Coupling rate of penetration and mechanical specific energy to Improve the efficiency of drilling gas wells

Abstract

Drilling operations for oil or gas wells are very expensive. Optimizing the drilling efficiency and increasing the rate of penetration (ROP) will reduce the overall cost of the drilling operation. Different approaches are utilized to increase the drilling performance including analytical and empirical methods. However, most of the available models have some limitations once they applied for real-time drilling operations. This study presents a new approach for evaluating and improving the drilling operations for real-time applications. Seven ROP models were developed using artificial neural network (ANN) technique. The ANN models were developed using real field data (20,000 data sets) which includes the real-time recording of the surface drilling parameters such as rate of penetration (ROP), weight on bit (WOB), torque, rotation speed (RPM) and mud flow rate (Q). The ANN-based models are able to provide an accurate estimation for the full ROP profile. Thereafter, the predicted ROP was coupled with the calculated MSE in order to optimize the drilling performance. Moreover, and for the first time, a new (ROP/MSE) ratio is suggested, which can be used to assess the drilling operations in a real-time. A new profile of ROP/MSE ratio can be displayed along with the drilling parameter in order to provide a quick and more reliable evaluation for the ongoing drilling operation. The suggested ratio incorporates the impacts of the primary drilling factors which are the drilling speed (ROP) and the required drilling energy (MSE). Also, the seven ANN-based models, developed in this work, can predict the full profile of ROP with an average absolute percentage error (AAPE) of around 7.9% and a correlation coefficient of around 0.92.