heating power P total , toroidal magnetic fields B t , internal inductance l i and electron temperature T e . The real-time predictor achieved 94% successful alarm rate with an average alarm time of 137 ms at 10% false alarm rate, demonstrating robustness against measurement uncertainties. An analysis of a typical LMiD discharge confirmed the model’s ability to identify critical parameter thresholds preceding disruptions.Keywords
Funding Information
- Chinese Academy of Sciences (No. XDB0790100)
- National Natural Science Foundation of China (12105323)
- Natural Science Foundation of Anhui Province (2208085J39)
- National Magnetic Confinement Fusion Program of China (2024YFE03010000)
This publication has 51 references indexed in Scilit:
- MHD spectrogram contribution to disruption prediction using Convolutional Neural NetworksFusion Engineering and Design, 2024
- ITER DMS fast shutter development and laboratory testingFusion Engineering and Design, 2024
- Locked mode detection during error field identification studiesFusion Engineering and Design, 2023
- CNN disruption predictor at JET: Early versus late data fusion approachFusion Engineering and Design, 2023
- Disruption prediction with artificial intelligence techniques in tokamak plasmasNature Physics, 2022
- Predicting disruptive instabilities in controlled fusion plasmas through deep learningNature, 2019
- A locked mode indicator for disruption prediction on JET and ASDEX upgradeFusion Engineering and Design, 2019
- Classification and regression treesNature Methods, 2017
- Global optimization driven by genetic algorithms for disruption predictors based on APODIS architectureFusion Engineering and Design, 2016
- Disruptions in ITER and strategies for their control and mitigationJournal of Nuclear Materials, 2015