Open Access

Digital Twin-Based Real-Time Monitoring and Intelligent Maintenance System for Oil and Gas Pipelines

Yihan Wang

Yihan Wang

College of Petroleum and Natural Gas Engineering, Southwest Petroleum UniversitySichuan, China
Search for this author on
Sciendo|Google Scholar
Wang, Yihan
  
Apr 11, 2025
Digital Twin-Based Real-Time Monitoring and Intelligent Maintenance System for Oil and Gas Pipelines's Cover Image
About this article
Previous Article
Next Article
Cite
Download Cover
Published Online: Apr 11, 2025
Received: Nov 05, 2024
Accepted: Mar 05, 2025
DOI: https://doi.org/10.2478/amns-2025-0849
Keywords
© 2025 Yihan Wang, published by Sciendo
This work is licensed under the Creative Commons Attribution 4.0 International License.

Figure 1.

Overall workflow of the digital twin-based monitoring and maintenance system. Data from pipeline sensors are incorporated into the digital twin via the EnKF, and the updated states are analyzed by a machine learning module. Anomalies trigger maintenance actions, and the entire process adapts over time through continual retraining and model refinement.
Overall workflow of the digital twin-based monitoring and maintenance system. Data from pipeline sensors are incorporated into the digital twin via the EnKF, and the updated states are analyzed by a machine learning module. Anomalies trigger maintenance actions, and the entire process adapts over time through continual retraining and model refinement.

Figure 2.

Experiment 1 (Baseline Condition): Average residual magnitude remains low and stable, indicating accurate alignment between sensor data and model forecasts.
Experiment 1 (Baseline Condition): Average residual magnitude remains low and stable, indicating accurate alignment between sensor data and model forecasts.

Figure 3.

Experiment 2 (Localized Corrosion): Wall thickness loss over time with the red dashed line indicating the point when the machine learning module issued a high-confidence anomaly alert.
Experiment 2 (Localized Corrosion): Wall thickness loss over time with the red dashed line indicating the point when the machine learning module issued a high-confidence anomaly alert.

Figure 4.

Experiment 3 (Combined Leak and Blockage): Timeline showing the onset and detection of two simultaneous anomalies. Dashed lines mark the true start of each anomaly, and dots indicate when the system raised alarms.
Experiment 3 (Combined Leak and Blockage): Timeline showing the onset and detection of two simultaneous anomalies. Dashed lines mark the true start of each anomaly, and dots indicate when the system raised alarms.
Language:
English
Publication timeframe:
1 times per year
Journal Subjects:
Life Sciences, Life Sciences, other, Mathematics, Applied Mathematics, General Mathematics, Physics, Physics, other
Journal RSS Feed