MHD mode tracking using high-speed cameras and deep learning

Wei, Y.; Levesque, J. P.; Hansen, C.; Mauel, M. E.; Navratil, G. A.

doi:10.1088/1361-6587/acd581

MHD mode tracking using high-speed cameras and deep learning

Journal Article · Tue May 30 00:00:00 EDT 2023 · Plasma Physics and Controlled Fusion

DOI:https://doi.org/10.1088/1361-6587/acd581· OSTI ID:2325440

; ; ; ;

Abstract

We present a new algorithm to track the amplitude and phase of rotating magnetohydrodynamic (MHD) modes in tokamak plasmas using high speed imaging cameras and deep learning. This algorithm uses a convolutional neural network (CNN) to predict the amplitudes of the n = 1 sine and cosine mode components using solely optical measurements from one or more cameras. The model was trained and tested on an experimental dataset consisting of camera frame images and magnetic-based mode measurements from the High Beta Tokamak - Extended Pulse (HBT-EP) device, and it outperformed other, more conventional, algorithms using identical image inputs. The effect of different input data streams on the accuracy of the model’s predictions is also explored, including using a temporal frame stack or images from two cameras viewing different toroidal regions.

View Journal Article

Research Organization:: Columbia Univ., New York, NY (United States); Univ. of Washington, Seattle, WA (United States)

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

Grant/Contract Number:: FG02-86ER53222; SC0021325

OSTI ID:: 2325440

Alternate ID(s):: OSTI ID: 2419319
OSTI ID: 1973719

Journal Information:: Plasma Physics and Controlled Fusion, Journal Name: Plasma Physics and Controlled Fusion Journal Issue: 7 Vol. 65; ISSN 0741-3335

Publisher:: IOP PublishingCopyright Statement

Country of Publication:: United Kingdom

Language:: English

References (41)

