| dc.description.abstract | Several drilling parameters influence the rate of penetration (ROP), including formation strength, normal compaction, bottom-hole pressure differential, flow rate, weight on bit (WOB), rotary speed (RPM), bit diameter, bit tooth wear, and bit hydraulics. Due to the complexity of the mathematical models, it is difficult to calculate and predict many of the drilling parameters involved in ROP calculations in real time, which makes ROP control and analysis difficult. The purpose of this study is to automatically extract trends from real-time ROP data using a moving window trend analysis, a new data analytics approach. As a result of this work, drillers will be able to detect changes in the ROP rapidly, learn the dynamics of the ROP in real time, and make better decisions regarding the deployment of the ROP. Using the time and depth characteristics of the ROP in combination with trend data can provide new insights into reducing drilling operation costs and improving drilling efficiency.
Using qualitative trend analysis (QTA), measured signals are analyzed and extracted to extract trends. The classification of trends into stationary, falling, and rising trends is a major result of the ROP trend extraction process. Testing of this methodology will be conducted in a drilling simulation environment with high fidelity. The simulator simulates real-life drilling operations by integrating a multiphase flow model with a transient torque and drag model, a cuttings transport model, a dynamic drilling string and BHA model, and a reservoir model. Afterward, ROP data is streamed in real-time from the simulator.
By observing how drilling parameters, such as the WOB and RPM, affect the ROP in real-time simulations, the presented algorithm is able to identify, analyze, and improve ROP trends. Results of this study indicate the potential for drilling automation based on data analytics to make drilling systems safer and more efficient. In addition, this method is capable of being incorporated into an advanced drilling control hierarchy, thereby supporting drilling engineering automation and intelligent decision-making.
Keywords – Trend analysis, ROP, Real time data analytics, Drilling automation. | |
