A New Hybrid Analytical-Machine Learning Method for Real-Time ROP Modeling

Abstract

Real-time drilling optimization refers to operations and equipment that could minimize total drilling costs. Drilling speed that is called the rate of penetration (ROP) in the drilling industry can be used as a good indicator for the performance evaluation of the drilling operation. Real-time control for drilling ROP is limited to just a few controllable parameters during drilling operations, that is, WOB, RPM, and hydraulics. These parameters can be controlled from the surface by the driller in real-time. In the traditional methods of ROP modeling, an inflexible equation could be developed between some important effective drilling parameters such as weight on the bit or bit rotational speed and drilling rate of penetration. These models had a low degree of accuracy, and they were not applicable in the newly drilled wells even in the same field with an acceptable degree of accuracy. In this study, a new real-time continues-learning method for ROP modeling was developed. In this method, as the drilling operation gets starts and the drilling data reaches the surface, ROP modeling starts, and as the drilling continues, the model accuracy increases. For the method evaluation, 5 famous existing analytical drilling model was selected. Also, a new ROP model was developed in this work. All of these 6 models contain some constant coefficients that were obtained using a new machine learning method named Rain Optimization Algorithm. In the end, the accuracy of the models was compared. Results show that the presented method for ROP modeling is a very flexible method with a high degree of accuracy that can be easily used in any formation. Also, the newly presented model could increase the accuracy of ROP prediction from 75% to 81%.