1
|
Sarancha G, Ammosov Y, Balashov A, Butrova N, Krokhalev O, Loginov A, Melnikov A, Popova M, Stepin A, Stolbov A, Svoboda V, Suntsov S, Timkovskiy G. Remote Plasma Physics Research and Teaching by Example of Turbulence Study at the University-Scale Tokamak GOLEM. FUSION SCIENCE AND TECHNOLOGY 2023. [DOI: 10.1080/15361055.2022.2148842] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 02/12/2023]
Affiliation(s)
- G. Sarancha
- National Research Center “Kurchatov Institute,” Moscow, Russia
- Moscow Institute of Physics and Technology (National Research University), Dolgoprudny, Russia
| | - Ya. Ammosov
- National Research Center “Kurchatov Institute,” Moscow, Russia
- Moscow Institute of Physics and Technology (National Research University), Dolgoprudny, Russia
- RUDN University, Moscow, Russia
| | - A. Balashov
- National Research Center “Kurchatov Institute,” Moscow, Russia
| | - N. Butrova
- National Research Nuclear University MЕPhI, Moscow, Russia
| | - O. Krokhalev
- National Research Center “Kurchatov Institute,” Moscow, Russia
- Moscow Institute of Physics and Technology (National Research University), Dolgoprudny, Russia
| | - A. Loginov
- Moscow Institute of Physics and Technology (National Research University), Dolgoprudny, Russia
| | - A. Melnikov
- National Research Center “Kurchatov Institute,” Moscow, Russia
- Moscow Institute of Physics and Technology (National Research University), Dolgoprudny, Russia
- National Research Nuclear University MЕPhI, Moscow, Russia
| | | | - A. Stepin
- National Research Center “Kurchatov Institute,” Moscow, Russia
| | - A. Stolbov
- National Research Nuclear University MЕPhI, Moscow, Russia
| | - V. Svoboda
- Czech Technical University in Prague, Prague, Czech Republic
| | - S. Suntsov
- National Research Center “Kurchatov Institute,” Moscow, Russia
- National Research Nuclear University MЕPhI, Moscow, Russia
| | - G. Timkovskiy
- National Research Nuclear University MЕPhI, Moscow, Russia
| | | |
Collapse
|
2
|
Krat S, Prishvitsyn A, Alieva A, Efimov N, Vinitskiy E, Ulasevich D, Izarova A, Podolyako F, Belov A, Meshcheryakov A, Ongena J, Kharchev N, Chernenko A, Khayrutdinov R, Lukash V, Sinelnikov D, Bulgadaryan D, Sorokin I, Gubskiy K, Kaziev A, Kolodko D, Tumarkin V, Isakova A, Grunin A, Begrambekov L, Voskoboinikov R, Melnikov A. MEPhIST-0 Tokamak for Education and Research. FUSION SCIENCE AND TECHNOLOGY 2023. [DOI: 10.1080/15361055.2022.2149033] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/27/2023]
Affiliation(s)
- S. Krat
- National Research Nuclear University MEPhI, Moscow, Russia
| | - A. Prishvitsyn
- National Research Nuclear University MEPhI, Moscow, Russia
| | - A. Alieva
- National Research Nuclear University MEPhI, Moscow, Russia
| | - N. Efimov
- National Research Nuclear University MEPhI, Moscow, Russia
| | - E. Vinitskiy
- National Research Nuclear University MEPhI, Moscow, Russia
| | - D. Ulasevich
- National Research Nuclear University MEPhI, Moscow, Russia
- National Research Center, Kurchatov Institute, Moscow, Russia
| | - A. Izarova
- National Research Nuclear University MEPhI, Moscow, Russia
| | - F. Podolyako
- National Research Nuclear University MEPhI, Moscow, Russia
| | - A. Belov
- National Research Nuclear University MEPhI, Moscow, Russia
| | | | - J. Ongena
- Koninklijke Militaire School—Ecole Royale Militaire, Brussels, Belgium
| | - N. Kharchev
- National Research Center, Kurchatov Institute, Moscow, Russia
| | - A. Chernenko
- National Research Nuclear University MEPhI, Moscow, Russia
- National Research Center, Kurchatov Institute, Moscow, Russia
| | - R. Khayrutdinov
- National Research Center, Kurchatov Institute, Moscow, Russia
