Use of Rigorous Multiphase Flow Models for Leak Detection and Online Flow Assurance
Bibliographic record
Abstract
Abstract Cenovus Energy has deployed a rigorous multiphase flow assurance online solution to detect leaks and monitor hydrate formation conditions at the White Rose Field and satellite extensions 350 km east of St. John's, Newfoundland and Labrador, Canada. Twenty-five production wells are connected via subsea manifolds to the SeaRose floating production storage and offloading (FPSO) system, through four flexible flowlines and risers. An online subsea advisor has been developed to provide control-room operators with enhanced monitoring/visibility in detecting potential leaks and hydrate formation within the subsea system, including the mechanical flowline connectors. The online solution makes use of a commercial multiphase flow simulator. An online real-time mode (RTM) was developed to simulate the production loops connecting the manifolds to the SeaRose FPSO. The wells are equipped with multiphase flowmeters, which are calibrated at regular intervals during well test campaigns. Reconciled flow rates from the meters are used as inlet boundary conditions to the real-time multiphase model. This RTM acts as a digital twin of the production network. As part of the online subsea advisor leak detection system (LDS), Schlumberger has delivered improved algorithms for leak detection in multiphase production networks. The solution makes use of 14 signatures indicating leaks, which form the basis for a generalized multivariable LDS. Artificial intelligence and data clustering are used to determine whether the signature vector indicates a leak. By making use of multiple leak signatures, the system becomes more robust with respect to sensor faults and drift. Multiple signatures also reduce the number of false alarms and make the LDS less dependent on model calibration. The use of signatures, artificial intelligence and data clustering is new compared to traditional mass balance model-based LDS. The theory is described with results from four of these 14 signatures in the paper. The advisor system monitors the potential for hydrate formation conditions and calculates the hydrate margin at the flowline connectors, which have been identified as potential "cold spots." A rigorous flowline connector model has been implemented at positions along the flow path where they exist in the field. This model is fine-tuned to estimate mechanical flowline connector wall temperatures. This gives the control-room operators a realistic estimate of reaction time to manage an emergency shutdown and initiates an alarm when hydrate conditions will be reached, prompting immediate action of predefined safeguard measures.
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 distilled prediction
Teacher imitationNot 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.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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.
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 teacher head, 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".