PaMMA-Net: Plasmas magnetic measurement evolution based on data-driven incremental accumulative prediction
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917901439598592 |
|---|---|
| author | Ling, Yunfei Liu, Zijie Du, Jun Huang, Yao Wang, Yuehang Xiao, Bingjia Fang, Xin |
| author_facet | Ling, Yunfei Liu, Zijie Du, Jun Huang, Yao Wang, Yuehang Xiao, Bingjia Fang, Xin |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_14003 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PaMMA-Net: Plasmas magnetic measurement evolution based on data-driven incremental accumulative prediction Ling, Yunfei Liu, Zijie Du, Jun Huang, Yao Wang, Yuehang Xiao, Bingjia Fang, Xin Plasma Physics Artificial Intelligence 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. |
| title | PaMMA-Net: Plasmas magnetic measurement evolution based on data-driven incremental accumulative prediction |
| topic | Plasma Physics Artificial Intelligence |
| url | https://arxiv.org/abs/2501.14003 |