| | - V. Lukash
- National Research Center, Kurchatov Institute, Moscow, Russia
| | - D. Sinelnikov
- National Research Nuclear University MEPhI, Moscow, Russia
| | - D. Bulgadaryan
- National Research Nuclear University MEPhI, Moscow, Russia
| | - I. Sorokin
- National Research Nuclear University MEPhI, Moscow, Russia
- Russian Academy of Sciences, Kotel’nikov Institute of Radio Engineering and Electronics, Fryazino Branch, Fryazino, Russia
| | - K. Gubskiy
- National Research Nuclear University MEPhI, Moscow, Russia
| | - A. Kaziev
- National Research Nuclear University MEPhI, Moscow, Russia
| | - D. Kolodko
- National Research Nuclear University MEPhI, Moscow, Russia
- Russian Academy of Sciences, Kotel’nikov Institute of Radio Engineering and Electronics, Fryazino Branch, Fryazino, Russia
| | - V. Tumarkin
- National Research Nuclear University MEPhI, Moscow, Russia
| | - A. Isakova
- National Research Nuclear University MEPhI, Moscow, Russia
| | - A. Grunin
- National Research Nuclear University MEPhI, Moscow, Russia
| | - L. Begrambekov
- National Research Nuclear University MEPhI, Moscow, Russia
| | - R. Voskoboinikov
- Budker Institute of Nuclear Physics of the Siberian Branch of the RAS, Novosibirsk, Russia
| | - A. Melnikov
- National Research Nuclear University MEPhI, Moscow, Russia
- National Research Center, Kurchatov Institute, Moscow, Russia
- Moscow Institute of Physics and Technology, Dolgoprudny, Russia
| |
Collapse
|
3
|
Chandrasekaran J, Jayaraman S. Magnetohydrodynamic Mode Identification for Golem Mirnov Coil Signals Using Singular Value Decomposition and Multichannel Variational Mode Decomposition Method for Analyzing Time–Frequency. JOURNAL OF FUSION ENERGY 2022. [DOI: 10.1007/s10894-022-00329-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/29/2022]
|
4
|
Chandrasekaran J, Jayaraman S. Data-driven technique for disruption prediction in GOLEM tokamak using stacked ensembles with active learning. THE REVIEW OF SCIENTIFIC INSTRUMENTS 2022; 93:033501. [PMID: 35364999 DOI: 10.1063/5.0061460] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/26/2021] [Accepted: 02/04/2022] [Indexed: 06/14/2023]
Abstract
In a tokamak, disruption is defined as losing control over a confined plasma resulting in sudden extinction of the plasma current. Machine learning offers potent solutions to classify plasma discharges into disruptive and non-disruptive classes. Evolving experimental programs reduce the performance of machine learning models, and also, the need for labeling the huge volume of data incurs more labor cost and time. This paper proposes a data-driven based machine learning technique that employs an active learning approach for labeling and classification of plasma discharges. The designed model uses 117 normally terminated shots and 70 disruptive shots with 14 labeled diagnostic signals. The stacking classifier is built over three base learners: logistic regression, reduced error pruning tree, and categorial boost algorithm, and the logistic regression technique is used at the meta-learner. An active learning approach is proposed for labeling the unlabeled dataset using a modified uncertainty sampling technique with minimal queries. The proposed model queries the unlabeled data to an oracle based on a selection strategy with uncertainty sampling using entropy metrics. The new labeled data and the class probabilities of the base classifiers are channeled to the final predictor for classifying the plasma discharge. The proposed model achieves an accuracy of 98.75% in classifying the disruptive vs non-disruptive discharges, with a minimally trained dataset, and also, it is free from aging of predictors.
