MétaCan
Menu
Back to cohort
Record W4414292676 · doi:10.1002/ghg.2379

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

2025· article· en· W4414292676 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenueGreenhouse Gases Science and Technology · 2025
Typearticle
Languageen
FieldEngineering
TopicNon-Destructive Testing Techniques
Canadian institutionsMemorial University of Newfoundland
FundersQatar National Research FundFonds National de la Recherche LuxembourgQatar Foundation
KeywordsLeakPipeline transportDecision treeSupport vector machinePipeline (software)Leak detectionMultiphase flowPiggingGradient boosting

Abstract

fetched live from OpenAlex

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 R 2 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.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: Bench or experimental
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.120
Threshold uncertainty score0.529

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.001
Science and technology studies0.0000.001
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.015
GPT teacher head0.281
Teacher spread0.266 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it