Visual Twin for Pipeline Leak Detection
Bibliographic record
Abstract
Abstract Objectives/Scope We describe a visual digital twin system to allow for both operation and training of a data-driven pipeline leak detection system. We show system design in terms of its data inputs and the software system which incorporates this data in real time. This system allows visualization of pipeline data and machine learning-driven leak detection in a pipeline sitting in a subsea context. The intended purpose of the system is to both train operators of the leak detection system in its use and also provide high situational awareness to those tasked with monitoring pipeline deployments. The visual digital twin system uses gaming engine technology to achieve high visual quality. We also construct a novel software system enhancement to incorporate live data streams into the gaming engine environment. This allows real-time driving of gaming engine visualization elements with which we may augment the gaming engine environment. In terms of visualization, we focus on addressing problems of large ranges of multiple scales and providing high situational awareness which minimize operator fatigue and cognitive load. We show how multiple camera views in combination with a convenient user interface can help to address these issues. We demonstrate a digital twin system for leak detection. We show its realtime operation in a gaming engine environment with the ability to instantaneously incorporate outside data sources into the visualizations. We demonstrate using simulated pipeline flow data from sensors such as pressure, temperature, etc. This is visualized in the context of a subsea pipeline on a sea floor. Given the large range of scales, we demonstrate how we can view both the full kilometer scale pipeline and smaller subsections in the context of specific sensor data streams. The overall system demonstrates a novel combination of advanced software systems which incorporates real-time data stream with visualization using a high-fidelity gaming engine. The data used represents a leak detection scenario where both operator training and situational awareness are key desired outcomes.
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.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.003 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.021 | 0.003 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".