Rate of Penetration (ROP) Optimization through Data-Driven Approach
Description
Full text not available
Abstract
One method to lower cost and Non-Productive Time (NPT) in drilling wells is to achieve the highest rate of penetration (ROP). ROP is influenced by a variety of factors, including tooth attrition and hole cleaning. Three sections made up the study's development. Data was first chosen, cleansed, and subjected to preprocessing. The ROP model was created in the second portion using four machine learning (ML) models: Random Forest (RF), K-Nearest Neighbors (KNN), Linear Regression (LR), Polynomial Regression (PL), AdaBoost (AB), XGBoost (XGB), LightGBM (LGB) and Artificial Neural Networks. The section with the best performance was chosen.ROP was modeled and analyzed in this work. It does a regression and forecasts ROP using Bit depth, Weight on Bit (WOB), rotary speed (RPM), and pump flow rate (Q) as inputs.