-
高约束模式对改善等离子体约束有着重要意义, 但目前主要依赖人工进行模式识别, 其效率低、成本高, 导致核聚变装置中大量的诊断数据没有得到充分分析. 为了解决这个问题, 本文将机器学习中的谱聚类算法应用到EAST托卡马克装置上的电子回旋辐射成像、一维诊断系统电子回旋辐射计、磁探针、软X射线和快辐射等不同诊断系统的数据上, 在时域及频域上识别出了锯齿模, 验证了谱聚类方法的迁移性及准确性, 解决了监督学习在数据处理上迁移性差以及需要依赖大量标签数据的问题. 此外, 本文实现了特定模式的筛选; 最后利用电子回旋辐射成像及磁探针数据发现了一种可能的新模式, 为新模式探索提供了一种新思路.The number of data accumulated by controllable nuclear fusion devices is too large, and a large number of data have not been fully exploited. In such big data processing machine learning can play an important role. Therefore, in this work the spectral clustering method is used to realize the automatic processing of data, which can easily and quickly find the pattern information contained in the data. The discovery of these patterns is of great significance in improving plasma confinement and understanding plasma physics. In addition, in this work the spectral clustering method is applied to the electron cyclotron emission imaging (ECEI), one-dimensional diagnostic system electron cyclotron emissiometer, magnetic probe, soft X-ray, fast radiation (fast bolometer) and other different diagnostic systems on the EAST tokamak device. The sawtooth pattern is identified, the migration of the spectral clustering method is verified, and the problems of poor data processing migration in supervised learning and the need to rely on a large number of labeled data are solved. Finally, in this work, the ECEI and magnetic probe data are used to discover a possible new mode in the time domain and frequency domain respectively, which provides a new idea for exploring new modes.
-
Keywords:
- plasma diagnostics /
- spectral clustering /
- pattern recognition /
- coherent mode
[1] 朱玉 2019 硕士学位论文 (合肥: 中国科学技术大学)
Zhu Y 2019 M. S. Thesis (Hefei: University of Science and Technology of China) (in Chinese)
[2] Boom J E, Wolfrum E, Classen I G J, et al. 2012 Nucl. Fusion 52 114004Google Scholar
[3] Wesson J A 1986 Plasma Phys. Control. Fusion 28 243Google Scholar
[4] Zhao Z L, Xie J L, Qu C M, Liao W, Li H, Lan T, Liu A D, Zhuang G, Liu W D 2017 Radiat. Eff. Defects Solids 172 760Google Scholar
[5] 赵朕领 2017 博士学位论文 (合肥: 中国科学技术大学)
Zhao Z L 2017 Ph. D. Dissertation (Hefei: University of Science and Technology of China) (in Chinese)
[6] 徐明 2011 博士学位论文 (合肥: 中国科学技术大学)
Xu M 2011 Ph. D. Dissertation (Hefei: University of Science and Technology of China) (in Chinese)
[7] Park H K, Mazzucato E, Luhmann N C, et al. 2006 Phys. Plasmas 13 055907Google Scholar
[8] Yun G S, Lee W, Choi M J, et al. 2011 Phys. Rev. Lett 107 045004Google Scholar
[9] Tobias B J, Classen I G J, Domier C W, et al. 2011 Phys. Rev. Lett. 106 075003Google Scholar
[10] Gaudio P, Murari A, Gelfusa M, Lupelli I, Vega J 2014 Plasma Phys. Control. Fusion 56 114002Google Scholar
[11] Arena P, Basile A, Fortuna L, Mazzitelli G, Rizzo A, Zammataro M 2004 IEEE International Symposium on Circuits and Systems Vancouver, BC, Canada, May 23—26, 2004 p77
[12] Gonzalez S, Vega J, Murari A, Pereira A, Ramirez J M, Dormido-Canto S 2010 Rev. Sci. Instrum. 81 10E123Google Scholar
