Plasma and Fusion Research

Volume 16, 1402073 (2021)

Regular Articles

Likelihood Identification of High-Beta Disruption in JT-60U
Tatsuya YOKOYAMA1,2), Hiroshi YAMADA1), Akihiko ISAYAMA3), Ryoji HIWATARI4), Shunsuke IDE3), Go MATSUNAGA3), Yuya MIYOSHI4), Naoyuki OYAMA3), Naoto IMAGAWA1), Yasuhiko IGARASHI5,6), Masato OKADA1) and Yuichi OGAWA1)
1)
Graduate School of Frontier Sciences, The University of Tokyo, Kashiwa 277-8561, Japan
2)
Research Fellow of Japan Society for the Promotion of Science, Tokyo 102-0083, Japan
3)
Naka Fusion Institute, National Institutes for Quantum and Radiological Science and Technology, Naka 311-0193, Japan
4)
Rokkasho Fusion Institute, National Institutes for Quantum and Radiological Science and Technology, Rokkasho 039-3212, Japan
5)
Faculty of Engineering, Information and Systems, University of Tsukuba, Tsukuba 305-8573, Japan
6)
Japan Science and Technology Agency, PRESTO, Kawaguchi 332-0012, Japan
(Received 11 February 2021 / Accepted 6 April 2021 / Published 24 May 2021)

Abstract

Prediction and likelihood identification of high-beta disruption in JT-60U has been discussed by means of feature extraction based on sparse modeling. In disruption prediction studies using machine learning, the selection of input parameters is an essential issue. A disruption predictor has been developed by using a linear support vector machine with input parameters selected through an exhaustive search, which is one idea of sparse modeling. The investigated dataset includes not only global plasma parameters but also local parameters such as ion temperature and plasma rotation. As a result of the exhaustive search, five physical parameters, i.e., normalized beta βN, plasma elongation κ, ion temperature Ti and magnetic shear s at the q = 2 rational surface, have been extracted as key parameters of high-beta disruption. The boundary between the disruptive and the non-disruptive zones in multidimensional space has been defined as the power law expression with these key parameters. Consequently, the disruption likelihood has been quantified in terms of probability based on this boundary expression. Careful deliberation of the expression of the disruption likelihood, which is derived with machine learning, could lead to the elucidation of the underlying physics behind disruptions.

Keywords

tokamak, JT-60U, disruption prediction, sparse modeling, machine learning

DOI: 10.1585/pfr.16.1402073

Full Text

PDF format (923Kbytes) PDF Download

References

  • [1] M. Lehnen et al., J. Nucl. Mater. 463, 39 (2015).
  • [2] E. Strait et al., Nucl. Fusion 59(11), 112012 (2019).
  • [3] A.H. Boozer, Phys. Plasmas 19(5), 058101 (2012).
  • [4] T. Hender et al., Nucl. Fusion 47(6), S128 (2007).
  • [5] A. Murari et al., Nucl. Fusion 59(8), 086037 (2019).
  • [6] A. Pau et al., IEEE Trans. Plasma Sci. 46(7), 2691 (2018).
  • [7] J. Kates-Harbeck, A. Svyatkovskiy and W. Tang, Nature 568(7753), 526 (2019).
  • [8] K.J. Montes et al., Nucl. Fusion 59(9), 096015 (2019).
  • [9] P. de Vries et al., Nucl. Fusion 49(5), 055011 (2009).
  • [10] S. Gerhardt et al., Nucl. Fusion 53(4), 043020 (2013).
  • [11] J.F. Lawless, Statistical Models and Methods for Lifetime Data, volume 362 (John Wiley & Sons, 2011).
  • [12] K. Olofsson, B. Sammuli and D. Humphreys, Fusion Eng. Des. 146, 1476 (2019).
  • [13] C. Rea et al., Nucl. Fusion 59(9), 096016 (2019).
  • [14] T. Yokoyama et al., Fusion Eng. Des. 140, 67 (2019).
  • [15] Y. Igarashi et al., J. Phys.: Conf. Series 1036, 012001 (2018).
  • [16] S. Ishida et al., Plasma Physics and Controlled Nuclear Fusion Research: Proceedings of 14th IAEA Fusion Energy Conference 1, 219 (1993).
  • [17] R. Sweeney et al., Nucl. Fusion 57(1), 016019 (2016).
  • [18] W. Howl et al., Phys. Fluids B: Plasma Physics 4(7), 1724 (1992).
  • [19] G. Matsunaga et al., Nucl. Fusion 50(8), 084003 (2010).
  • [20] S. Tokuda and T. Watanabe, Phys. Plasmas 6(8), 3012 (1999).
  • [21] C. Cortes and V. Vapnik, Machine Learning 20(3), 273 (1995).
  • [22] T.S. Taylor et al., Phys. Plasmas 2(6), 2390 (1995).
  • [23] M. Takechi et al., Phys. Rev. Lett. 98(5), 055002 (2007).
  • [24] Y. Miyoshi and Y. Ogawa, Plasma Fusion Res. 9, 1405015 (2014).