Prediction of Equivalent Circulation Density of Drilling Fluids Using Machine Learning

Résumé fourni par la source

Abstract This study demonstrates a reliable approach, integrating comprehensive statistical analysis, correlation evaluation, and the use of Machine Learning (ML) models to predict drilling fluids’ Equivalent Circulation Density (ECD). By utilizing a dataset from drilling operations, encompassing parameters such as formation depth, mud weight, viscosity, flow rate, revolutions per minute (RPM), weight on bit, total flow area (TFA), and ECD, we uncovered inverse linear relationships between ECD and both flow rate and TFA, while other relationships were positive. The ML models, particularly the Random Forest Regressor and XGB Regressor, showcased robust performance in predicting ECD. The feature importance analysis underscored key variables influencing ECD calculation, providing reliable insights to enhance drilling techniques and safety measures.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.