Developing an Efficient Drilling System by Coupling Torque Modelling with Mechanical Specific Energy

Abstract

Understanding the formation behavior and the drilling operation is essential to optimize the performance of drilling systems. Several studies were conducted to improve the drilling operation in real time basis utilizing different approaches. Numerous mathematical models (analytical or empirical) were developed to relate the drilling parameters with the rate of penetrations and to predict the drilling efficiency. However, these models are arrived at by ignoring some parameters or employing simplifying assumption(s), which may lead to over or under optimistic drilling performance. The main objective of this research is to investigate the analytical and numerical approaches to calculate the torque and drag in drilling operations and produce a simple and robust model using artificial intelligent techniques. More than 22,000 data point from several wells for depth up to 18,000 ft. was used to develop and validate the model reliability. The full profiles of torque and rate of penetrations was determined, also the required energy for drilling each section has been estimated. The developed model could be utilized to define the optimum range for torque, which leads consequently to generate an efficient drilling system and reduce the drilling cost. In this study, rate of penetration (ROP) was determined using the torque profile and mechanical specific energy (MSE) based on real time and rig-site data. Statistical analysis was conducted to understand the importance of drilling parameters on the variations of torque and rate of penetration. Drilling parameters such as weight on bit (WOB), revolution per minute (RPM), fluid circulation rate (Q), and bit hydraulic horse power (HPb) has been studied. Thereafter, artificial neural network (ANN) model was developed to predict the torque and ROP profiles. The suggested models enable the drilling engineers to optimize the drilling parameters in a real-time manner, by changing the surface and controllable parameters in such a way that maintains the drilling operations within the optimum conditions. This research will assist in improving the operations efficiency through optimizing the drilling parameters. A strong robust model was developed which yields high accuracy results when compared with actual field measurements, average absolute percentage error of less than 6.5% was achieved.