Semi-supervised deep networks for plasma state identification

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61389021%3A_____%2F22%3A00564063" target="_blank" >RIV/61389021:_____/22:00564063 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/68407700:21230/22:00362328 RIV/68407700:21340/22:00362328

Výsledek na webu

<a href="https://iopscience.iop.org/article/10.1088/1361-6587/ac9926" target="_blank" >https://iopscience.iop.org/article/10.1088/1361-6587/ac9926</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1088/1361-6587/ac9926" target="_blank" >10.1088/1361-6587/ac9926</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Semi-supervised deep networks for plasma state identification

Popis výsledku v původním jazyce

Correct and timely detection of plasma confinement regimes and edge localized modes (ELMs) is important for improving the operation of tokamaks. Existing machine learning approaches detect these regimes as a form of post-processing of experimental data. Moreover, they are typically trained on a large dataset of tens of labeled discharges, which may be costly to build. We investigate the ability of current machine learning approaches to detect the confinement regime and ELMs with the smallest possible delay after the latest measurement. We also demonstrate that including unlabeled data into the training process can improve the results in a situation where only a limited set of reliable labels is available. All training and validation is performed on data from the COMPASS tokamak. The InceptionTime architecture trained using a semi-supervised approach was found to be the most accurate method based on the set of tested variants. It is able to achieve good overall accuracy of the regime classification at the time instant of 100 mu s delayed behind the latest data record. We also evaluate the capability of the model to correctly predict class transitions. While ELM occurrence can be detected with a tolerance smaller than 50 mu s, detection of the confinement regime transition is more demanding and it was successful with 2 ms tolerance. Sensitivity studies to different values of model parameters are provided. We believe that the achieved accuracy is acceptable in practice and the method could be used in real-time operation.

Název v anglickém jazyce

Semi-supervised deep networks for plasma state identification

Popis výsledku anglicky

Correct and timely detection of plasma confinement regimes and edge localized modes (ELMs) is important for improving the operation of tokamaks. Existing machine learning approaches detect these regimes as a form of post-processing of experimental data. Moreover, they are typically trained on a large dataset of tens of labeled discharges, which may be costly to build. We investigate the ability of current machine learning approaches to detect the confinement regime and ELMs with the smallest possible delay after the latest measurement. We also demonstrate that including unlabeled data into the training process can improve the results in a situation where only a limited set of reliable labels is available. All training and validation is performed on data from the COMPASS tokamak. The InceptionTime architecture trained using a semi-supervised approach was found to be the most accurate method based on the set of tested variants. It is able to achieve good overall accuracy of the regime classification at the time instant of 100 mu s delayed behind the latest data record. We also evaluate the capability of the model to correctly predict class transitions. While ELM occurrence can be detected with a tolerance smaller than 50 mu s, detection of the confinement regime transition is more demanding and it was successful with 2 ms tolerance. Sensitivity studies to different values of model parameters are provided. We believe that the achieved accuracy is acceptable in practice and the method could be used in real-time operation.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10305 - Fluids and plasma physics (including surface physics)

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2022

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Plasma Physics and Controlled Fusion

ISSN

0741-3335

e-ISSN

1361-6587

Svazek periodika

64

Číslo periodika v rámci svazku

12

Stát vydavatele periodika

GB - Spojené království Velké Británie a Severního Irska

Počet stran výsledku

16

Strana od-do

125004

Kód UT WoS článku

000876069600001

EID výsledku v databázi Scopus

2-s2.0-85141293718