Disruption prediction with artificial intelligence techniques in tokamak plasmas

J Vega, A Murari, S Dormido-Canto, GA Rattá… - Nature Physics, 2022 - nature.com
In nuclear fusion reactors, plasmas are heated to very high temperatures of more than 100
million kelvin and, in so-called tokamaks, they are confined by magnetic fields in the shape …

A control oriented strategy of disruption prediction to avoid the configuration collapse of tokamak reactors

A Murari, R Rossi, T Craciunescu, J Vega… - Nature …, 2024 - nature.com
The objective of thermonuclear fusion consists of producing electricity from the coalescence
of light nuclei in high temperature plasmas. The most promising route to fusion envisages …

Disruption prediction for future tokamaks using parameter-based transfer learning

W Zheng, F Xue, Z Chen, D Chen, B Guo… - Communications …, 2023 - nature.com
Tokamaks are the most promising way for nuclear fusion reactors. Disruption in tokamaks is
a violent event that terminates a confined plasma and causes unacceptable damage to the …

Disruption prediction on EAST tokamak using a deep learning algorithm

BH Guo, DL Chen, B Shen, C Rea… - Plasma Physics and …, 2021 - iopscience.iop.org
In this study, a long short-term memory (LSTM) model is trained on a large disruption
warning database to predict the disruption on EAST tokomak. To compare the performance …

All superconducting tokamak: EAST

J Hu, W **, J Zhang, L Huang, D Yao, Q Zang, Y Hu… - AAPPS Bulletin, 2023 - Springer
Abstract Experimental Advanced Superconducting Tokamak (EAST) was built to
demonstrate high-power, long-pulse operations under fusion-relevant conditions, with major …

Real-time prediction of high-density EAST disruptions using random forest

WH Hu, C Rea, QP Yuan, KG Erickson, DL Chen… - Nuclear …, 2021 - iopscience.iop.org
A real-time disruption predictor using random forest was developed for high-density
disruptions and used in the plasma control system (PCS) of the EAST tokamak for the first …

Disruption prediction on EAST with different wall conditions based on a multi-scale deep hybrid neural network

BH Guo, DL Chen, C Rea, MQ Wu, B Shen… - Nuclear …, 2023 - iopscience.iop.org
Plasma disruption is a very dangerous event for future tokamaks and fusion reactors.
Therefore, predicting disruption is crucial for ensuring the safety and performance of …

Alfvén eigenmode classification based on ECE diagnostics at DIII-D using deep recurrent neural networks

A Jalalvand, AA Kaptanoglu, AV Garcia… - Nuclear …, 2021 - iopscience.iop.org
Modern tokamaks have achieved significant fusion production, but further progress towards
steady-state operation has been stymied by a host of kinetic and MHD instabilities. Control …

Performance comparison of machine learning disruption predictors at JET

E Aymerich, B Cannas, F Pisano, G Sias, C Sozzi… - Applied Sciences, 2023 - mdpi.com
Reliable disruption prediction (DP) and disruption mitigation systems are considered
unavoidable during international thermonuclear experimental reactor (ITER) operations and …

Real-time disruption prediction in multi-dimensional spaces leveraging diagnostic information not available at execution time

J Vega, S Dormido-Canto, R Castro… - Nuclear …, 2024 - iopscience.iop.org
This article describes the use of privileged information to train supervised classifiers, applied
for the first time to the prediction of disruptions in tokamaks. The objective consists of making …