An optical-input Maximum Likelihood Estimation feedback system demonstrated on tokamak horizontal equilibrium control Chandra, Rian; Levesque, Jeffrey; Wei, Yumou Fusion Engineering and Design, Vol. 191 https://doi.org/10.1016/j.fusengdes.2023.113565	journal	June 2023
Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) network Sherstinsky, Alex Physica D: Nonlinear Phenomena, Vol. 404 https://doi.org/10.1016/j.physd.2019.132306	journal	March 2020
Encoder–decoder neural network for solving the nonlinear Fokker–Planck–Landau collision operator in XGC Miller, M. A.; Churchill, R. M.; Dener, A. Journal of Plasma Physics, Vol. 87, Issue 2 https://doi.org/10.1017/S0022377821000155	journal	March 2021
Deep learning LeCun, Yann; Bengio, Yoshua; Hinton, Geoffrey Nature, Vol. 521, Issue 7553 https://doi.org/10.1038/nature14539	journal	May 2015
Predicting disruptive instabilities in controlled fusion plasmas through deep learning Kates-Harbeck, Julian; Svyatkovskiy, Alexey; Tang, William Nature, Vol. 568, Issue 7753 https://doi.org/10.1038/s41586-019-1116-4	journal	April 2019
Magnetic control of tokamak plasmas through deep reinforcement learning Degrave, Jonas; Felici, Federico; Buchli, Jonas Nature, Vol. 602, Issue 7897 https://doi.org/10.1038/s41586-021-04301-9	journal	February 2022
Tracking blobs in the turbulent edge plasma of a tokamak fusion device Han, Woonghee; Pietersen, Randall A.; Villamor-Lora, Rafael Scientific Reports, Vol. 12, Issue 1 https://doi.org/10.1038/s41598-022-21671-w	journal	October 2022
Automatic heterogeneous quantization of deep neural networks for low-latency inference on the edge for particle detectors Coelho, Claudionor N.; Kuusela, Aki; Li, Shan Nature Machine Intelligence, Vol. 3, Issue 8 https://doi.org/10.1038/s42256-021-00356-5	journal	June 2021
A Kalman filter for feedback control of rotating external kink instabilities in the presence of noise Hanson, Jeremy M.; De Bono, Bryan; Levesque, Jeffrey P. Physics of Plasmas, Vol. 16, Issue 5 https://doi.org/10.1063/1.3110110	journal	May 2009
Fast, multi-channel real-time processing of signals with microsecond latency using graphics processing units Rath, N.; Kato, S.; Levesque, J. P. Review of Scientific Instruments, Vol. 85, Issue 4 https://doi.org/10.1063/1.4870901	journal	April 2014
Characterizing magnetized plasmas with dynamic mode decomposition Kaptanoglu, A. A.; Morgan, K. D.; Hansen, C. J. Physics of Plasmas, Vol. 27, Issue 3 https://doi.org/10.1063/1.5138932	journal	March 2020
Feedback control of tearing modes via modulated neutral beams Sen, A. K.; Singh, R.; Sen, A. Physics of Plasmas, Vol. 4, Issue 9 https://doi.org/10.1063/1.872463	journal	September 1997
Deep learning for Gaussian process soft x-ray tomography model selection in the ASDEX Upgrade tokamak Matos, F.; Svensson, J.; Pavone, A. Review of Scientific Instruments, Vol. 91, Issue 10 https://doi.org/10.1063/5.0020680	journal	October 2020
Deep Learning for the Analysis of Disruption Precursors Based on Plasma Tomography Ferreira, Diogo R.; Carvalho, Pedro J.; Sozzi, Carlo Fusion Science and Technology, Vol. 76, Issue 8 https://doi.org/10.1080/15361055.2020.1820749	journal	November 2020
State-of-the-art neoclassical tearing mode control in DIII-D using real-time steerable electron cyclotron current drive launchers Kolemen, E.; Welander, A. S.; La Haye, R. J. Nuclear Fusion, Vol. 54, Issue 7 https://doi.org/10.1088/0029-5515/54/7/073020	journal	May 2014
Diagnostics and control for the steady state and pulsed tokamak DEMO Orsitto, F. P.; Villari, R.; Moro, F. Nuclear Fusion, Vol. 56, Issue 2 https://doi.org/10.1088/0029-5515/56/2/026009	journal	January 2016
Stabilization of the external kink and the resistive wall mode Chu, M. S.; Okabayashi, M. Plasma Physics and Controlled Fusion, Vol. 52, Issue 12 https://doi.org/10.1088/0741-3335/52/12/123001	journal	October 2010
Adaptive control of rotating magnetic perturbations in HBT-EP using GPU processing Rath, N.; Angelini, S.; Bialek, J. Plasma Physics and Controlled Fusion, Vol. 55, Issue 8 https://doi.org/10.1088/0741-3335/55/8/084003	journal	June 2013
High-Speed imaging of the plasma response to resonant magnetic perturbations in HBT-EP Angelini, Sarah M.; Levesque, Jeffrey P.; Mauel, Michael E. Plasma Physics and Controlled Fusion, Vol. 57, Issue 4 https://doi.org/10.1088/0741-3335/57/4/045008	journal	March 2015
Improved feedback control of wall stabilized kink modes with different plasma–wall couplings and mode rotation Peng, Q.; Levesque, J. P.; Stoafer, C. C. Plasma Physics and Controlled Fusion, Vol. 58, Issue 4 https://doi.org/10.1088/0741-3335/58/4/045001	journal	January 2016
Physics-based control of neoclassical tearing modes on TCV Kong, M.; Felici, F.; Sauter, O. Plasma Physics and Controlled Fusion, Vol. 64, Issue 4 https://doi.org/10.1088/1361-6587/ac48be	journal	February 2022
