Case-Based Reasoning Technology Used to Provide Early Indications of Potential NPT-Related Problems while Drilling the Viking
Bibliographic record
Abstract
Abstract There is a considerable value proposition for drilling personnel to be able to use real-time data and have an intelligent technology scan for potential problems before they are realized. To then further offer resolution options for the potential problem is an even greater value proposition. Use of automated intelligent technologies to interpret data and alert users of potential problems is in existence for many commercial and industrial applications. These technologies are frequently employed in surveillance systems such as traffic control, security, and internet usage. The historic challenge for most of these technologies in field applications is that many of the problem scenarios have varying degrees of parameter differences. As such, rule-based technologies have not met expectations. This challenge has been resolved through use of an intelligent technology that evaluates and ranks a problem scenario’s parameters based on case similarity. In other words, this technology compares the relative differences of problem parameters to baseline case history problem parameters. This approach is a much better representation of reality in the field, where no two problems are exactly the same – they are only similar. An intelligent real-time technology utilizing case-based reasoning can now be deployed in drilling operations to help recognize and mitigate non-productive time problems before they occur, thereby improving overall drilling efficiency. This software technology recalls human and situational experience across rigs, assets and regions. By continuously monitoring the real-time data-streams from ongoing drilling operations, it compares the current situation with past experience (cases). When the current situation is similar to a case, an alert is sent to users and the case is displayed along with lessons learned, advice and best practices. This technology was successfully deployed in a proof of concept with junior oil company, drilling the Viking formation. This paper highlights the theory behind the technology, deployment and integration with the junior oil company, and the results of the project, including a case study in which the technology sent an alert of a potential stuck pipe incident and suggested remedial actions to address the problem before it occurred. This paper concludes with how the technology can be continually adapted to new downhole drilling challenges.
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 | 0.004 | 0.018 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.005 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.004 | 0.003 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.010 | 0.002 |
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".