skip to main content
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Machine learning control for disruption and tearing mode avoidance

Abstract

In this work, real-time feedback control based on machine learning algorithms (MLA) was successfully developed and tested on DIII-D plasmas to avoid tearing modes and disruptions while maximizing the plasma performance, which is measured by normalized plasma beta. Control uses MLAs that were trained with ensemble learning methods using only the data available to the real-time Plasma Control System (PCS) from several thousand DIII-D discharges. A `tearability' metric that quantifies the likelihood of the onset of 2/1 tearing modes (TM) in a given time window, and a 'disruptivity' metric that quantifies the likelihood of the onset of plasma disruptions were first tested o -line then implemented on the PCS. A real-time control system based on these MLAs was successfully tested on DIII-D discharges, using feedback algorithms to maximize βΝ while avoiding tearing modes and to dynamically adjust ramp down to avoid high-current disruptions in ramp down.

Authors:
ORCiD logo [1]; ORCiD logo [2];  [3];  [4]; ORCiD logo [1];  [3];  [2];  [5]; ORCiD logo [1]; ORCiD logo [6]
  1. Princeton Univ., NJ (United States)
  2. General Atomics, San Diego, CA (United States)
  3. Princeton Plasma Physics Lab. (PPPL), Princeton, NJ (United States)
  4. Eindhoven Univ. of Technology, Eindhoven (The Netherlands)
  5. Yale Univ., New Haven, CT (United States)
  6. Eindhoven Univ. of Technology, Eindhoven (The Netherlands); Princeton Univ., NJ (United States)
Publication Date:
Research Org.:
General Atomics, San Diego, CA (United States)
Sponsoring Org.:
USDOE Office of Science (SC), Fusion Energy Sciences (FES)
OSTI Identifier:
1607465
Alternate Identifier(s):
OSTI ID: 1596898
Grant/Contract Number:  
FC02-04ER54698; AC02-09CH11466; SC0015878; 633053
Resource Type:
Accepted Manuscript
Journal Name:
Physics of Plasmas
Additional Journal Information:
Journal Volume: 27; Journal Issue: 2; Journal ID: ISSN 1070-664X
Publisher:
American Institute of Physics (AIP)
Country of Publication:
United States
Language:
English
Subject:
70 PLASMA PHYSICS AND FUSION TECHNOLOGY

Citation Formats

Fu, Yichen, Eldon, David, Erickson, Keith, Kleijwegt, Kornee, Lupin-Jimenez, Leonard, Boyer, Mark D., Eidietis, Nick, Barbour, Nathaniel, Izacard, Olivier, and Kolemen, Egemen. Machine learning control for disruption and tearing mode avoidance. United States: N. p., 2020. Web. https://doi.org/10.1063/1.5125581.
Fu, Yichen, Eldon, David, Erickson, Keith, Kleijwegt, Kornee, Lupin-Jimenez, Leonard, Boyer, Mark D., Eidietis, Nick, Barbour, Nathaniel, Izacard, Olivier, & Kolemen, Egemen. Machine learning control for disruption and tearing mode avoidance. United States. https://doi.org/10.1063/1.5125581
Fu, Yichen, Eldon, David, Erickson, Keith, Kleijwegt, Kornee, Lupin-Jimenez, Leonard, Boyer, Mark D., Eidietis, Nick, Barbour, Nathaniel, Izacard, Olivier, and Kolemen, Egemen. Mon . "Machine learning control for disruption and tearing mode avoidance". United States. https://doi.org/10.1063/1.5125581. https://www.osti.gov/servlets/purl/1607465.
@article{osti_1607465,
title = {Machine learning control for disruption and tearing mode avoidance},
author = {Fu, Yichen and Eldon, David and Erickson, Keith and Kleijwegt, Kornee and Lupin-Jimenez, Leonard and Boyer, Mark D. and Eidietis, Nick and Barbour, Nathaniel and Izacard, Olivier and Kolemen, Egemen},
abstractNote = {In this work, real-time feedback control based on machine learning algorithms (MLA) was successfully developed and tested on DIII-D plasmas to avoid tearing modes and disruptions while maximizing the plasma performance, which is measured by normalized plasma beta. Control uses MLAs that were trained with ensemble learning methods using only the data available to the real-time Plasma Control System (PCS) from several thousand DIII-D discharges. A `tearability' metric that quantifies the likelihood of the onset of 2/1 tearing modes (TM) in a given time window, and a 'disruptivity' metric that quantifies the likelihood of the onset of plasma disruptions were first tested o -line then implemented on the PCS. A real-time control system based on these MLAs was successfully tested on DIII-D discharges, using feedback algorithms to maximize βΝ while avoiding tearing modes and to dynamically adjust ramp down to avoid high-current disruptions in ramp down.},
doi = {10.1063/1.5125581},
journal = {Physics of Plasmas},
number = 2,
volume = 27,
place = {United States},
year = {2020},
month = {2}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Citation Metrics:
Cited by: 1 work
Citation information provided by
Web of Science

Save / Share:

Works referenced in this record:

Disruptions in ITER and strategies for their control and mitigation
journal, August 2015


Theory of tokamak disruptions
journal, May 2012


Optimized tokamak power exhaust with double radiative feedback in ASDEX Upgrade
journal, November 2012


Heterodyne ECE diagnostic in the mode detection and disruption avoidance at TEXTOR
journal, November 2003


A reduced resistive wall mode kinetic stability model for disruption forecasting
journal, May 2017

  • Berkery, J. W.; Sabbagh, S. A.; Bell, R. E.
  • Physics of Plasmas, Vol. 24, Issue 5
  • DOI: 10.1063/1.4977464

Detection of disruptions in the high- β spherical torus NSTX
journal, May 2013


Neural network prediction of some classes of tokamak disruptions
journal, August 1996


Tokamak disruption alarm based on a neural network model of the high- beta limit
journal, June 1997


Prediction and mitigation of disruptions in ASDEX Upgrade
journal, March 2001


A cross-tokamak neural network disruption predictor for the JET and ASDEX Upgrade tokamaks
journal, April 2005


A prediction tool for real-time application in the disruption protection system at JET
journal, October 2007


Neural-net disruption predictor in JT-60U
journal, December 2003


Forecasting disruptions in the ADITYA tokamak using neural networks
journal, December 2000


Predicting disruptive instabilities in controlled fusion plasmas through deep learning
journal, April 2019


On the form of NTM onset scalings
journal, April 2004


An advanced disruption predictor for JET tested in a simulated real-time environment
journal, January 2010


Prediction of disruptions on ASDEX Upgrade using discriminant analysis
journal, May 2011


Results of the JET real-time disruption predictor in the ITER-like wall campaigns
journal, October 2013


Real-Time Implementation in JET of the SPAD Disruption Predictor Using MARTe
journal, February 2018

  • Esquembri, S.; Vega, J.; Murari, A.
  • IEEE Transactions on Nuclear Science, Vol. 65, Issue 2
  • DOI: 10.1109/TNS.2018.2791719

A survey of decision tree classifier methodology
journal, January 1991

  • Safavian, S. R.; Landgrebe, D.
  • IEEE Transactions on Systems, Man, and Cybernetics, Vol. 21, Issue 3
  • DOI: 10.1109/21.97458

Unbiased and non-supervised learning methods for disruption prediction at JET
journal, April 2009


Ensemble based systems in decision making
journal, January 2006


Disruption prediction investigations using Machine Learning tools on DIII-D and Alcator C-Mod
journal, June 2018

  • Rea, C.; Granetz, R. S.; Montes, K.
  • Plasma Physics and Controlled Fusion, Vol. 60, Issue 8
  • DOI: 10.1088/1361-6587/aac7fe

High beta tokamak operation in DIII-D limited at low density/collisionality by resistive tearing modes
journal, March 1997


Integrated modeling applications for tokamak experiments with OMFIT
journal, July 2015


A flexible software architecture for tokamak discharge control systems
conference, January 1995

  • Ferron, J. R.; Penaflor, B.; Walker, M. L.
  • Proceedings of 16th International Symposium on Fusion Engineering
  • DOI: 10.1109/FUSION.1995.534361

Introduction to the Bootstrap World
journal, May 2003


Bagging predictors
journal, August 1996


Random Forests
journal, January 2001


Extremely randomized trees
journal, March 2006


An introduction to ROC analysis
journal, June 2006


Survey of disruption causes at JET
journal, April 2011


MDS plus data acquisition system
journal, January 1997

  • Stillerman, J. A.; Fredian, T. W.; Klare, K. A.
  • Review of Scientific Instruments, Vol. 68, Issue 1
  • DOI: 10.1063/1.1147719

Real time equilibrium reconstruction for tokamak discharge control
journal, July 1998


Long pulse high performance discharges in the DIII-D tokamak
journal, November 2001


Disruption forecasting at JET using neural networks
journal, December 2003


Experimental simulation of ITER rampdown in DIII-D
journal, March 2010


Multi-machine analysis of termination scenarios with comparison to simulations of controlled shutdown of ITER discharges
journal, December 2017


Implementing a finite-state off-normal and fault response system for disruption avoidance in tokamaks
journal, March 2018


Avoidance of q a =3 disruption by electron cyclotron heating in the JFT-2M tokamak
journal, October 1992


Effect of Heating on the Suppression of Tearing Modes in Tokamaks
journal, January 2007


Requirements for Triggering the ITER Disruption Mitigation System
journal, April 2016

  • de Vries, P. C.; Pautasso, G.; Humphreys, D.
  • Fusion Science and Technology, Vol. 69, Issue 2
  • DOI: 10.13182/FST15-176

Adaptive high learning rate probabilistic disruption predictors from scratch for the next generation of tokamaks
journal, October 2014