EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Implementing deep learning-based disruption prediction in a drifting data environment of new tokamak: HL-3

Zongyu Yang, Wulyu Zhong, Fan Xia, Zhe Gao, Xiaobo Zhu, Jiyuan Li, Liwen Hu, Zhaohe Xu, Da Li, Guohui Zheng, Yihang Chen, Junzhao Zhang und 12 weitere

Nuclear Fusion · 01.02.2025 · 65 (2) · 026030

DOI: 10.1088/1741-4326/ada396 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Nuclear Fusion, online erschienen am 07.01.2025. Verfasst von Zongyu Yang und 23 weiteren Autor:innen. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Sichuan Province Innovative Talent Funding Project for Postdoctoral fellows, National MCF R&D program of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

A deep learning-based disruption prediction algorithm has been implemented on a new tokamak, HL-3. An Area Under receiver-operator characteristic Curve of 0.940 has been realized offline over a test campaign involving 72 disruptive and 240 non-disruptive shots, despite the limited training data available from the initial two campaigns. In addition to the well-documented challenge of insufficient training data, a previously unanticipated issue is addressed that the data distribution of a new device is continuously drifting. The plasma scans across a broad parameter space, bringing a drifting distribution of disruption causes and diagnostic data. This problem is often overlooked in previous implementations on steadily operating tokamaks, necessitating greater attention in future tokamaks like ITER. To address these challenges, innovative modules including predict-first neural network, data augmentation, and pseudo data placeholders are developed and implemented, which promotes the accuracy by up to 20%. A series of advantages are also brought by the modules, including the robustness in handling missing input channels, and the interpretability to identify which parameter of plasma is under abnormal condition. The results demonstrate that, with dedicated data collection and algorithm implementation, the issues of limited data and drifting distribution can be overcome, and further, the deep learning-based algorithm can reliably provide disruption alarms on a new tokamak.

Förderung

  • National Natural Science Foundation of China
  • Sichuan Province Innovative Talent Funding Project for Postdoctoral fellows
  • National MCF R&D program of China

Zitieren

APA

Yang, Z., Zhong, W., Xia, F., Gao, Z., Zhu, X., Li, J., Hu, L., Xu, Z., Li, D., Zheng, G., Chen, Y., Zhang, J., Li, B., Zhang, X., Zhu, Y., Tong, R., Dong, Y., Zhang, Y., Yuan, B., …, & Xu, M. (2025). Implementing deep learning-based disruption prediction in a drifting data environment of new tokamak: HL-3. Nuclear Fusion, 65(2), 026030. https://doi.org/10.1088/1741-4326/ada396

Vancouver

Yang Z, Zhong W, Xia F, Gao Z, Zhu X, Li J, et al. Implementing deep learning-based disruption prediction in a drifting data environment of new tokamak: HL-3. Nuclear Fusion. 2025;65(2):026030. doi:10.1088/1741-4326/ada396

BibTeX
@article{Yang2025,
  author = {Yang, Zongyu and Zhong, Wulyu and Xia, Fan and Gao, Zhe and Zhu, Xiaobo and Li, Jiyuan and Hu, Liwen and Xu, Zhaohe and Li, Da and Zheng, Guohui and Chen, Yihang and Zhang, Junzhao and Li, Bo and Zhang, Xiaolong and Zhu, Yiren and Tong, Ruihai and Dong, Yunbo and Zhang, Yipo and Yuan, Boda and Yu, Xin and He, Zongyuhui and Tian, Wenjing and Gong, Xinwen and Xu, Min},
  title = {Implementing deep learning-based disruption prediction in a drifting data environment of new tokamak: HL-3},
  journal = {Nuclear Fusion},
  year = {2025},
  volume = {65},
  number = {2},
  pages = {026030},
  doi = {10.1088/1741-4326/ada396}
}
Kostenlos starten →