EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Transfer learning-driven prediction of oil and gaspipeline corrosion rates in small sample scenarios

Pujun Long iD, Guopan Yang, Haiyang Liu, Weiwei Deng, Mi Liang iD

PLOS One · 16.10.2025 · 20 (10) · e0333914

DOI: 10.1371/journal.pone.0333914 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 16.10.2025. Verfasst von Pujun Long und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Mathematical and Physical Sciences, Chongqing University of Science and Technology, Chongqing, China. Hauptthemen laut MEDLINE: Oil and Gas Industry, Natural Gas, Machine Learning. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Science and Technology Research Program of Chongqing Municipal Education Commission, Chongqing Social Science Planning Doctoral Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To ensure the safe operation of oil and gas pipeline systems in complex environments, accurately predicting the corrosion rate of natural gas well pipes is of paramount importance. Given the widespread challenge of pipe corrosion in the oil and gas industry, we propose a transfer learning model based on a CNN-LSTM-Transformer architecture with a staged fine-tuning strategy for corrosion rate prediction under small-sample conditions. The model integrates Convolutional Neural Networks (CNN), Long Short-Term Memory networks (LSTM), and Transformer modules. CNN is employed to extract local features from corrosion data. LSTM captures the temporal dependencies within the data, and the Transformer module applies multi-head attention to recalibrate features, effectively addressing long-range dependencies. To enhance the model’s adaptability, the CNN-LSTM-Transformer model is initially trained on a source domain and then progressively fine-tuned on a target domain to facilitate knowledge transfer. Experimental results demonstrate that, after staged fine-tuning, the CNN-LSTM-Transformer model achieves an MAE of 0.021, RMSE of 0.031, and an R² of 0.909, outperforming other transfer learning approaches by a substantial margin.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Oil and Gas IndustryNatural GasMachine LearningCorrosionNeural Networks, ComputerOil and Gas Fields

Substanzen

Natural Gas

Autor:innen und Institutionen

  • School of Mathematical and Physical Sciences, Chongqing University of Science and Technology, Chongqing, China.
  • School of Artificial Intelligence, Chongqing University of Science and Technology, Chongqing, China.

ORCID-Profile: Pujun Long, Mi Liang

Förderung

  • Science and Technology Research Program of Chongqing Municipal Education Commission
  • Chongqing Social Science Planning Doctoral Program

Zitieren

APA

Long, P., Yang, G., Liu, H., Deng, W., & Liang, M. (2025). Transfer learning-driven prediction of oil and gaspipeline corrosion rates in small sample scenarios. PLOS One, 20(10), e0333914. https://doi.org/10.1371/journal.pone.0333914

Vancouver

Long P, Yang G, Liu H, Deng W, Liang M. Transfer learning-driven prediction of oil and gaspipeline corrosion rates in small sample scenarios. PLOS One. 2025;20(10):e0333914. doi:10.1371/journal.pone.0333914

BibTeX
@article{Long2025,
  author = {Long, Pujun and Yang, Guopan and Liu, Haiyang and Deng, Weiwei and Liang, Mi},
  title = {Transfer learning-driven prediction of oil and gaspipeline corrosion rates in small sample scenarios},
  journal = {PLOS One},
  year = {2025},
  volume = {20},
  number = {10},
  pages = {e0333914},
  doi = {10.1371/journal.pone.0333914}
}
Kostenlos starten →