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.
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: