Unsupervised PSD Clustering to Assess Reservoir Quality Along the Horizontal Wells: An Efficient Inflow Control Devices Design
Bibliographic record
Abstract
Abstract In steam-assisted gravity drainage (SAGD) operations, inflow control devices (ICDs) might provide an extra pressure drop (ΔP) on top of the liquid pool's ΔP. To avoid hot-spot zones, this ΔP design heavily relies on reservoir quality. Flow-loop experiments can provide flow قate measurements versus ΔP for various nozzle designs. Therefore, an efficient ICD design should be investigated in a numerical flow simulation that represents reservoir quality and heterogeneity by employing flow-loop data. In this study, core analysis and 40 PSD data drilled in the same location are collected, and permeability for each PSD is estimated using a correlation developed in our previous study. Given PSD offers a measure of hydraulic properties and heterogeneity, it can provide an indirect indicator of potential hot-spot zones. Moreover, representative PSDs are determined by using a clustering algorithm to tie the best-designed ICD to the relevant geology. The reservoir model for the database's location is generated using real data, three tabular data from flow-loop experiments are assigned to the reservoir simulation, and the ICDs' performances are compared. The clustering algorithm generated five groups with a weighted average permeability of 4,013 mD. The first and second largest clusters with 6.55% and 35.05% fines content cover 55% and 23% of the database, respectively. By employing a relatively conservative production with subcooling between 10°C and 15°C, the cases with liner deployed (LD) ICDs offered a greater oil production rate, better steam conformance, and lower cumulative steam oil ratio (cSOR) than the cases without ICDs. However, in a rather risky production scenario with subcool between 1°C and 5°C, the case without ICDs could not be simulated in the desired the subcool temperature. Because of its enhanced steam conformance and slightly higher oil production rate, LDICD#1 was picked as the best case for the two scenarios. Compared to the case without ICDs, the oil production rate and cSOR for the case with LDICD#1 at higher subcool temperature rose by 17% and reduced by 8%, respectively. Compared to the case without ICDs, the oil production rate and cSOR for the case at lower subcool temperature with LDICD#1 raised by 21% and reduced by 12%, respectively. The findings demonstrate the effectiveness of ICDs at various subcool levels. The results could be applied in SAGD projects to reduce greenhouse gas emissions by reducing the water and natural gas usage to generate steam. Completion and production engineers would benefit from a better understanding of production relative performance to develop more effective operations design.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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 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".