[13] Hartigan J A, Wong M A 1979 J. R. Stat. Soc. Ser. C-Appl. Stat. 28 100Google Scholar
[14] Tian Z, Ramakrishnan R, Livny M 1996 Sigmod. Rec. 25 103Google Scholar
[15] von Luxburg U 2007 Stat. Comput. 17 395Google Scholar
[16] Shi J B, Malik J 2000 IEEE Trans. Pattern Anal. Mach. Intell. 22 888Google Scholar
[17] Nam Y B, Park H K, Lee W, Yun G S, Kim M, Sabot R, Elbeze D, Lotte P, Shen J 2016 Rev. Sci. Instrum. 87 11E135Google Scholar
[18] Deng B H, Domier C W, Luhmann N C, et al. 2001 Rev. Sci. Instrum. 72 301Google Scholar
[19] Gao B X, Xie J L, Mao Z, et al. 2018 J. Instrum. 13 P02009Google Scholar
[20] Gao B X 2013 Ph. D. Dissertation (Hefei: University of Science and Technology of China) (in Chinese) [高炳西 2013 博士学位论文(合肥: 中国科学技术大学)]
[21] Drake J F, Lee Y C 1977 Phys. Fluids 20 1341Google Scholar
-
-
[1] 朱玉 2019 硕士学位论文 (合肥: 中国科学技术大学)
Zhu Y 2019 M. S. Thesis (Hefei: University of Science and Technology of China) (in Chinese)
[2] Boom J E, Wolfrum E, Classen I G J, et al. 2012 Nucl. Fusion 52 114004Google Scholar
[3] Wesson J A 1986 Plasma Phys. Control. Fusion 28 243Google Scholar
[4] Zhao Z L, Xie J L, Qu C M, Liao W, Li H, Lan T, Liu A D, Zhuang G, Liu W D 2017 Radiat. Eff. Defects Solids 172 760Google Scholar
[5] 赵朕领 2017 博士学位论文 (合肥: 中国科学技术大学)
Zhao Z L 2017 Ph. D. Dissertation (Hefei: University of Science and Technology of China) (in Chinese)
[6] 徐明 2011 博士学位论文 (合肥: 中国科学技术大学)
Xu M 2011 Ph. D. Dissertation (Hefei: University of Science and Technology of China) (in Chinese)
[7] Park H K, Mazzucato E, Luhmann N C, et al. 2006 Phys. Plasmas 13 055907Google Scholar
[8] Yun G S, Lee W, Choi M J, et al. 2011 Phys. Rev. Lett 107 045004Google Scholar
[9] Tobias B J, Classen I G J, Domier C W, et al. 2011 Phys. Rev. Lett. 106 075003Google Scholar
[10] Gaudio P, Murari A, Gelfusa M, Lupelli I, Vega J 2014 Plasma Phys. Control. Fusion 56 114002Google Scholar
[11] Arena P, Basile A, Fortuna L, Mazzitelli G, Rizzo A, Zammataro M 2004 IEEE International Symposium on Circuits and Systems Vancouver, BC, Canada, May 23—26, 2004 p77
[12] Gonzalez S, Vega J, Murari A, Pereira A, Ramirez J M, Dormido-Canto S 2010 Rev. Sci. Instrum. 81 10E123Google Scholar
[13] Hartigan J A, Wong M A 1979 J. R. Stat. Soc. Ser. C-Appl. Stat. 28 100Google Scholar
[14] Tian Z, Ramakrishnan R, Livny M 1996 Sigmod. Rec. 25 103Google Scholar
[15] von Luxburg U 2007 Stat. Comput. 17 395Google Scholar
[16] Shi J B, Malik J 2000 IEEE Trans. Pattern Anal. Mach. Intell. 22 888Google Scholar
[17] Nam Y B, Park H K, Lee W, Yun G S, Kim M, Sabot R, Elbeze D, Lotte P, Shen J 2016 Rev. Sci. Instrum. 87 11E135Google Scholar
[18] Deng B H, Domier C W, Luhmann N C, et al. 2001 Rev. Sci. Instrum. 72 301Google Scholar
[19] Gao B X, Xie J L, Mao Z, et al. 2018 J. Instrum. 13 P02009Google Scholar
[20] Gao B X 2013 Ph. D. Dissertation (Hefei: University of Science and Technology of China) (in Chinese) [高炳西 2013 博士学位论文(合肥: 中国科学技术大学)]
[21] Drake J F, Lee Y C 1977 Phys. Fluids 20 1341Google Scholar
计量
- 文章访问数: 3708
- PDF下载量: 69
- 被引次数: 0