MétaCan
Menu
Back to cohort
Record W3202664641 · doi:10.2118/204508-ms

Reinforcement Learning Control Scheme for Electrical Submersible Pumps

2021· article· en· W3202664641 on OpenAlexaff
Jonathan Chong, Dwayne Kelly, Shivam Agrawal, Nam Hoai Nguyen, Mauricio Monzon

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldEngineering
TopicOil and Gas Production Techniques
Canadian institutionsApache (Canada)
Fundersnot available
KeywordsReinforcement learningComputer scienceScheme (mathematics)Action (physics)Control (management)Intervention (counseling)ReinforcementState (computer science)Artificial intelligenceRisk analysis (engineering)Engineering

Abstract

fetched live from OpenAlex

Abstract Electrical submersible pumps (ESPs) are closely monitored in surveillance operations because they operate in challenging environments and are subject to stressful events that, if left without intervention, may lead to unplanned shutdowns, decreased run life, or even failures. These events can occur unannounced with different magnitudes of severity due to the large range of operating conditions. Thus, a universally prescriptive response is challenging because each well may require a tailored and dynamic course of action over time. This paper proposes leveraging a powerful multidimensional state engine known as automated events detection (AED), working together with an artificial intelligence agent, to respond to these stressful events and subsequently improve actions using a reinforcement learning (RL) scheme. Motivations of this approach are to move toward more autonomous, self-protecting systems with closed-loop actions and to achieve this at scale across many wells.

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 imitation

Not 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.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.002
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.007
Threshold uncertainty score0.013

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0010.002
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0000.000
Science and technology studies0.0000.001
Scholarly communication0.0010.000
Open science0.0010.001
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0020.000

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.

Opus teacher head0.008
GPT teacher head0.213
Teacher spread0.206 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

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".

Quick stats

Citations9
Published2021
Admission routes1
Has abstractyes

Explore more

Same topicOil and Gas Production TechniquesFrench-language works237,207