MétaCan
Menu
Back to cohort
Record W3199903924 · doi:10.2118/205984-ms

A Real-Time Probabilistic Slide Drilling Dysfunction Advisory to Assist Remote Directional Drilling Operations

2021· article· en· W3199903924 on OpenAlexaff
Dawson Ramos, Pradeepkumar Ashok, Michael Yi, John Angelo, Ian Rostagno, Spencer Bohlander, Taylor Thetford, James Moisan, Michael Behounek, Mickey Noworyta, Jason Beasley, Joshua Kyle Wilson

Bibliographic record

VenueSPE Annual Technical Conference and Exhibition · 2021
Typearticle
Languageen
FieldEngineering
TopicDrilling and Well Engineering
Canadian institutionsApache (Canada)
Fundersnot available
KeywordsDrillingMeasurement while drillingDirectional drillingProbabilistic logicBayesian networkComputer scienceCrewMissileSimulationArtificial intelligenceEngineeringMechanical engineering

Abstract

fetched live from OpenAlex

Abstract Current slide drilling practices rely heavily on the intuition of the directional drillers to identify and correct drilling dysfunctions. Monitoring numerous dysfunctions simultaneously requires more complex analysis than can be done manually in real-time. There is also currently a big shift towards remote directional drilling. And as such, there is the need for a tool that can, in real-time, diagnose slide drilling dysfunctions accurately and provide advisory to both the remote directional drillers and rig crew. This paper proposes a method for a real-time slide drilling advisory system consisting of a probabilistic model which computes the likelihood that various slide drilling dysfunctions are occurring and an algorithm that determines what corrective action, if any, should be taken as a result. The dysfunction types monitored include buckling, high friction, poor toolface control, stick slip, and bit bounce. The model employs a Bayesian network which uses evidence derived from transient drilling data trends to infer the probability that any of the five considered dysfunctions are taking place. Data trends known to correlate with each dysfunction type are considered simultaneously to ensure that all dysfunction types are monitored continuously. As dysfunction probabilities are calculated, the algorithm cross references them with current drilling parameters and contextual data to determine necessary corrective actions. Corrective actions are output in the form of simple drilling parameter changes shown on a customizable graphical display. The dysfunction beliefs calculated were validated using historical data gathered from North America land drilling operations. For high friction and poor toolface control, known instances of dysfunction were identified using information in drilling logs and expert opinion and used for validation. The validation process resulted in a further refinement of the model. The proposed model along with graphical advisory displays were deployed on rigs in several North American land well drilling operations, as well as in the remote directional drilling center. While there is a lot of prior work that enables identification of rotary drilling dysfunctions in real-time, this is the first method that diagnoses slide drilling dysfunctions in real-time. The approach combines physics based models with a Bayesian network to improve accuracy and robustness in dysfunction detection. Additionally, it considers both real-time drilling data as well as drilling data from the past when diagnosing dysfunctions and facilitates remote directional drilling.

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: none
Teacher disagreement score0.759
Threshold uncertainty score0.923

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 head0.013
GPT teacher head0.227
Teacher spread0.214 · 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

Citations5
Published2021
Admission routes1
Has abstractyes

Explore more

Same venueSPE Annual Technical Conference and ExhibitionSame topicDrilling and Well EngineeringFrench-language works237,207