Development of predictive optimization model for autonomous rotary drilling system using machine learning approach

• Published in: Journal of petroleum exploration and production technology 2023-10, Vol.13 (10), p.2049-2062
• Main Authors: Amadi, Kingsley, Iyalla, Ibiye, Prabhu, Radhakrishna, Alsaba, Mortadha, Waly, Marwa
• Format: Article
• Language: English
• Subjects: Artificial neutral network; Autonomous drilling system; Comparative analysis; Comparative studies; Correlation coefficient; Correlation coefficients; Drilling; Drilling machines (tools); Earth and Environmental Science; Earth Sciences; Energy demand; Energy Systems; Environmental policies; Environmental policy; Geology; Industrial and Production Engineering; Industrial Chemistry/Chemical Engineering; Machine learning; Monitoring/Environmental Analysis; Offshore Engineering; Optimization; Optimization models; Original Paper-Exploration Engineering; Parameter identification; Parameters; Penetration rate prediction; Root-mean-square errors; Rotary drilling; Specific energy; Tuning
• ISSN: 2190-0558; 2190-0566
• DOI: 10.1007/s13202-023-01656-9

The growing global energy demand and strict environmental policies motivate the use of technology and performance improvement techniques in drilling operations. In the traditional drilling method, the effort and time required to optimize drilling depend on the effectiveness of human driller in selecting the optimal set of parameters to improve system performance. Although existing work has identified the significance of upscaling from manual drilling to autonomous drilling system, little has been done to support this transition. In this paper, predictive optimization model is proposed for autonomous drilling systems. To evaluate optimized operating procedure, a comparative study of surface operating parameters using weight on bit (WOB), rotary speed (RPM) versus drilling mechanical specific energy (DMSE), and feed thrust (FET) is presented. The study used a data-driven approach that uses offset drilling data with machine learning model in finding a pair of input operating variables that serves as best tuning parameters for the topdrive and drawwork system. The results illustrate that derived variables (DMSE, FET) gave higher prediction accuracy with correlation coefficient ( R 2 ) of 0.985, root mean square error (RMSE) of 7.6 and average absolute percentage error (AAPE) of 34, whilst using the surface operating parameters (WOB, RPM) delivered an R 2 , RMSE and AAPE of 0.74, 28 and 106, respectively. Although previous researches have predicted ROP using ANN, this research considered the selection of tuning control variables and using it in predicting the system ROP for an autonomous system. The model output offers parameter optimization and adaptative control of autonomous drilling system.