Achieving Production Optimization Using Progressive Cavity Pumps, Artificial Neural Networks, and System-Based Monitoring
Bibliographic record
Abstract
Abstract Petrocedeño is a Venezuelan joint venture (JV) between PDVSA, Total, and Statoil. Petrocedeño operates in the San Diego field of the Junín block located in the Orinoco Belt, where over 500 lifted wells currently produce over 120,000 bpd of extra- heavy oil (7-9.5 API) using progressive cavity pumps (PCPs). Petrocedeño has extensively used down-hole sensors to monitor PCP operational parameters, such as velocity, torque, vibration, intake and discharge pressure, and temperature. Timely and proper usage of this data, incorporated with other well information and operational data, improves production optimization using proactive surveillance and diagnostics of underperforming wells. In spite of having process data in hand, it was noticed that additional optimization can be obtained by integrating the data available with articulated workflows. Initially, a pilot was conducted to evaluate technology aimed at optimizing the production of 50 wells through timely identification of underperformance occurrences. This was achieved using: Automated data gathering and integration Automated daily production rate estimation using operational data and artificial neural networks (ANNs) Customized surveillance and diagnostic workflows The technology applied was developed by integrating data and estimating well production rates on an hourly basis. This involved using trained ANNs and a leading production technology platform. In addition, continuous surveillance workflows of operational parameters as well as estimated rates and other production information were implemented on engineers’ computers through customized well and reservoir analysis software created during the pilot. After the pilot project, Petrocedeño engineers were able to reduce the time to identify underperforming wells in 20%. The positive results achieved in the mentioned pilot, encouraged the company to implement the system in the whole San Diego field, as well as introducing additional production surveillance and optimization workflows and visualization tools. This paper presents some of the main workflows implemented and the results obtained.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 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".