中国物理B ›› 2007, Vol. 16 ›› Issue (12): 3738-3741.doi: 10.1088/1009-1963/16/12/030

• • 上一篇    下一篇

HL-2A tokamak disruption forecasting based on an artificial neural network

Sanuki H1, Itoh K1, 王 灏2, 王爱科2, 杨青巍2, 丁玄同2, 董家齐2   

  1. (1)National Institute for Fusion Science, Toki, Gifu, 509-5292, Japan; (2)Southwestern Institute of Physics, Chengdu 610041, China
  • 出版日期:2007-12-20 发布日期:2007-12-20
  • 基金资助:
    Project supported by the National Natural Science Foundations of China (Grant No~10775040) and partially by JSPS-CAS Core University Program on Plasma and Nuclear Fusion.

HL-2A tokamak disruption forecasting based on an artificial neural network

Wang Hao(王灏)a)† , Wang Ai-Ke(王爱科)a), Yang Qing-Wei(杨青巍)a), Ding Xuan-Tong(丁玄同)a), Dong Jia-Qi(董家齐)a), Sanuki Hb), and Itoh Kb)   

  1. a Southwestern Institute of Physics, Chengdu 610041, China; b National Institute for Fusion Science, Toki, Gifu, 509-5292, Japan
  • Online:2007-12-20 Published:2007-12-20
  • Supported by:
    Project supported by the National Natural Science Foundations of China (Grant No~10775040) and partially by JSPS-CAS Core University Program on Plasma and Nuclear Fusion.

PDF (PC)

612

赞

摘要： Artificial neural networks are trained to forecast the plasma disruption in HL-2A tokamak. Optimized network architecture is obtained. Saliency analysis is made to assess the relative importance of different diagnostic signals as network input. The trained networks can successfully detect the disruptive pulses of HL-2A tokamak. The results obtained show the possibility of developing a neural network predictor that intervenes well in advance for avoiding plasma disruption or mitigating its effects.

关键词: disruption, prediction, artificial neural networks

Abstract: Artificial neural networks are trained to forecast the plasma disruption in HL-2A tokamak. Optimized network architecture is obtained. Saliency analysis is made to assess the relative importance of different diagnostic signals as network input. The trained networks can successfully detect the disruptive pulses of HL-2A tokamak. The results obtained show the possibility of developing a neural network predictor that intervenes well in advance for avoiding plasma disruption or mitigating its effects.

Key words: disruption, prediction, artificial neural networks

中图分类号:  (Tokamaks, spherical tokamaks)

  • 52.55.Fa
52.65.-y (Plasma simulation) 52.70.Ds (Electric and magnetic measurements)