Collapse
Affiliation(s)
- Jayakumar Chandrasekaran
- School of Computing, SASTRA Deemed to be University, Tirumalaisamudram, Thanjavur 613401, Tamilnadu, India
| | - Sangeetha Jayaraman
- Department of Computer Science and Engineering, Srinivasa Ramanujan Center, SASTRA Deemed to be University, Kumbakonam 612001, Tamilnadu, India
| |
Collapse
|
5
|
Chandrasekar J, Madhawa S, Sangeetha J. Data-driven disruption prediction in GOLEM Tokamak using ensemble classifiers. JOURNAL OF INTELLIGENT & FUZZY SYSTEMS 2020. [DOI: 10.3233/jifs-189155] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022]
Abstract
A robust disruption prediction system is mandatory in a Tokamak control system as the disruption can cause malfunctioning of the plasma-facing components and impair irrecoverable structural damage to the vessel. To mitigate the disruption, in this article, a data-driven based disruption predictor is developed using an ensemble technique. The ensemble algorithm classifies disruptive and non-disruptive discharges in the GOLEM Tokamak system. Ensemble classifiers combine the predictive capacity of several weak learners to produce a single predictive model and are utilized both in supervised and unsupervised learning. The resulting final model reduces the bias, minimizes variance and is unlikely to over-fit when compared to the individual model from a single algorithm. In this paper, popular ensemble techniques such as Bagging, Boosting, Voting, and Stacking are employed on the time-series Tokamak dataset, which consists of 117 normal and 70 disruptive shots. Stacking ensemble with REPTree (Reduced Error Pruning Tree) as a base learner and Multi-response Linear Regression as meta learner produced better results in comparison to other ensembles. A comparison with the widely employed stand-alone machine learning algorithms and ensemble algorithms are illustrated. The results show the excellent performance of the Stacking model with an F1 score of 0.973. The developed predictive model would be capable of warning the human operator with feedback about the feature(s) causing the disruption.
Collapse
Affiliation(s)
- Jayakumar Chandrasekar
- School of Computing, SASTRA Deemed University, Thirumalaisamudram, Thanjavur, Tamilnadu, India
| | - Surendar Madhawa
- School of Computing, SASTRA Deemed University, Thirumalaisamudram, Thanjavur, Tamilnadu, India
| | - J. Sangeetha
- School of Computing, SASTRA Deemed University, Thirumalaisamudram, Thanjavur, Tamilnadu, India
| |
Collapse
|
6
|
Tokunaga S, Moreau P, Signoret J, Imbeaux F, Tsitrone E, Loarer T, Salmon T, Hutter T, Giruzzi G, Joffrin E, De Tommasi G, Sartori F, Farthing J, Nakanishi H, Ozeki T, Asakura N, Sakamoto Y, Ohtsu H, Sugie Y, Suzuki S, Fukuda M, Nakano T, Sano R, Ishii Y, Clement-Lorenzo S, Nakajima N. Remote experiment with WEST from ITER Remote Experimentation Centre. FUSION ENGINEERING AND DESIGN 2020. [DOI: 10.1016/j.fusengdes.2020.111554] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/25/2022]
|
7
|
|
8
|
|
9
|
Development of 3D ferromagnetic model of tokamak core with strong toroidal asymmetry. FUSION ENGINEERING AND DESIGN 2015. [DOI: 10.1016/j.fusengdes.2015.03.041] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/21/2022]
|
10
|
Svoboda V, Kocman J, Grover O, Krbec J, Stöckel J. Remote operation of the vertical plasma stabilization @ the GOLEM tokamak for the plasma physics education. FUSION ENGINEERING AND DESIGN 2015. [DOI: 10.1016/j.fusengdes.2015.06.044] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
|
11
|
A GPU-based real time high performance computing service in a fast plant system controller prototype for ITER. FUSION ENGINEERING AND DESIGN 2012. [DOI: 10.1016/j.fusengdes.2012.05.008] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 10/28/2022]
|
12
|
Odstrcil T, Odstrcil M, Grover O, Svoboda V, Duran I, Mlynár J. Low cost alternative of high speed visible light camera for tokamak experiments. THE REVIEW OF SCIENTIFIC INSTRUMENTS 2012; 83:10E505. [PMID: 23127012 DOI: 10.1063/1.4731003] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/01/2023]
Abstract
We present design, analysis, and performance evaluation of a new, low cost and high speed visible-light camera diagnostic system for tokamak experiments. The system is based on the camera Casio EX-F1, with the overall price of approximately a thousand USD. The achieved temporal resolution is up to 40 kHz. This new diagnostic was successfully implemented and tested at the university tokamak GOLEM (R = 0.4 m, a = 0.085 m, B(T) < 0.5 T, I(p) < 4 kA). One possible application of this new diagnostic at GOLEM is discussed in detail. This application is tomographic reconstruction for estimation of plasma position and emissivity.
Collapse
Affiliation(s)
- T Odstrcil
- Czech Technical University in Prague, FNSPE, Praha 1, Czech Republic
| | | | | | | | | | | |
Collapse
|