Development and Implementation of an Automated ESP Failure Database and Reliability Analysis Platform
Bibliographic record
Abstract
Abstract Identifying and prioritizing reliability improvement opportunities for ESPs, requires proper consideration of hundreds of parameters that include equipment characteristics, operational conditions, and root cause analyses results (Brookbank, E. B., 1997). One of the main challenges is that this data typically resides in a variety of commercial software products used internally by ConocoPhillips Canada as well as various other repositories such as spreadsheets, PDFs and numerous other internal databases and usually needs to be manually integrated for analysis. A second challenge is how to easily and consistently data mine such an extensive dataset. This paper presents the approach taken, hurdles faced, and results obtained to effectively address both challenges above. First, a failure database was designed to automatically capture time continuous data flows from various data streams, many of them flowing from commercial software tools but also some via email. To address the second challenge, an advanced visualizations and data analytics layer was developed to mine the database, in order to estimate various reliability and optimization metrics, uncover trends and generate forecasts instantaneously. Our solution was to create a unique cradle to grave ESP tracking and visualization integrated system, supporting the complete ESP reliability engineering workflow. It includes vendor to operator ESP equipment data transfer, database and nomenclature structure, operational data capture during the life of the ESP and RCA results data capturing via a 3rdparty low-code application development platform (LCADP). A visualization layer for data analytics and reliability metrics was seamlessly integrated through the use of a commercial software analytics and visualization platform (AVP). Results to date are very encouraging, both in terms of efficiency gains and quality of analysis and results. Consistent use of reliability metrics when used by different members of the production team have been achieved. Lessons learned during the development and specific examples on how the system is being used are presented, including AVP based trend visualization and failure forecast estimations. Key examples of the value captured with this Failure Database and Visualization Platform are also presented, including improved data quality, increased analytical capabilities and enhanced understanding of reliability improving options. The overall net benefit being optimized ESP life cycle costs. This development has the potential to be easily extended to other downhole production equipment such as fiber optic strings, liners, flow control devices, steam splitters and other artificial lift methods utilized in SAGD such as progressing cavity pumps.
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".