EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Entropy-Driven Intelligent Diagnosis for SMR Loss of Coolant Accidents: A CNN-LSTM-Attention Hybrid Model for Break Size Assessment

Lang Yang, Jichong Lei iD

Entropy · 01.07.2026 · 28 (7) · 745

DOI: 10.3390/e28070745 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Entropy, online erschienen am 01.07.2026. Verfasst von Lang Yang und 1 weiteren Autor:innen. Beteiligte Einrichtung: School of Humanity, Shanghai University of Finance and Economics, Shanghai 200433, China. Die Arbeit nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Hengyang Social Science Fund Project, Hunan Institute of Technology, Technology innovation Program of Hunan Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate break size assessment is critical for the safety response of small modular reactors (SMRs) during loss-of-coolant accidents (LOCAs). Traditional methods struggle with the rapid transient features, strong spatiotemporal coupling, and complex uncertainty characteristics of SMR-LOCA, leading to low accuracy and poor stability. To address these issues, this study proposes an entropy-driven intelligent diagnosis approach based on a CNN-LSTM-Attention hybrid model. The framework adopts information entropy for data uncertainty quantification, adaptive weighting, and loss constraint, so as to realize high-precision break size assessment. A time-series dataset covering break sizes from 0.05 to 10 cm2 was constructed using the PCTRAN/SMART platform. The CNN module extracts spatial coupling features of multi-sensor parameters, the LSTM module captures long-term temporal dependencies, and the attention mechanism dynamically weights key information to enhance feature representation under high uncertainty. Experimental results show that the model achieves a mean absolute error (MAE) of 0.096311, reducing errors by over 64.4% compared with baseline models; more than 90% of prediction errors are within ±5%, and the correlation coefficient reaches 0.994902. Based on the well-validated PCTRAN/SMART simulation platform, the proposed entropy-informed spatiotemporal learning framework provides a technical solution for intelligent LOCA diagnosis, uncertainty quantification, and safety assessment of SMRs.

Schlagwörter

Stichwörter der Autor:innen

CNN-LSTM-Attentionbreak size assessmentdeep learningentropy-driven diagnosisloss of coolant accident (LOCA)small modular reactor (SMR)spatiotemporal feature learning

Autor:innen und Institutionen

  • School of Humanity, Shanghai University of Finance and Economics, Shanghai 200433, China.
  • School of Marxism, Hunan Institute of Technology, Hengyang 421002, China.
  • School of Safety and Management Engineering, Hunan Institute of Technology, Hengyang 421002, China.

ORCID-Profile: Jichong Lei

Förderung

  • Hengyang Social Science Fund Project
  • Hunan Institute of Technology
  • Technology innovation Program of Hunan Province
  • College Students' Innovation Plan Projects of Hunan Province
  • Open Fund of Hunan Institute of Technology
  • science and technology innovation Program of Hunan Province
  • College Students’ Innovation Plan Projects of Hunan Province

Zitieren

APA

Yang, L., & Lei, J. (2026). Entropy-Driven Intelligent Diagnosis for SMR Loss of Coolant Accidents: A CNN-LSTM-Attention Hybrid Model for Break Size Assessment. Entropy, 28(7), 745. https://doi.org/10.3390/e28070745

Vancouver

Yang L, Lei J. Entropy-Driven Intelligent Diagnosis for SMR Loss of Coolant Accidents: A CNN-LSTM-Attention Hybrid Model for Break Size Assessment. Entropy. 2026;28(7):745. doi:10.3390/e28070745

BibTeX
@article{Yang2026,
  author = {Yang, Lang and Lei, Jichong},
  title = {Entropy-Driven Intelligent Diagnosis for SMR Loss of Coolant Accidents: A CNN-LSTM-Attention Hybrid Model for Break Size Assessment},
  journal = {Entropy},
  year = {2026},
  volume = {28},
  number = {7},
  pages = {745},
  doi = {10.3390/e28070745}
}
Kostenlos starten →