Measurement of scrape-off-layer current dynamics during MHD activity and disruptions in HBT-EP Levesque, J. P.; Brooks, J. W.; Abler, M. C. Nuclear Fusion, Vol. 57, Issue 8 https://doi.org/10.1088/1741-4326/aa75ea	journal	July 2017
Machine learning for disruption warnings on Alcator C-Mod, DIII-D, and EAST Montes, K. J.; Rea, C.; Granetz, R. S. Nuclear Fusion, Vol. 59, Issue 9 https://doi.org/10.1088/1741-4326/ab1df4	journal	July 2019
A real-time machine learning-based disruption predictor in DIII-D Rea, C.; Montes, K. J.; Erickson, K. G. Nuclear Fusion, Vol. 59, Issue 9 https://doi.org/10.1088/1741-4326/ab28bf	journal	July 2019
A machine learning approach based on generative topographic mapping for disruption prevention and avoidance at JET Pau, A.; Fanni, A.; Carcangiu, S. Nuclear Fusion, Vol. 59, Issue 10 https://doi.org/10.1088/1741-4326/ab2ea9	journal	August 2019
Prediction of electron density and pressure profile shapes on NSTX-U using neural networks Boyer, M. D.; Chadwick, J. Nuclear Fusion, Vol. 61, Issue 4 https://doi.org/10.1088/1741-4326/abe08b	journal	March 2021
Data-driven profile prediction for DIII-D Abbate, J.; Conlin, R.; Kolemen, E. Nuclear Fusion, Vol. 61, Issue 4 https://doi.org/10.1088/1741-4326/abe08d	journal	March 2021
Experiment data-driven modeling of tokamak discharge in EAST Wan, Chenguang; Yu, Zhi; Wang, Feng Nuclear Fusion, Vol. 61, Issue 6 https://doi.org/10.1088/1741-4326/abf419	journal	April 2021
Feedforward beta control in the KSTAR tokamak by deep reinforcement learning Seo, Jaemin; Na, Y. -S.; Kim, B. Nuclear Fusion, Vol. 61, Issue 10 https://doi.org/10.1088/1741-4326/ac121b	journal	September 2021
Scenario adaptive disruption prediction study for next generation burning-plasma tokamaks Zhu, J.; Rea, C.; Granetz, R. S. Nuclear Fusion, Vol. 61, Issue 11 https://doi.org/10.1088/1741-4326/ac28ae	journal	October 2021
A dimensionality reduction algorithm for mapping tokamak operational regimes using a variational autoencoder (VAE) neural network Wei, Y.; Levesque, J. P.; Hansen, C. J. Nuclear Fusion, Vol. 61, Issue 12 https://doi.org/10.1088/1741-4326/ac3296	journal	November 2021
Toward active disruption avoidance via real-time estimation of the safe operating region and disruption proximity in tokamaks Boyer, M. D.; Rea, C.; Clement, M. Nuclear Fusion, Vol. 62, Issue 2 https://doi.org/10.1088/1741-4326/ac359e	journal	December 2021
Development of an operation trajectory design algorithm for control of multiple 0D parameters using deep reinforcement learning in KSTAR Seo, J.; Na, Y. -S.; Kim, B. Nuclear Fusion, Vol. 62, Issue 8 https://doi.org/10.1088/1741-4326/ac79be	journal	July 2022
Fast inference of deep neural networks in FPGAs for particle physics Duarte, J.; Han, S.; Harris, P. Journal of Instrumentation, Vol. 13, Issue 07 https://doi.org/10.1088/1748-0221/13/07/P07027	journal	July 2018
Compressing deep neural networks on FPGAs to binary and ternary precision with `hls4ml` Ngadiuba, Jennifer; Loncar, Vladimir; Pierini, Maurizio Machine Learning: Science and Technology, Vol. 2, Issue 1 https://doi.org/10.1088/2632-2153/aba042	journal	December 2020
Fast convolutional neural networks on FPGAs with hls4ml Aarrestad, Thea; Loncar, Vladimir; Ghielmetti, Nicolò Machine Learning: Science and Technology, Vol. 2, Issue 4 https://doi.org/10.1088/2632-2153/ac0ea1	journal	July 2021
Data-driven discovery of reduced plasma physics models from fully kinetic simulations Alves, E. P.; Fiuza, F. Physical Review Research, Vol. 4, Issue 3 https://doi.org/10.1103/PhysRevResearch.4.033192	journal	September 2022
Real-Time and Adaptive Reservoir Computing With Application to Profile Prediction in Fusion Plasma Jalalvand, Azarakhsh; Abbate, Joseph; Conlin, Rory IEEE Transactions on Neural Networks and Learning Systems, Vol. 33, Issue 6 https://doi.org/10.1109/TNNLS.2021.3085504	journal	June 2022
Long Short-Term Memory Hochreiter, Sepp; Schmidhuber, Jürgen Neural Computation, Vol. 9, Issue 8 https://doi.org/10.1162/neco.1997.9.8.1735	journal	November 1997
Fully Convolutional Spatio-Temporal Models for Representation Learning in Plasma Science Dong, Ge; Felker, Kyle Gerard; Svyatkovskiy, Alexey Journal of Machine Learning for Modeling and Computing, Vol. 2, Issue 1 https://doi.org/10.1615/JMachLearnModelComput.2021037052	journal	January 2021
Real-Time Inference With 2D Convolutional Neural Networks on Field Programmable Gate Arrays for High-Rate Particle Imaging Detectors Jwa, Yeon-jae; Di Guglielmo, Giuseppe; Arnold, Lukas Frontiers in Artificial Intelligence, Vol. 5 https://doi.org/10.3389/frai.2022.855184	journal	May 2022

Similar Records

Suppression of MHD modes with active phase-control of probe-injected currents

Journal Article · Thu Aug 05 00:00:00 EDT 2021 · Nuclear Fusion · OSTI ID:1849935

Related Subjects

70 PLASMA PHYSICS AND FUSION TECHNOLOGY
HBT-EP
MHD mode tracking
Physics
control
diagnostics
fast camera
machine learning

MHD mode tracking using high-speed cameras and deep learning

Citation Formats

References (41)

Similar Records

Related Subjects