Modeling of transport phenomena in tokamak plasmas with neural networks
Modeling of transport phenomena in tokamak plasmas with neural networks
复制标题
用神经网络模拟托卡马克等离子体中的输运现象
DOI：
10.1063/1.4885343
复制
发表时间：
2014
影响因子：
2.2
通讯作者：
L. Lao
中科院分区：
文献类型：
--
作者：
O. Meneghini;C. Luna;Sterling P. Smith;L. Lao
一种使用神经网络 (NN) 生成电子和离子热通量分布的新传输模型已经开发出来。给定一组与最高保真度模型使用的参数类似的局部无量纲等离子体参数，神经网络模型能够高效、准确地预测离子和电子热传输曲线。作为基准，我们根据 2012 年和 2013 年 DIII-D 实验活动的数据构建、训练和测试了神经网络。研究发现，神经网络可以捕获大部分等离子体半径和广泛等离子体状态下的实验行为。尽管每个径向位置都是独立计算的，但热通量分布是平滑的，这表明神经网络找到的解是局部输入参数的平滑函数。该结果支持了输入参数与实验测量的传输通量之间存在明确定义的非随机关系的证据。该方法的数值效率高，每个数据点仅需要几个 CPU-μs，使其成为场景开发模拟和实时等离子体控制的理想选择。
A new transport model that uses neural networks (NNs) to yield electron and ion heat flux profiles has been developed. Given a set of local dimensionless plasma parameters similar to the ones that the highest fidelity models use, the NN model is able to efficiently and accurately predict the ion and electron heat transport profiles. As a benchmark, a NN was built, trained, and tested on data from the 2012 and 2013 DIII-D experimental campaigns. It is found that NN can capture the experimental behavior over the majority of the plasma radius and across a broad range of plasma regimes. Although each radial location is calculated independently from the others, the heat flux profiles are smooth, suggesting that the solution found by the NN is a smooth function of the local input parameters. This result supports the evidence of a well-defined, non-stochastic relationship between the input parameters and the experimentally measured transport fluxes. The numerical efficiency of this method, requiring only a few CPU-μs per data point, makes it ideal for scenario development simulations and real-time plasma control.
影响因子：
3.3
作者：
Shimada, M.;Campbell, D. J.;Sipps, A. C. C.
通讯作者：
Sipps, A. C. C.