Development of Digital/Visual Twin for Real‐Time Leak Detection in Gas Pipelines Under Multiphase Flow Conditions

Wahib A. Al‐Ammari, Ahmad K. Sleiti, Matthew Hamilton, Hicham Ferroudji, Sina Rezaei Gomari, Ibrahim Hassan, Rashid Hasan, Ibnelwaleed A. Hussein and Mohammad Azizur Rahman

Greenhouse Gases: Science and Technology, 2025, vol. 15, issue 5, 513-530

Abstract: Leak detection (LD) in gas pipelines (GPs) is critical for ensuring operational safety and environmental protection. This study presents a novel digital/visual twin for detecting single‐ and multiple leaks in GPs under both single‐ and multiphase flow conditions. The framework of the digital twin leverages experimental data from a multiphase flow‐testing loop and synthetic data generated using OLGA software to validate and optimize machine learning (ML) models for leak detection and localization. Several ML models, including random forest (RF), support vector machine (SVM), k‐nearest neighbors (k‐NNs), decision tree regression (DTR), and eXtreme gradient boosting (XGBoost), were tested individually for their ability to classify leak conditions and localize leaks. Initial results showed moderate performance for individual models, with accuracies ranging from 42% to 57%. However, a significant improvement was observed through the use of advanced techniques such as stacking models, feature engineering, and data averaging. The final stacking regressor model, which combined the strengths of RF, k‐NN, and SVM, outperformed the individual models, achieving R2 values exceeding 0.96 with an accuracy of 90% in complex multiple leak scenarios. The digital twin system integrates this ML framework with real‐time data visualization, allowing operators to visualize offshore pipeline conditions, detect leaks, and localize leak positions using a virtual twin representation of the physical pipeline. The virtual twin provides an interactive, high‐fidelity interface that enables users to monitor and analyze leak events as they occur, enhancing situational awareness and decision‐making capabilities. The combination of advanced ML techniques and digital twin technology provides a robust and accurate solution for real‐time LD in offshore pipelines. It significantly improves detection performance in multiphase flow conditions. This innovative approach sets a new benchmark for offshore pipeline monitoring systems, offering superior LD capabilities under a range of operational conditions. The system is readily adaptable for integration with SCADA platforms and pipeline monitoring infrastructures, supporting deployment in offshore oil and gas operations, industrial gas distribution networks, and critical energy corridors where early LD is essential.

Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://doi.org/10.1002/ghg.2379

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:wly:greenh:v:15:y:2025:i:5:p:513-530

Access Statistics for this article

More articles in Greenhouse Gases: Science and Technology from Blackwell Publishing
Bibliographic data for series maintained by Wiley Content Delivery ().