Bibliographic record
Abstract
Technology Focus Artificial-lift reliability is strongly influenced by how well the equipment is selected, designed, and operated for its particular application. The required artificial-lift knowledge is more than simply entering data into a software program or taking one class on the subject. We have a new generation of production engineers entering the industry who need to learn about artificial lift. How do we transfer our collective artificial-lift knowledge to them? How can we convince management that you cannot typically buy reliability from a vendor catalog and that investing in the training of their personnel is the better way to effect artificial-lift reliability? Several challenges hinder the collection and dissemination of artificial-lift information. Our fundamental knowledge of existing technology has grown immensely over the past decade. The industry has continued to push the operational envelope, resulting in modifications or new-technology development that we are just starting to implement and understand. Training materials, textbooks, and design software that were created more than 10 years ago may be outdated and no longer relevant. A wealth of artificial-lift knowledge exists that has not been well documented or is not easily assessable. Many conferences for the artificial-lift community do not publish papers; thus, the knowledge that was shared becomes lost to the rest of the industry. Operating companies have much to share with the industry on their artificial-lift applications; however, many engineers are being deterred or restricted by their company communication policies. This leaves manufacturers to fill the knowledge-sharing void, but their attempts to publish the information without the support of the operating companies is often perceived as a sales pitch. Our artificial-lift community needs to be active in documenting and sharing our collective knowledge so the next generation of production engineers can start higher on the learning curve than my generation did 20 years ago. This includes supporting SPE Artificial Lift activities (e.g., conferences, papers, online seminars, course development, online discussion groups, and PetroWiki) that are working toward the creation of resources needed to educate our future artificial-lift experts and champions. The papers highlighted in this feature are excellent examples of test programs developed to increase our artificial-lift knowledge and ultimately increase efficiency or reliability. To keep updated on the latest SPE artificial-lift events and discussions, join the SPE Connect online technical community for production at www.spe.org/network/connect.php. Recommended additional reading at OnePetro: www.onepetro.org. SPE 164382 - ESP Surveillance and Optimization Solutions: Ensuring Best Performance and Optimum Value by Abdulmonam Al Maghlouth, Saudi Aramco, et al. SPE 162006 - Development and Application of Small ESPs for Efficient Development of Remaining Reserves in Poorly Drained Parts of Reservoirs in Samotlor Field by B. Akopyan, OJSC TNK-BP Management, et al. SPE 161648 - Production Optimization and Zonal Allocation for Auto Gas Lift Wells: A Case Study From Oman by Sharifa Al-Ruheili, Petroleum Development Oman, et al.
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 | 0.002 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.002 | 0.001 |
| Scholarly communication | 0.007 | 0.004 |
| Open science | 0.001 | 0.003 |
| Research integrity | 0.004 | 0.003 |
| Insufficient payload (model declined to judge) | 0.329 | 0.205 |
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".