Modification of a machine learning‐based semi‐empirical turbulent transport model for its versatility

Modification of a machine learning‐based semi‐empirical turbulent transport model for its versatility
复制标题

基于机器学习的半经验湍流输运模型的多功能性修改

DOI:
10.1002/ctpp.202200152
复制
发表时间:
2023
影响因子:
1.6
通讯作者:
Yoshida Maiko
Yoshida Maiko
中科院分区:
物理与天体物理3区
文献类型:
--
作者:
Narita Emi;Honda Mitsuru;Nakata Motoki;Hayashi Nobuhiko;Nakayama Tomonari;Yoshida Maiko

文献摘要

参考文献

被引文献

相似文献

已经修改了基于机器学习的半经验湍流输运模型DeKANIS,使其独立于设备应用。DeKANIS预测粒子和热通量,区分扩散和非扩散输运过程。DeKANIS由一个神经网络(NN)模型和一个标度公式组成,前者根据陀螺动力学计算非扩散项的系数和通量的比率,后者根据经验通量估计湍流饱和水平。到目前为止,用于神经网络训练的数据集是基于JT - 60U等离子体制备的,但是通过利用JET等离子体,数据集得到了扩展,神经网络模型所涵盖的参数范围也变得更广。考虑碰撞引起的残余带向流水平的降低,重新建立了标度公式。新的DeKANIS已经用集成模型GOTRESS+证明了ITER等离子体在聚变前功率运行1阶段的合理剖面预测。在用陀螺动力学计算验证预报结果时,展示了引起通量的输运过程。
A machine learning‐based semi‐empirical turbulent transport model DeKANIS has been modified to apply it independently of the device. DeKANIS predicts particle and heat fluxes, distinguishing diffusive and non‐diffusive transport processes. DeKANIS consists of a neural network (NN) model, which computes coefficients of the non‐diffusive terms and the ratio of the fluxes based on the gyrokinetic calculations, and a scaling formula, which estimates the turbulent saturation level founded on empirical fluxes. The datasets used for NN training have been prepared based on JT‐60U plasmas so far, but by exploiting JET plasmas, the datasets have been expanded and the parameter ranges covered by the NN models have become wider. The scaling formula has been rebuilt considering the decrease in the residual zonal flow level due to collisions. The new DeKANIS has demonstrated a reasonable profile prediction of an ITER plasma in the pre‐fusion power operation 1 phase with an integrated model GOTRESS+. In validating the prediction results with the gyrokinetic calculations, transport processes causing the fluxes have been exhibited.
将纽科姆方程推广到真空中托卡马克边缘等离子体稳定性分析
DOI: --
发表时间: 2006
期刊: Comput. Phys. Commun 175
影响因子: --
作者:
N. Aiba;S. Tokuda;T. Ishizawa;他1名
通讯作者: 他1名
使用拟线性回旋输运模型 QuaLiKiz 进行可处理的通量驱动温度、密度和旋转剖面演化
DOI: 10.1088/1361-6587/aa8aeb
发表时间: 2017
影响因子: 2.2
作者:
J. Citrin;C. Bourdelle;F. Casson;C. Angioni;N. Bonanomi;Y. Camenen;X. Garbet;L. Garzotti;T. Görler;Ö. Gürcan;F. Koechl;F. Imbeaux;O. Linder;K. V. D. Plassche;P. Strand;G. Szepesi;J. Contributors
通讯作者: J. Contributors
DOI: --
发表时间: 2004
期刊:
影响因子: --
作者:
A. Peeters;D. Strintzi
通讯作者: D. Strintzi
DOI: 10.1088/1361-6587/abc861
发表时间: 2020
影响因子: 2.2
作者:
G. Staebler;J. Candy;E. Belli;J. Kinsey;N. Bonanomi;B. Patel
通讯作者: B. Patel
DOI: 10.1088/0741-3335/49/12/001
发表时间: 2007
影响因子: 2.2
作者:
K. Hamamatsu;T. Takizuka;N. Hayashi;T. Ozeki
通讯作者: T. Ozeki