FusionPapers
図版検索トレンドwiki日本の研究
© 2026 FUSIONPAPERS
About法務情報
トップに戻る

Experiment data-driven modeling of tokamak discharge in EAST

Chenguang Wan, Zhi Yu, Feng Wang, Xiaojuan Liu, Jiangang Li2021年被引用 12Nuclear FusionIF 3出版社

A neural network model of tokamak discharge is developed based on the experimental dataset of a superconducting long-pulse tokamak (EAST) campaign 2016–2018. The purpose is to reproduce the response of diagnostic signals to actuator signals without introducing additional physical models. In the present work, the discharge curves of electron density ne, stored energy Wmhd, and loop voltage Vloop were reproduced from a series of actuator signals. For ne and Wmhd, the average similarity between the modeling results and the experimental data achieve 89% and 97%, respectively. The promising results demonstrate that the data-driven methodology provides an alternative to the physical-driven methodology for tokamak discharge modeling. The method presented in the manuscript has the potential of being used for validating the tokamak's experimental proposals, which could advance and optimize experimental planning and validation.

日本語訳

トカマク放電のニューラルネットワークモデルを、超伝導長パルストカマク(EAST)の2016年から2018年までの実験データセットに基づいて構築した。その目的は、追加の物理モデルを導入することなく、アクチュエータ信号に対する診断信号の応答を再現することである。本研究では、一連のアクチュエータ信号から、電子密度ne、蓄積エネルギーWmhd、ループ電圧Vloopの放電曲線を再現した。neおよびWmhdについては、モデリング結果と実験データの平均類似度はそれぞれ89%および97%に達した。これらの有望な結果は、データ駆動型手法がトカマク放電モデリングにおける物理駆動型手法の代替手段を提供することを示している。本稿で提示した手法は、トカマクの実験提案の検証に利用できる可能性があり、実験計画と検証の最適化を促進し得る。

装置

east高精度(タイトル一致)

wiki

EAST
この論文にはまだAI要約がありません。

関連論文

EAST discharge prediction without integrating simulation results

2022Nuclear Fusion

Advances in prediction of tokamak experiments with theory-based models

2022Nuclear Fusion

Experimental advanced superconducting tokamak ohmic discharge simulation by the tokamak simulation code

2012Plasma Physics and Controlled Fusion

Problems and methods of self-consistent reconstruction of tokamak equilibrium profiles from magnetic and polarimetric measurements

1990Nuclear Fusion

The modeling of a tokamak plasma discharge, from first principles to a flight simulator

2022Plasma Physics and Controlled Fusion

The International Multi-Tokamak Profile Database

2000Nuclear Fusion

Models for the development of the discharge in a tokamak

1983Nuclear Fusion

Machine learning prediction of plasma behavior from discharge configurations on WEST

2026Nuclear Fusion

Time series extrinsic regression for reconstructing missing electron temperature in tokamak

2025Nuclear Fusion

Cross-tokamak disruption prediction based on domain adaptation

2024Nuclear Fusion