EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Research on Gas Pipeline Leakage Prediction Model Based on Physics-Aware GL-TransLSTM

Chunjiang Wu, Haoyu Lu, Dianming Liu, Chen Wang, Jianhong Gan, Zhibin Li iD

Biomimetics · 05.11.2025 · 10 (11) · 743

DOI: 10.3390/biomimetics10110743 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biomimetics, online erschienen am 05.11.2025. Verfasst von Chunjiang Wu und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Software Engineering, Chengdu University of Information Technology, Chengdu 610225, China. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Industrial Development Funds of Sichuan Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Natural gas pipeline leak monitoring suffers from severe environmental noise, non-stationary signals, and complex multi-source variable couplings, limiting prediction accuracy and robustness. Inspired by biological perceptual systems, particularly their multimodal integration and dynamic attention allocation, we propose GL-TransLSTM, a biomimetic hybrid deep learning model. It synergistically combines Transformer’s global self-attention (emulating selective focus) and LSTM’s gated memory (mimicking neural temporal retention). The architecture incorporates a multimodal fusion pipeline; raw sensor data are first decomposed via CEEMDAN to extract multi-scale features, then processed by an enhanced LSTM-Transformer backbone. A novel physics-informed gated attention mechanism embeds gas diffusion dynamics into attention weights, while an adaptive sliding window adjusts temporal granularity. This study makes evaluations on an industrial dataset with methane concentration, temperature, and pressure, GL-TransLSTM achieves 99.93% accuracy, 99.86% recall, and 99.89% F1-score, thereby significantly outperforming conventional LSTM and Transformer-LSTM baselines. Experimental results demonstrate that the proposed biomimetic framework substantially enhances modeling capacity and generalization for non-stationary signals in noisy and complex industrial environments through multi-scale fusion, physics-guided learning, and bio-inspired architectural synergy.

Schlagwörter

Stichwörter der Autor:innen

GL-TransLSTMadaptive sliding windowdeep learningnatural gas pipeline leakagephysics-informed gated attentiontime series forecasting

Autor:innen und Institutionen

  • School of Software Engineering, Chengdu University of Information Technology, Chengdu 610225, China.
  • Sichuan Province Engineering Technology Research Center of Support Software of Informatization Application, Chengdu 610225, China.
  • School of Automation Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China.
  • School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 610054, China.

ORCID-Profile: Zhibin Li

Förderung

  • Industrial Development Funds of Sichuan Province

Zitieren

APA

Wu, C., Lu, H., Liu, D., Wang, C., Gan, J., & Li, Z. (2025). Research on Gas Pipeline Leakage Prediction Model Based on Physics-Aware GL-TransLSTM. Biomimetics, 10(11), 743. https://doi.org/10.3390/biomimetics10110743

Vancouver

Wu C, Lu H, Liu D, Wang C, Gan J, Li Z. Research on Gas Pipeline Leakage Prediction Model Based on Physics-Aware GL-TransLSTM. Biomimetics. 2025;10(11):743. doi:10.3390/biomimetics10110743

BibTeX
@article{Wu2025,
  author = {Wu, Chunjiang and Lu, Haoyu and Liu, Dianming and Wang, Chen and Gan, Jianhong and Li, Zhibin},
  title = {Research on Gas Pipeline Leakage Prediction Model Based on Physics-Aware GL-TransLSTM},
  journal = {Biomimetics},
  year = {2025},
  volume = {10},
  number = {11},
  pages = {743},
  doi = {10.3390/biomimetics10110743}
}
Kostenlos starten →