Nuclear Fusion Knowledge Graph Guided Edge-Localized Mode Recognition on EAST
Abstract
Edge-localized modes (ELMs) are transient magnetohydrodynamic instabilities commonly observed in tokamak plasmas. Although deep time-series models can learn complex dynamic patterns from multi-diagnostic signals, their predictions are mainly data-driven and lack explicit utilization of ELM physics, plasma operating states, and historical discharge experience. As a result, they may confuse categories with similar temporal patterns, particularly under severe class imbalance. To address this issue, we propose KGF-ELM, a Knowledge Graph Fusion Network for ELM Recognition, and introduce a Knowledge Graph Collaborative Fusion Module (KGCFM) that organizes physical evidence from the current time window, ELM prototypes, relational knowledge graph representations, and similar historical discharge cases into complementary multi-source knowledge representations. KGCFM collaboratively models these knowledge sources through physics prototype matching, graph-structured knowledge encoding, historical case retrieval, cross-evidence consistency analysis, and reliability estimation, thereby generating knowledge representations for enhancing temporal features and correcting classification results. Based on this module, KGF-ELM employs a dual-level reliability-aware fusion mechanism. At the feature level, physical residuals and graph-guided knowledge representations are adaptively incorporated into temporal features according to their reliability. At the decision level, reliability gating, minority-class protection, and bounded knowledge correction are used to safely refine the classification results and reduce the negative influence of unreliable knowledge on the base model.
Related
- Nuclear landscape based on point-coupling density functional with localized exchange terms
- Localized Hybrid Analytical-Finite-Element Thermal Modeling for Laser Powder Bed Fusion
- Towards Stellarator Geometry Optimisation for Nuclear Fusion
- Towards Large-Scale Heterogeneous Data Organization for Scientific Foundation Models: A Nuclear Fusion Case Study
- Machine Learning Meets High-Energy Nuclear Physics: From Pattern Recognition to Physics-Integrated Discovery
BibTeX
@misc{lyu2026nuclear,
title = {{Nuclear Fusion Knowledge Graph Guided Edge-Localized Mode Recognition on EAST}},
author = {Wanli Lyu and Laiqi Qian and Xiao Wang and Qingquan Yang and Zehua Chen and Dengdi Sun and Guosheng Xu and Jin Tang},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.00244},
eprint = {2610.00244},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.00244},
}
RIS
TY - UNPB
TI - Nuclear Fusion Knowledge Graph Guided Edge-Localized Mode Recognition on EAST
AU - Wanli Lyu
AU - Laiqi Qian
AU - Xiao Wang
AU - Qingquan Yang
AU - Zehua Chen
AU - Dengdi Sun
AU - Guosheng Xu
AU - Jin Tang
PY - 2026
DA - 2026/10/01
PB - arXiv
DO - 10.48550/arxiv.2610.00244
UR - https://arxiv.org/abs/2610.00244
AB - Edge-localized modes (ELMs) are transient magnetohydrodynamic instabilities commonly observed in tokamak plasmas. Although deep time-series models can learn complex dynamic patterns from multi-diagnostic signals, their predictions are mainly data-driven and lack explicit utilization of ELM physics, plasma operating states, and historical discharge experience. As a result, they may confuse categories with similar temporal patterns, particularly under severe class imbalance. To address this issue, we propose KGF-ELM, a Knowledge Graph Fusion Network for ELM Recognition, and introduce a Knowledge Graph Collaborative Fusion Module (KGCFM) that organizes physical evidence from the current time window, ELM prototypes, relational knowledge graph representations, and similar historical discharge cases into complementary multi-source knowledge representations. KGCFM collaboratively models these knowledge sources through physics prototype matching, graph-structured knowledge encoding, historical case retrieval, cross-evidence consistency analysis, and reliability estimation, thereby generating knowledge representations for enhancing temporal features and correcting classification results. Based on this module, KGF-ELM employs a dual-level reliability-aware fusion mechanism. At the feature level, physical residuals and graph-guided knowledge representations are adaptively incorporated into temporal features according to their reliability. At the decision level, reliability gating, minority-class protection, and bounded knowledge correction are used to safely refine the classification results and reduce the negative influence of unreliable knowledge on the base model.
ER -