[CCoE Notice] Thesis Defense: Analysis of Drilling Data and ROP Optimization Using Artificial Intelligence Techniques with Statistical Regression Coupling

[Grayson, Audrey A]

MASTER’S THESIS DEFENSE



ANALYSIS OF DRILLING DATA AND ROP OPTIMIZATION USING ARTIFICIAL INTELLIGENCE TECHNIQUES WITH STATISTICAL REGRESSION COUPLING


Bharat Mantha

Date: Monday, June 13, 2016

Location: Petroleum Engineering (ERP) Building 9
Room 124
Time: 10:00 am – 12:00 pm

Committee Chair: Dr. Konstantinos Kostarelos,
Committee Members:
Dr. Robello Samuel
Dr. Thomas K. Holley
Predictive data-driven analytics has the potential to successfully predict the downhole environment in Drilling Engineering. In general, rate of penetration (ROP) optimization involves adjustment of the weight on bit (WOB) and rotary speed (RPM) for efficient drilling. ROP has a complex relationship with several other parameters, such as formation properties, mud properties, mud hydraulics, borehole deviation as well as the size/type of bit. In this study, a new workflow based on statistical regression and artificial intelligence (AI) techniques was designed to predict ROP using field data gathered from the North Sea horizontal wells. Several machine-learning models such as such as step-wise regression, neural networks, support vector regression, classification-regression trees, random forests and boosting were applied for prediction. A web based prediction app was developed that could perform predictive analytics and uncertainty analysis on any data. The app was further tested on other wells and was shown to predict with significant accuracy.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://Bug.EGR.UH.EDU/pipermail/engi-dist/attachments/20160607/cb3b610e/attachment-0001.html 
-------------- next part --------------
A non-text attachment was scrubbed...
Name: publicize doc.docx
Type: application/vnd.openxmlformats-officedocument.wordprocessingml.document
Size: 14276 bytes
Desc: publicize doc.docx
Url : http://Bug.EGR.UH.EDU/pipermail/engi-dist/attachments/20160607/cb3b610e/attachment-0001.bin