Disruption prediction using a full convolutional neural network on EAST

被引：42

作者：

Guo, B. H. ^{[1
,2
]}

Shen, B. ^{[1
]}

Chen, D. L. ^{[1
]}

Rea, C. ^{[3
]}

Granetz, R. S. ^{[3
]}

Huang, Y. ^{[1
]}

Zeng, L. ^{[1
]}

Zhang, H. ^{[4
]}

Qian, J. P. ^{[1
]}

Sun, Y. W. ^{[1
]}

Xiao, B. J. ^{[1
,2
]}

机构：

[1] Chinese Acad Sci, Inst Plasma Phys, HFIPS, Hefei 230031, Peoples R China

[2] Univ Sci & Technol China, Hefei 230026, Peoples R China

[3] MIT, Plasma Sci & Fus Ctr, 77 Massachusetts Ave, Cambridge, MA 02139 USA

[4] Chongqing Univ Posts & Telecommun, Chongqing 400065, Peoples R China

来源：

PLASMA PHYSICS AND CONTROLLED FUSION | 2021年 / 63卷 / 02期

基金：

中国国家自然科学基金;

关键词：

plasma; disruption prediction; deep learning; convolutional neural network;

D O I：

10.1088/1361-6587/abcbab

中图分类号：

O35 [流体力学]; O53 [等离子体物理学];

学科分类号：

070204 ; 080103 ; 080704 ;

摘要：

In this study, a full convolutional neural network is trained on a large database of experimental EAST data to classify disruptive discharges and distinguish them from non-disruptive discharges. The database contains 14 diagnostic parameters from the similar to 10(4) discharges (disruptive and non-disruptive). The test set contains 417 disruptive discharges and 999 non-disruptive discharges, which are used to evaluate the performance of the model. The results reveal that the true positive (TP) rate is similar to 0.827, while the false positive (FP) rate is similar to 0.067. This indicates that 72 disruptive discharges and 67 non-disruptive discharges are misclassified in the test set. The FPs are investigated in detail and are found to emerge due to some subtle disturbances in the signals, which lead to misjudgment of the model. Therefore, hundreds of non-disruptive discharges from training set, containing time slices of small disturbances, are artificially added into the training database for retraining the model. The same test set is used to assess the performance of the improved model. The TP rate of the improved model increases up to 0.875, while its FP rate decreases to 0.061. Overall, the proposed data-driven predicted model exhibits immense potential for application in long pulse fusion devices such as ITER.

引用

页数：13

共 30 条

[1] Improvements in disruption prediction at ASDEX Upgrade [J].

Aledda, R. ;

Cannas, B. ;

Fanni, A. ;

Pau, A. ;

Sias, G. .

FUSION ENGINEERING AND DESIGN, 2015, 96-97 :698-702

[2]

[Anonymous], 2014, P INT C LEARN REPR D

[3] The H-mode density limit in the full tungsten ASDEX Upgrade tokamak [J].

Bernert, M. ;

Eich, T. ;

Kallenbach, A. ;

Carralero, D. ;

Huber, A. ;

Lang, P. T. ;

Potzel, S. ;

Reimold, F. ;

Schweinzer, J. ;

Viezzer, E. ;

Zohm, H. .

PLASMA PHYSICS AND CONTROLLED FUSION, 2015, 57 (01)

[4] Automatic disruption classification in JET with the ITER-like wall [J].

Cannas, B. ;

de Vries, P. C. ;

Fanni, A. ;

Murari, A. ;

Pau, A. ;

Sias, G. .

PLASMA PHYSICS AND CONTROLLED FUSION, 2015, 57 (12)

[5] Characterization of disruption halo current between 'W-Like' graphite divertor and 'ITER-Like' divertor structure on EAST tokamak [J].

Chen, D. L. ;

Granetz, R. S. ;

Zeng, L. ;

Shen, B. ;

Qian, J. P. ;

Liu, L. ;

Xue, M. M. ;

Shi, T. H. ;

Wang, H. H. ;

Sun, Y. W. ;

Xiao, B. J. .

PLASMA PHYSICS AND CONTROLLED FUSION, 2020, 62 (09)

[6] The influence of an ITER-like wall on disruptions at JET [J].

de Vries, P. C. ;

Baruzzo, M. ;

Hogeweij, G. M. D. ;

Jachmich, S. ;

Joffrin, E. ;

Lomas, P. J. ;

Matthews, G. F. ;

Murari, A. ;

Nunes, I. ;

Puetterich, T. ;

Reux, C. ;

Vega, J. .

PHYSICS OF PLASMAS, 2014, 21 (05)

[7] Survey of disruption causes at JET [J].

de Vries, P. C. ;

Johnson, M. F. ;

Alper, B. ;

Buratti, P. ;

Hender, T. C. ;

Koslowski, H. R. ;

Riccardo, V. .

NUCLEAR FUSION, 2011, 51 (05)

[8] Development of an efficient real-time disruption predictor from scratch on JET and implications for ITER [J].

Dormido-Canto, S. ;

Vega, J. ;

Ramirez, J. M. ;

Murari, A. ;

Moreno, R. ;

Lopez, J. M. ;

Pereira, A. .

NUCLEAR FUSION, 2013, 53 (11)

[9] Deep Learning for Plasma Tomography and Disruption Prediction From Bolometer Data [J].

Ferreira, Diogo R. ;

Carvalho, Pedro J. ;

Fernandes, Horacio .

IEEE TRANSACTIONS ON PLASMA SCIENCE, 2020, 48 (01) :36-45

[10] Detection of disruptions in the high-β spherical torus NSTX [J].

Gerhardt, S. P. ;

Darrow, D. S. ;

Bell, R. E. ;

LeBlanc, B. P. ;

Menard, J. E. ;

Mueller, D. ;

Roquemore, A. L. ;

Sabbagh, S. A. ;

Yuh, H. .

NUCLEAR FUSION, 2013, 53 (06)

← 1 2 3 →