Yahia ElSayed Khamis; Shady Galal El-Rammah; Adel M Salem
Abstract
The rate of penetration plays a key role in maximizing drilling efficiency, so it is essential for the drilling process optimization and management. Traditional mathematical models have been used with some success to predict the rate of penetration in drilling. Due to the high complexity and non-linear ...
Read More
The rate of penetration plays a key role in maximizing drilling efficiency, so it is essential for the drilling process optimization and management. Traditional mathematical models have been used with some success to predict the rate of penetration in drilling. Due to the high complexity and non-linear behavior of drilling parameters with the rate of penetration, these mathematical models cannot accurately and comprehensively predict the rate of penetration. Machine learning (ML) seems to be an attractive alternative to model this complicated physical process. This research paper introduces new data-driven models used to predict ROP using different parameters such as (depth, weight on bit (WOB), revolution per minute (RPM), Torque (T), standpipe pressure (SPP), flow in pump (pumping flow rate(Q), mud weight, hours on bit (HOB), revolutions on bit, bit diameter, total flow area (TFA), pore pressure, overburden pressure, and pit volume). Data-driven models are built using two different machine learning techniques, using 1771 raw real field data. The coding is built using the python programming language. The k-nearest neighbors (KNN) model predicting ROP for the training dataset show a correlation coefficient (R2) of 0.94. The multi-layer perceptron (MLP) model predicting ROP for the training dataset show a correlation coefficient (R2) of 0.98. We can conclude that MLP has a better accuracy, and removing outliers enhances model performance.
