Sign in Subscribe
Natural gas

Machine Learning Enhances Pipeline Safety in Seismically Active Fault Zones

Strategic Insights

— 2 min read

Researchers at the China University of Petroleum have combined experimental testing, numerical simulation, and machine learning to develop an advanced framework for pipeline safety assessment under seismic loading conditions. This study investigates the mechanical behavior and safety performance of buried natural gas pipelines crossing seismically active fault zones and liquefaction-prone areas, with particular application to the China-Russia East-Route Natural Gas Pipeline. The research provides robust theoretical support for pipeline routing and seismic design in high-risk zones, enhancing the safety and reliability of energy infrastructure.

Key Takeaways:

  • The research combines experimental testing, numerical simulation, and machine learning to develop an advanced framework for pipeline safety assessment under seismic loading conditions.
  • A series of large-scale pipe-soil interaction experiments were conducted under seismic-frequency cyclic loading, leading to the development of a modified soil spring model that accurately captures the nonlinear soil-resistance characteristics during seismic events.
  • Finite element analyses were systematically performed to evaluate pipeline response under liquefaction-induced ground displacement, considering key influencing factors including liquefaction zone length, seismic wave frequency content, operational pressure, and pipe wall thickness.
  • An innovative machine learning-based predictive model was developed by integrating LightGBM, XGBoost, and CatBoost algorithms, achieving remarkable prediction accuracy for pipeline strain (R-2 0.999, MAPE 2.17%).
  • The research concluded that the findings provide robust theoretical support for pipeline routing and seismic design in high-risk zones, enhancing the safety and reliability of energy infrastructure.
  • The study was funded by the Key Science and Technology Project of Ministry of Emergency Management of the People's Republic of China, National Key R&D Program of China, and Young Elite Scientists Sponsorship Program by Beijing Association for Science and Technology.
  • The research team included Hong Zhang, China University of Petroleum, Ning Shi, Tianwei Kong, Wancheng Ding, Xiaoben Liu, Xianbin Zheng, and others.

Statistics:

  • The predicted pipeline strain accuracy achieved by the machine learning-based model is R-2 0.999 (0.999).
  • The mean absolute percentage error (MAPE) of the model is 2.17% (2.17).
  • The number of large-scale pipe-soil interaction experiments conducted is not specified.
  • The study focuses on the China-Russia East-Route Natural Gas Pipeline.

Sources:

  • NewsRx. Data on Machine Learning Discussed by Researchers at China University of Petroleum (Structural Health Prediction Method for Pipelines Subjected To Seismic Liquefaction-induced Displacement Via Fem and Automl). Energy Weekly News. August 29, 2025; p 57.
  • Structural Health Prediction Method for Pipelines Subjected To Seismic Liquefaction-induced Displacement Via Fem and Automl. Processes, 2025;13(7):2163.

Read more