Data-driven profile prediction for DIII-D

被引：28

作者：

Abbate, J. ^{[1
,2
]}

Conlin, R. ^{[2
,3
]}

Kolemen, E. ^{[2
,3
]}

机构：

[1] Princeton Univ, Dept Astrophys Sci, Princeton, NJ 08544 USA

[2] Princeton Plasma Phys Lab, Princeton, NJ 08543 USA

[3] Princeton Univ, Dept Mech & Aerosp Engn, Princeton, NJ 08544 USA

来源：

NUCLEAR FUSION | 2021年 / 61卷 / 04期

关键词：

DIII-D; neural networks; transport; control; TRANSPORT; DISRUPTIONS;

D O I：

10.1088/1741-4326/abe08d

中图分类号：

O35 [流体力学]; O53 [等离子体物理学];

学科分类号：

070204 ; 080103 ; 080704 ;

摘要：

A new, fully data-driven algorithm has been developed that uses a neural network to predict plasma profiles on a scale of tau(E) into the future given an actuator trajectory and the plasma state history. The model was trained and tested on DIII-D data from the 2013-2018 experimental campaigns. The model runs in tens of milliseconds and is very simple to use. This makes it a potentially useful tool for operators and physicists when planning plasma scenarios. It is also fast enough to be used for real-time model-predictive control.

引用

页数：12

共 50 条

[1]

[Anonymous], 2016, P 4 INT C LEARN REPR

[2]

[Anonymous], 2010, ICML

[3] Metis: a fast integrated tokamak modelling tool for scenario design [J].

Artaud, J. F. ;

Imbeaux, F. ;

Garcia, J. ;

Giruzzi, G. ;

Aniel, T. ;

Basiuk, V ;

Becoulet, A. ;

Bourdelle, C. ;

Buravand, Y. ;

Decker, J. ;

Dumont, R. ;

Eriksson, L. G. ;

Garbet, X. ;

Guirlet, R. ;

Hoang, G. T. ;

Huynh, P. ;

Joffrin, E. ;

Litaudon, X. ;

Maget, P. ;

Moreau, D. ;

Nouailletas, R. ;

Pegourie, B. ;

Peysson, Y. ;

Schneide, M. ;

Urban, J. .

NUCLEAR FUSION, 2018, 58 (10)

[4] Gyrokinetic simulation of global and local Alfven eigenmodes driven by energetic particles in a DIII-D discharge [J].

Bass, E. M. ;

Waltz, R. E. .

PHYSICS OF PLASMAS, 2013, 20 (01)

[5] Real-time capable modeling of neutral beam injection on NSTX-U using neural networks [J].

Boyer, M. D. ;

Kaye, S. ;

Erickson, K. .

NUCLEAR FUSION, 2019, 59 (05)

[6] A prediction tool for real-time application in the disruption protection system at JET [J].

Cannas, B. ;

Fanni, A. ;

Sonato, P. ;

Zedda, M. K. .

NUCLEAR FUSION, 2007, 47 (11) :1559-1569

[7]

Cenacchi G., 1988, JETTO FREE BOUNDARY, V84

[8] NON-INDUCTIVELY DRIVEN CURRENTS IN JET [J].

CHALLIS, CD ;

CORDEY, JG ;

HAMNEN, H ;

STUBBERFIELD, PM ;

CHRISTIANSEN, JP ;

LAZZARO, E ;

MUIR, DG ;

STORK, D ;

THOMPSON, E .

NUCLEAR FUSION, 1989, 29 (04) :563-570

[9] Comparison between measured and predicted turbulence frequency spectra in ITG and TEM regimes [J].

Citrin, J. ;

Arnichand, H. ;

Bernardo, J. ;

Bourdelle, C. ;

Garbet, X. ;

Jenko, F. ;

Hacquin, S. ;

Pueschel, M. J. ;

Sabot, R. .

PLASMA PHYSICS AND CONTROLLED FUSION, 2017, 59 (06)

[10]

Duchi J, 2011, J MACH LEARN RES, V12, P2121

← 1 2 3 4 5 →