Accelerated version of NUBEAM capabilities in DIII-D using neural networks

Morosohk, Shira M.; Boyer, Mark D.; Schuster, Eugenio

doi:10.1016/j.fusengdes.2020.112125

Accelerated version of NUBEAM capabilities in DIII-D using neural networks

Journal Article · Tue Dec 08 23:00:00 EST 2020 · Fusion Engineering and Design

DOI:https://doi.org/10.1016/j.fusengdes.2020.112125· OSTI ID:1814847

Morosohk, Shira M. ^[1]; Boyer, Mark D. ^[2]; Schuster, Eugenio ^[1]

Lehigh Univ., Bethlehem, PA (United States)
Princeton Plasma Physics Lab. (PPPL), Princeton, NJ (United States)

A neural network model of the effects of neutral beam injection on DIII-D has been developed. The training and testing data used by the model have been generated by the NUBEAM module of TRANSP for experimental discharges from the 2018 DIII-D campaign. Using a principle component analysis to reduce the dimensionality of profile data, the model has been shown to reproduce the results of the Monte Carlo code NUBEAM with a high level of accuracy and an execution time orders of magnitude faster than the execution time of NUBEAM. Furthermore, this makes the neural network model uniquely suited to applications in model-based scenario planning (off-line) and active control (on-line), where a large number of simulation runs are required by the associated optimization tasks that need to be performed before and during the discharge.

Research Organization:: Princeton Plasma Physics Laboratory (PPPL), Princeton, NJ (United States)

Sponsoring Organization:: USDOE Office of Science (SC), Fusion Energy Sciences (FES)

Contributing Organization:: National Science Foundation (NSF)

Grant/Contract Number:: SC0010661

OSTI ID:: 1814847

Alternate ID(s):: OSTI ID: 23195020

Journal Information:: Fusion Engineering and Design, Journal Name: Fusion Engineering and Design Vol. 163; ISSN 0920-3796

Publisher:: ElsevierCopyright Statement

Country of Publication:: United States

Language:: English

References (9)

New techniques for calculating heat and particle source rates due to neutral beam injection in axisymmetric tokamaks Goldston, R. J.; McCune, D. C.; Towner, H. H. Journal of Computational Physics, Vol. 43, Issue 1 https://doi.org/10.1016/0021-9991(81)90111-X	journal	September 1981
Approximation capabilities of multilayer feedforward networks Hornik, Kurt Neural Networks, Vol. 4, Issue 2 https://doi.org/10.1016/0893-6080(91)90009-T	journal	January 1991
The tokamak Monte Carlo fast ion module NUBEAM in the National Transport Code Collaboration library Pankin, Alexei; McCune, Douglas; Andre, Robert Computer Physics Communications, Vol. 159, Issue 3 https://doi.org/10.1016/j.cpc.2003.11.002	journal	June 2004
Optimizing feedforward artificial neural network architecture Benardos, P. G.; Vosniakos, G. -C. Engineering Applications of Artificial Intelligence, Vol. 20, Issue 3 https://doi.org/10.1016/j.engappai.2006.06.005	journal	April 2007
Towards model-based current profile control at DIII-D Ou, Y.; Luce, T. C.; Schuster, E. Fusion Engineering and Design, Vol. 82, Issue 5-14 https://doi.org/10.1016/j.fusengdes.2007.04.016	journal	October 2007
Integrated current profile, normalized beta and NTM control in DIII-D Pajares, A.; Wehner, W. P.; Schuster, E. Fusion Engineering and Design, Vol. 146 https://doi.org/10.1016/j.fusengdes.2019.01.022	journal	September 2019
How Neural Networks Learn from Experience Hinton, Geoffrey E. Scientific American, Vol. 267, Issue 3 https://doi.org/10.1038/scientificamerican0992-144	journal	September 1992
Integrated modeling applications for tokamak experiments with OMFIT Meneghini, O.; Smith, S. P.; Lao, L. L. Nuclear Fusion, Vol. 55, Issue 8 https://doi.org/10.1088/0029-5515/55/8/083008	journal	July 2015
Feedback control of stored energy and rotation with variable beam energy and perveance on DIII-D Boyer, M. D.; Erickson, K. G.; Grierson, B. A. Nuclear Fusion, Vol. 59, Issue 7 https://doi.org/10.1088/1741-4326/ab17f5	journal	May 2019

Similar Records

Real-time capable modeling of neutral beam injection on NSTX-U using neural networks

Dataset · Thu Jan 31 23:00:00 EST 2019 · OSTI ID:1562069

Real-time capable modeling of neutral beam injection on NSTX-U using neural networks

Journal Article · Fri Mar 22 00:00:00 EDT 2019 · Nuclear Fusion · OSTI ID:1503000

Neural network model of neutral beam injection in the EAST tokamak to enable fast transport simulations

Journal Article · Sun Feb 12 23:00:00 EST 2023 · Fusion Engineering and Design · OSTI ID:1974424

Related Subjects

70 PLASMA PHYSICS AND FUSION TECHNOLOGY
Machine learning
NUBEAM
Neural networks

Accelerated version of NUBEAM capabilities in DIII-D using neural networks

Citation Formats

References (9)

Similar Records

Related Subjects