ABSTRACT: The prediction of the pore pressure is significant mainly for drilling. It can improve the quality of decisions and the drilling economics. The offered models in the literature for pressure prediction are based on well logs or a combination of some drilling data and well logs. The purpose of this work is to apply support vector machines (SVM), and functional networks (FNs) to develop two models for real-time pore pressure gradient estimation using drilling data. The used parameters are mud flow rate (Q), standpipe pressure (SPP), rate of penetration (ROP) and rotary speed (RS). The two models predicted the pore pressure gradient with a correlation coefficient (R) of 0.99 and 0.97 for training and testing. The root mean squared error (RMSE) ranged from 0.008 to 0.021 psi/ft for training and testing respectively between the predicted and the actual pore pressure data. Moreover, the average absolute percentage error (AAPE) ranged from 0.97% to 3.07% for training and testing respectively. The developed models were validated using another dataset. The models predicted the pore pressure gradient for the validation dataset with high accuracy (R of 0.99, RMSE around 0.01 and AAPE around 1.8%). This work shows the reliability of the proposed models to forecast the pressure gradient from both mechanical and hydraulic drilling data while drilling.
Pore Pressure Estimation While Drilling Using Machine Learning
Ahmed Abdelaal, A. A., Salaheldin Elkatatny, S. E., and A. A. Abdulazeez Abdulraheem. "Pore Pressure Estimation While Drilling Using Machine Learning." Paper presented at the ARMA/DGS/SEG International Geomechanics Symposium, Virtual, November 2021.
Download citation file: