Papers
Topics
Authors
Recent
Search
2000 character limit reached

Real-time equilibrium reconstruction by neural network based on HL-3 tokamak

Published 18 May 2024 in physics.plasm-ph | (2405.11221v1)

Abstract: A neural network model, EFITNN, has been developed capable of real-time magnetic equilibrium reconstruction based on HL-3 tokamak magnetic measurement signals. The model processes inputs from 68 channels of magnetic measurement data gathered from 1159 HL-3 experimental discharges, including plasma current, loop voltage, and the poloidal magnetic fields measured by equilibrium probes. The outputs of the model feature eight key plasma parameters, alongside high-resolution ($129\times129$) reconstructions of the toroidal current density $J_{\text P}$ and poloidal magnetic flux profiles $\Psi_{rz}$. Moreover, the network's architecture employs a multi-task learning structure, which enables the sharing of weights and mutual correction among different outputs, and lead to increase the model's accuracy by up to 32%. The performance of EFITNN demonstrates remarkable consistency with the offline EFIT, achieving average $R2 = 0.941, 0.997$ and $0.959$ for eight plasma parameters, $\Psi_{rz}$ and $J_{\text P}$, respectively. The model's robust generalization capabilities are particularly evident in its successful predictions of quasi-snowflake (QSF) divertor configurations and its adept handling of data from shot numbers or plasma current intervals not previously encountered during training. Compared to numerical methods, EFITNN significantly enhances computational efficiency with average computation time ranging from 0.08ms to 0.45ms, indicating its potential utility in real-time isoflux control and plasma profile management.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (55)
  1. Reconstruction of current profile parameters and plasma shapes in tokamaks. Nuclear fusion, 25(11):1611, 1985.
  2. Mhd equilibrium reconstruction in the diii-d tokamak. Fusion science and technology, 48(2):968–977, 2005.
  3. Equilibrium analysis of iron core tokamaks using a full domain method. Nuclear fusion, 32(8):1351, 1992.
  4. Equilibrium properties of spherical torus plasmas in nstx. Nuclear Fusion, 41(11):1601, 2001.
  5. Equilibrium reconstruction in east tokamak. Plasma Science and Technology, 11(2):142, 2009.
  6. Kinetic equilibrium reconstruction on east tokamak. Plasma Physics and Controlled Fusion, 55(12):125008, 2013.
  7. Kstar equilibrium operating space and projected stabilization at high normalized beta. Nuclear Fusion, 51(5):053001, 2011.
  8. Kinetic equilibrium reconstruction and the impact on stability analysis of kstar plasmas. Nuclear Fusion, 61(11):116033, 2021.
  9. Equilibrium reconstruction in the start tokamak. Nuclear fusion, 41(2):169, 2001.
  10. A unified approach to equilibrium reconstruction. In Proceedings-33rd EPS conference on Controlled Fusion and Plasma Physics, pp. P–2.160, 2006.
  11. Resistive n= 1 modes in reversed magnetic shear alcator c-mod plasmas. Nuclear fusion, 40(8):1463, 2000.
  12. Wolfgang Zwingmann. Equilibrium analysis of steady state tokamak discharges. Nuclear Fusion, 43(9):842, 2003.
  13. Efit equilibrium reconstruction including polarimetry measurements on tore supra. Fusion Science and Technology, 59(2):397–405, 2011.
  14. Study of plasma mhd equilibrium in hl-2a tokamak. Plasma Science and Technology, 8(4):397, 2006.
  15. Equilibrium reconstruction and equilibrium properties in quest tokamak. Journal of Fusion Energy, 38:244–252, 2019.
  16. Kinetic equilibrium reconstructions of plasmas in the mast database and preparation for reconstruction of the first plasmas in mast upgrade. Plasma Physics and Controlled Fusion, 63(5):055014, 2021.
  17. Hydromagnetic equilibria and force-free fields. Journal of Nuclear Energy (1954), 7(3-4):190, 1958.
  18. VD Shafranov. Plasma equilibrium in a magnetic field. Reviews of plasma physics, 2:103, 1966.
  19. Acceleration optimization of real-time equilibrium reconstruction for hl-2a tokamak discharge control. Plasma Science and Technology, 20(2):025601, 2018.
  20. Real time equilibrium reconstruction for tokamak discharge control. Nuclear fusion, 38(7):1055, 1998.
  21. Gpu-optimized fast plasma equilibrium reconstruction in fine grids for real-time control and data analysis. Nuclear Fusion, 60(7):076023, 2020.
  22. Machine learning control for disruption and tearing mode avoidance. Physics of Plasmas, 27(2), 2020.
  23. Machine learning methods for probabilistic locked-mode predictors in tokamak plasmas. Physics of Plasmas, 28(8), 2021.
  24. Deep learning for plasma tomography and disruption prediction from bolometer data. IEEE Transactions on Plasma Science, 48(1):36–45, 2019.
  25. Disruption prediction on east tokamak using a deep learning algorithm. Plasma Physics and Controlled Fusion, 63(11):115007, 2021.
  26. A disruption predictor based on a 1.5-dimensional convolutional neural network in hl-2a. Nuclear Fusion, 60(1):016017, 2019.
  27. Disruption prediction investigations using machine learning tools on diii-d and alcator c-mod. Plasma Physics and Controlled Fusion, 60(8):084004, 2018.
  28. Machine learning for disruption warnings on alcator c-mod, diii-d, and east. Nuclear Fusion, 59(9):096015, 2019.
  29. Predicting disruptive instabilities in controlled fusion plasmas through deep learning. Nature, 568(7753):526–531, 2019.
  30. Physics-guided machine learning approaches to predict the ideal stability properties of fusion plasmas. Nuclear Fusion, 60(4):046033, 2020.
  31. Machine-learning enabled analysis of elm filament dynamics in kstar. arXiv preprint arXiv:2201.07941, 2022.
  32. An alternative approach to the determination of scaling law expressions for the l–h transition in tokamaks utilizing classification tools instead of regression. Plasma Physics and Controlled Fusion, 56(11):114002, 2014.
  33. Simulation prediction of micro-instability transition and associated particle transport in tokamak plasmas. Nuclear Fusion, 62(3):036014, 2022.
  34. Machine learning of turbulent transport in fusion plasmas with neural network. Plasma Science and Technology, 23(11):115102, 2021.
  35. Uncovering turbulent plasma dynamics via deep learning from partial observations. Physical Review E, 104(2):025205, 2021.
  36. Real-time capable first principle based modelling of tokamak turbulent transport. Nuclear Fusion, 55(9):092001, 2015.
  37. Real-time-capable prediction of temperature and density profiles in a tokamak using raptor and a first-principle-based transport model. Nuclear Fusion, 58(9):096006, 2018.
  38. Fast modeling of turbulent transport in fusion plasmas using neural networks. Physics of Plasmas, 27(2), 2020.
  39. Deep learning for plasma tomography using the bolometer system at jet. Fusion engineering and design, 114:18–25, 2017.
  40. A machine-learning-based tool for last closed-flux surface reconstruction on tokamaks. Nuclear Fusion, 63(5):056019, 2023.
  41. Magnetic control of tokamak plasmas through deep reinforcement learning. Nature, 602(7897):414–419, 2022.
  42. Deep neural network grad–shafranov solver constrained with measured magnetic signals. Nuclear Fusion, 60(1):016034, 2019.
  43. Application of machine learning and artificial intelligence to extend efit equilibrium reconstruction. Plasma Physics and Controlled Fusion, 64(7):074001, 2022.
  44. New identification approach and methods for plasma equilibrium reconstruction in d-shaped tokamaks. Mathematics, 10(1):40, 2021.
  45. Neural net modeling of equilibria in nstx-u. Nuclear Fusion, 62(8):086042, 2022.
  46. Fast equilibrium reconstruction by deep learning on east tokamak. arXiv preprint arXiv:2305.12098, 2023.
  47. Progress of hl-2a experiments and hl-2m program. Nuclear Fusion, 62(4):042020, 2022.
  48. George Cybenko. Approximation by superpositions of a sigmoidal function. Mathematics of control, signals and systems, 2(4):303–314, 1989.
  49. Backpropagation applied to handwritten zip code recognition. Neural computation, 1(4):541–551, 1989.
  50. Visualizing and understanding convolutional networks. In Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part I 13, pages 818–833. Springer, 2014.
  51. A guide to convolutional neural networks for computer vision, volume 8. Springer, 2018.
  52. A stochastic approximation method. The annals of mathematical statistics, pages 400–407, 1951.
  53. Boris T Polyak. Some methods of speeding up the convergence of iteration methods. Ussr computational mathematics and mathematical physics, 4(5):1–17, 1964.
  54. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.
  55. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101, 2017.
Citations (1)
View on Semantic Scholar

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now

Collections

Sign up for free to add this paper to one or more collections.

Sign Up

Tweets

Sign up for free to view the 1 tweet with 0 likes about this paper.

Sign Up for Free