MétaCan
Menu
Back to cohort
Record W2751871035 · doi:10.2118/186166-ms

A Novel Probabilistic Rig Based Drilling Optimization Index to Improve Drilling Performance

2017· article· en· W2751871035 on OpenAlexaff
Adrian Ambrus, Pradeepkumar Ashok, A.. Chintapalli, Dawson Ramos, Michael Behounek, Taylor Thetford, B. NELSON

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldEngineering
TopicDrilling and Well Engineering
Canadian institutionsApache (Canada)
FundersUniversity of Texas at Austin
KeywordsDrillingComputer scienceRange (aeronautics)Measurement while drillingProbabilistic logicData miningEngineeringArtificial intelligenceMechanical engineering

Abstract

fetched live from OpenAlex

Abstract Currently, real-time adjustments to drilling parameters such as weight on bit (WOB), drillstring revolutions per minute (RPM), flow rate, etc., are based primarily on experience. This is mainly due to the uncertain nature of information (both downhole and surface) available and inability of humans to aggregate multiple data streams in real-time to make optimal decisions. The objective therefore is to build a decision support tool that can overcome these limitations by automatically aggregating this data, identifying drilling inefficiency and suggesting optimal drilling parameters. The methodology presented in this paper uses a Bayesian network to represent the drilling process and is capable of representing uncertainty in a way that is robust to bad sensor data. The model is updated in real-time and tracks variations in drilling conditions. Various dysfunctions such as bit balling, bit bounce, whirl, torsional vibrations, high mechanical specific energy (MSE), auto-driller erratic behavior, etc., are identified by tracking the movement characteristics of various sensor data in relation to model predicted values. A holistic drilling optimization index is thus derived by aggregating all this information. This index coupled with the drilling dysfunction prediction ultimately enables recommendation of drilling parameter corrections. The drilling optimization index has been integrated into a drilling rig data aggregation system currently in operation on twenty rigs in North America. The system has access to real-time data, both at low frequency (less than 1 Hz) as well as data in the 1 to 10 Hz range, and also contextual data (such as data typically available in a tour sheet or well plan). In deploying the system, human factors aspects were given significant consideration. A typical driller is not familiar with concepts such as Bayesian networks, MSE, etc. By displaying the effectiveness of drilling as a single, dimensionless parameter, an index that varies between 0 and 1, with 0 representing inefficient drilling and 1 representing optimal drilling, the message is effectively communicated to the driller. The index is currently depicted in a very intuitive "speedometer" type of visual. Values are low and closer to 0 when dysfunctions occur, and when that happens suggestions are provided on how to mitigate the dysfunctions. These suggestions are visually presented in the form of operational cones in the WOB-RPM space. Additionally, the variation of the index with drilling depth is displayed to enable the driller to identify how formation changes impact drilling performance. This was found to be useful to drilling engineers who are generally tasked with optimizing the drilling process.

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: Methods · Consensus signal: none
Teacher disagreement score0.884
Threshold uncertainty score0.990

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 communication0.0000.000
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 head0.009
GPT teacher head0.197
Teacher spread0.187 · 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
GenreMethods

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

Citations22
Published2017
Admission routes1
Has abstractyes

Explore more

Same topicDrilling and Well EngineeringFrench-language works237,207