Disruption forecasting at JET using neural networks
Disruption forecasting at JET using neural networks
复制标题
DOI：
10.1088/0029-5515/44/1/008
复制
发表时间：
2002
期刊：
影响因子：
--
通讯作者：
B. Cannas;A. Fanni;E. Marongiu;P. Sonato
中科院分区：
文献类型：
--
作者：
B. Cannas;A. Fanni;E. Marongiu;P. Sonato
神经网络经过训练，在托卡马克实验中使用几个诊断信号作为输入来评估等离子体中断的风险。显著性分析确认了所选输入的好坏，所有这些都对网络性能有贡献。所进行的测试参考了在两年的喷气托卡马克实验期间从成功终止和中断终止的脉冲中收集的数据。结果表明，开发一种神经网络预测器的可能性，这种预测器可以提前很好地干预，以避免等离子体中断或减轻其影响。
Neural networks are trained to evaluate the risk of plasma disruptions in a tokamak experiment using several diagnostic signals as inputs. A saliency analysis confirms the goodness of the chosen inputs, all of which contribute to the network performance. Tests that were carried out refer to data collected from succesfully terminated and disruption terminated pulses performed during two years of JET tokamak experiments. Results show the possibility of developing a neural network predictor that intervenes well in advance in order to avoid plasma disruption or mitigate its effects.