PaMMA-Net: Plasmas magnetic measurement evolution based on data-driven incremental accumulative prediction

TL;DR

This paper introduces PaMMA-Net, a deep learning model that accurately predicts the evolution of plasma magnetic measurements over time, improving control and analysis in tokamak experiments.

Contribution

It presents a novel incremental prediction network tailored for magnetic measurement evolution, addressing robustness and computational efficiency issues of physical models.

Findings

PaMMA-Net outperforms existing methods in magnetic measurement evolution.

The model demonstrates high generalization on EAST experimental data.

It effectively predicts plasma parameters over extended periods.

Abstract

An accurate evolution model is crucial for effective control and in-depth study of fusion plasmas. Evolution methods based on physical models often encounter challenges such as insufficient robustness or excessive computational costs. Given the proven strong fitting capabilities of deep learning methods across various fields, including plasma research, this paper introduces a deep learning-based magnetic measurement evolution method named PaMMA-Net (Plasma Magnetic Measurements Incremental Accumulative Prediction Network). This network is capable of evolving magnetic measurements in tokamak discharge experiments over extended periods or, in conjunction with equilibrium reconstruction algorithms, evolving macroscopic parameters such as plasma shape. Leveraging a incremental prediction approach and data augmentation techniques tailored for magnetic measurements, PaMMA-Net achieves superior evolution results compared to existing studies. The tests conducted on real experimental data from EAST validate the high generalization capability of the proposed method.