Show simple item record

dc.contributor.authorGolden, Timothy B.
dc.date.accessioned2025-02-01T02:47:01Z
dc.date.available2025-02-01T02:47:01Z
dc.date.issued2024-12
dc.identifier.urihttp://hdl.handle.net/11122/15678
dc.descriptionThesis (M.S.) University of Alaska Fairbanks, 2024en_US
dc.description.abstractThe objective of this work is to develop an accurate and practical tool for drilling engineers supporting operations to predict rate of penetration (ROP) in the tangent section of the wellbore using easily obtainable data. Historically, tacit knowledge has been used to predict both ROP and the ideal parameters. Such a tool is valuable for planners seeking to adjust rig schedules. Further, this tool could easily be modified to also optimize parameters. This work was comprised of two major efforts: data acquisition and wrangling, and modeling. Data was obtained from three distinct sources: well files, drilling logs, and survey logs. Data on bit geometry or formation was not available. This data was manually downloaded and imported into Python. Due to the size of the data, a university-owned high-performance computer (HPC) was required to process the data. Special care was given to optimizing for memory efficiencies that allowed the HPC to perform these operations. A test data set of 5 wells was used to pilot the data wrangling process and initial linear regression models. Four different model types were produced and evaluated: linear regression, polynomial regression, nonlinear regression, and neural networks. Neural networks provided the best prediction with a R2 of 0.85. The most important variables affecting ROP in the tangent section in descending order are: total pump output, rotary speed, hook load, differential pressure, and bit type. To the best of our knowledge, this is the largest dataset of ROP data found in literature; containing over 350 wells and 30 million rows of data. This workflow can be adopted to create other field-specific models or adapted to evaluate other sections of the wellbore. More immediately, this work creates a large database ready to be utilized for developing other models undergirded by different computational methodologies.en_US
dc.description.tableofcontentsChapter 1: Introduction -- 1.1 Motivation -- Chapter 2: Literature review -- 2.1 Introduction -- 2.2 Basic overview of deterministic equations -- 2.3 Bourgoyne & Young (1974) model -- 2.4 Ziaja (1985) model -- 2.5 Hareland & Rampersad (1994) model -- 2.6 Other deterministic equations of note -- 2.7 Relevant, tangential research to deterministic equations -- 2.8 Mechanical specific energy -- 2.9 Machine learning models -- 2.10 Machine learning for ROP -- 2.11 Gaps in literature and opportunity for a novel contribution -- Chapter 3: Procedure -- 3.1 Development of procedure -- 3.2 Data wrangling procedure -- 3.3 Model development and creation procedure -- 3.4 Linear regression model -- 3.5 Polynomial regression procedures -- 3.6 Nonlinear regression procedures -- 3.7 Neural network procedures -- Chapter 4: Results and discussion -- 4.1 Linear regression -- 4.2 Polynomial regression -- 4.3 Nonlinear regression -- 4.4 Neural networks -- 4.5 Discussion -- Chapter 5: Conclusions and recommendations -- 5.1 Conclusions -- 5.2 Recommendations -- 5.3 Future research opportunities -- References -- Appendix A: Linear model parameters.en_US
dc.language.isoen_USen_US
dc.subjectOil well drillingen_US
dc.subjectMathematical modelsen_US
dc.subjectData processingen_US
dc.subject.otherMaster of Science in Petroleum Engineeringen_US
dc.titleModeling rate of penetration in a south Texas oil field with aggregated well data in a supercomputing frameworken_US
dc.typeThesisen_US
dc.type.degreemsen_US
dc.identifier.departmentDepartment of Petroleum Engineeringen_US
dc.contributor.chairAwoleke, Obadare
dc.contributor.chairDas, Arghya
dc.contributor.committeeGoddard, Scott
dc.contributor.committeeMattiolli, Brandon
refterms.dateFOA2025-02-01T02:47:03Z


Files in this item

Thumbnail
Name:
Golden_T_2024.pdf
Size:
6.314Mb
Format:
PDF

This item appears in the following Collection(s)

Show simple item record