Bibliographic record
Abstract
This article, written by Senior Technology Editor Dennis Denney, contains highlights of paper SPE 127860, ’Exception- Based Surveillance,’ by Jorge Yero and Thomas A. Moroney, SPE, Shell Exploration and Production Company, prepared for the 2010 SPE Intelligent Energy Conference and Exhibition, Utrecht, Netherlands, 23-25 March. The paper has not been peer reviewed. With ever-increasing amounts of data available to surveillance engineers, Lean concepts can be used to eliminate waste, allowing engineers to concentrate on the highest-value tasks by removing unnecessary analysis. An exception-based-surveillance (EBS) tool and integration of the tool into a collaborative work environment improved reservoir and facility surveillance and led to efficiencies in procedures, engineering performance, and production. Introduction Shell Upstream America’s business unit has producing assets onshore in the USA and Canada and offshore in the Gulf of Mexico and Brazil. These assets include very complex production facilities that use some of the most advanced technology available. With the complexity of these assets and the high cost of equipment and/or well failures, combined with the potential cost of lost production, it becomes necessary to monitor a wide variety of measurement points continuously on the surface and subsurface of these assets. The problem becomes more complex when external factors are considered. With increasing demand and a low-cost environment that often forces lower staff counts, companies are compelled to use the same staff resources that are required to monitor production, perform surveillance activities, and proactively determine failures to additionally participate in more-strategic and longer-term initiatives. Unfortunately, these individuals no longer have time to perform the tasks required to optimize uptime and maximize efficiency and productivity in the assets. With the lack of a shared understanding of the method, process, or procedure for surveillance or monitoring and a lack of experience with the well or equipment being analyzed, each person can miss opportunities because of a simple lack of common practices. Optimizing people’s time, standardizing their work, capturing knowledge, and establishing the ability to automate surveillance activities have become imperative. Shell developed a framework based on Lean practices that encompasses collaborative work environments, standardized analytical tools and procedures, a sophisticated event engine, automated workflows, and a knowledge-capture system. Lean Basis Several process-improvement initiatives were implemented that are based on the Lean principles of waste elimination, value-stream mapping, continuous flow, pull, and continuous improvement. The Lean concept mandated that a set of standard operating procedures (SOPs) follow each exception generated by the EBS system. Work that was performed was role based, and people executed against the highest-value work at each step. Another Lean principle was to make information visible. Andon boards, similar to call-center dashboards, enabled supervisors to load balance the work no matter where an individual was originally assigned. “Signals” were monitored for improvement opportunities when the frequency of the event was significantly higher than that of other comparable events. Finally, signals followed an assigned workflow so that when assigned work was completed by the signal recipient, the signal was passed on to a person in the appropriate role for the next level of analysis.
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 | 0.001 |
| 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".