arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1802.02242physics.comp-phstat.ML
收藏

基于深度神经网络的全脉冲层析成像重建

Full-pulse Tomographic Reconstruction with Deep Neural Networks

Diogo R. Ferreira, Pedro J. Carvalho, Horácio Fernandes

摘要:

等离子体层析成像是基于沿几条视线的线积分测量,重建聚变装置极向横截面中的二维辐射轮廓。重建过程是计算密集型的,并且在实践中,每个脉冲通常仅计算几个重建。在这项工作中,我们根据JET多年来制作的大量样本断层图像训练了一个深度神经网络。一旦经过训练,网络就能够以高精度重现这些结果。更重要的是,它可以在几秒钟内计算给定脉冲的所有断层重建。这使得在放电过程中可视化几种现象成为可能-例如等离子体加热,中断和杂质传输。

英文摘要:

Plasma tomography consists in reconstructing the 2D radiation profile in a poloidal cross-section of a fusion device, based on line-integrated measurements along several lines of sight. The reconstruction process is computationally intensive and, in practice, only a few reconstructions are usually computed per pulse. In this work, we trained a deep neural network based on a large collection of sample tomograms that have been produced at JET over several years. Once trained, the network is able to reproduce those results with high accuracy. More importantly, it can compute all the tomographic reconstructions for a given pulse in just a few seconds. This makes it possible to visualize several phenomena -- such as plasma heating, disruptions and impurity transport -- over the course of a discharge.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