Feature investigation on the ROP machine learning model using realtime drilling data

Abstract

To meet the demand for reducing drilling costs in petroleum engineering, improving drilling efficiency is one of the main objectives in field operations. Highly accurate prediction of ROP is an essential basis for improving drilling efficiency and reducing development cycle time. However, realtime prediction of the Rate of Penetration (ROP) is not straightforward, affected by a number of operational and mechanical parameters. The interactions between these parameters also complicated the analysis and modeling ROP. In the presented study, we apply the Feature Engineering approach to analyze the features affecting ROP according to their relevance and relative importance. In addition, the input features are reduced from 14, manually selected based on physical relevance, to optimized 8. Then the model is retrained again for comparing the accuracy of the two prediction models. As a result, it is concluded that by reducing the input of low impact features, the model is substantially simplified, while there are only insignificant accuracy changes.