MétaCan
Menu
Back to cohort
Record W3093974523 · doi:10.2118/201298-ms

Automated Gas Lift System Optimization Through Combined Data Analytics and Wellbore Modeling Approach: A Case Study in an Offshore Middle East Oilfield

2020· article· en· W3093974523 on OpenAlexaff
Meher Surendra, Lichi Deng, Rami Kansao, Ehsan Davani, Hamed Darabi, David Castiñeira

Bibliographic record

VenueSPE Annual Technical Conference and Exhibition · 2020
Typearticle
Languageen
FieldEngineering
TopicOil and Gas Production Techniques
Canadian institutionsImpact
Fundersnot available
KeywordsWorkflowGas liftLift (data mining)Artificial liftAutomationComputer scienceAnalyticsSystems engineeringData miningEngineeringPetroleum engineeringDatabaseMechanical engineering

Abstract

fetched live from OpenAlex

Abstract Systematic and comprehensive analysis of gas lift operations must include historical performance evaluation and heuristic diagnostics for identification of suboptimal performers. Reliable nodal analysis models are necessary to optimize the gas lift systems. Though some degree of automation is currently possible, this process still takes substantial effort and time. The work presented here is a streamlined, repeatable, and automated workflow to diagnose and optimize gas lift operation through analytics, reliable wellbore modeling and calibration that reduces the time from days to hours. The workflow is also very easily repeatable, which makes it very efficient to update when new data is available. The workflow combines the emerging data analytics efforts in the oil and gas industry along with traditional gas lift optimization guidelines to identify artificial lift-related key recovery obstacles and corresponding development plans. This novel combined approach proves the effectiveness and necessity of augmented artificial intelligence, and the case study of field analysis and execution further endorse the impact of such optimization workflow for gas lift assessment and operations. It builds from data-driven and engineering-based workflows that compute smart metrics and dashboards based on the historical well production and the gas lift systems performance. Several KPIs and metrics are utilized, some of which are industry standard while others are intuitively built exclusively for this workflow. In this paper, we present the results and challenges in applying this workflow to an offshore Middle East oilfield, with over 50 gas lift wells. As always with field data, several aspects of the data had to be addressed. Accuracy and relevancy of data was questionable. We developed several workflows to address the missing/incorrect data to ensure the robustness and credibility of the results from the workflow. Due to the practical implication of the analysis, stringent quality control and error margins were maintained throughout the analysis. No nodal analysis models were available, consequently models were built and calibrated as a part of this effort. Overall field and facility constraints were also incorporated to ensure results were achievable in the field. The optimized operational plan would yield an additional 15 to 20% gains over current production rate. Further benefits by upgrading the gas lift design are also quantified using the proposed workflow. The time required to construct, calibrate, and optimize around 50 wells was less than two weeks.

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 imitation

Not 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.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation 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: Empirical
Teacher disagreement score0.103
Threshold uncertainty score0.741

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.001
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

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 head0.126
GPT teacher head0.285
Teacher spread0.160 · 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 teacher head, 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

Citations6
Published2020
Admission routes1
Has abstractyes

Explore more

Same venueSPE Annual Technical Conference and ExhibitionSame topicOil and Gas Production TechniquesFrench-language works237,207