Use of machine learning and data analytics to increase drilling efficiency for nearby wells

Abstract Data-driven models can be used as an efficient proxy to model complex concepts in engineering. It is common engineering practice to optimize some controllable input parameters in a model to increase efficiency of operations. Machine Learning can be used to predict the rate of penetration (ROP) during drilling to a great accuracy as shown by Hegde, Wallace, and Gray (2015). This paper illustrates the use of machine learning to predict and increase ROP effectively. The machine learning model is first used to predict ROP – with input parameters such as weight on bit (WOB), rotations per minute of the drill bit (RPM), and flow rate of the drilling mud. The input parameters are then modified to increase ROP. This process has been applied to field drilling data from a vertical well consisting of different rocks and formations. The procedure can be used to determine the maximum achievable ROP in each formation, and map out operational guidelines for drilling of pad wells. A post drilling analysis can be conducted for pad wells to cut costs and save time while drilling. This model is very innovative because only surface measured parameters are used, without a priori requirements for geological, laboratory, or drilling data.

[1]  T. M. Warren,et al.  Penetration Rate Performance of Roller Cone Bits , 1984 .

[2]  Scott Wallace,et al.  Real Time Prediction and Classification of Torque and Drag During Drilling Using Statistical Learning Methods , 2015 .

[3]  Shahab D. Mohaghegh,et al.  A New Approach for the Prediction of Rate of Penetration (ROP) Values , 1997 .

[4]  Tommy M. Warren,et al.  Roller Bit Model With Rock Ductility and Cone Offset , 1987 .

[5]  Scott Wallace,et al.  A System for Real-Time Drilling Performance Optimization and Automation Based on Statistical Learning Methods , 2015 .

[6]  R. Jahanbakhshi,et al.  Real-time Prediction of Rate of Penetration During Drilling Operation In Oil And Gas Wells , 2012 .

[7]  Scott Wallace,et al.  Using Trees, Bagging, and Random Forests to Predict Rate of Penetration During Drilling , 2015 .

[8]  Scott Wallace,et al.  Use of Regression and Bootstrapping in Drilling Inference and Prediction , 2015 .

[9]  M. Khodaverdian,et al.  Roller-Bit Penetration Rate Response as a Function of Rock Properties and Well Depth , 1986 .

[10]  M. Grant Bingham,et al.  A new approach to interpreting-- rock drillability , 1965 .

[11]  Geir Hareland,et al.  Improved Drilling Efficiency Technique Using Integrated PDM and PDC Bit Parameters , 2010 .

[12]  F. S. Young,et al.  A Multiple Regression Approach to Optimal Drilling and Abnormal Pressure Detection , 1974 .

[13]  Isabelle Guyon,et al.  An Introduction to Variable and Feature Selection , 2003, J. Mach. Learn. Res..

[14]  J. Eckel.  Microbit Studies of the Effect of Fluid Properties and Hydraulics on Drilling Rate , 1967 .

[15]  J. Ross Quinlan,et al.  Induction of Decision Trees , 1986, Machine Learning.

[16]  Jonathan Dunlop,et al.  Increased Rate of Penetration Through Automation , 2011 .

[17]  W. C. Maurer,et al.  The "Perfect - Cleaning" Theory of Rotary Drilling , 1962 .

[18]  Geir Hareland,et al.  Drag - Bit Model Including Wear , 1994 .