Prediction of the ROP based on GA-LightGBM and drilling data

Abstract

Listen

Translate article

ABSTRACT Constructing oil and gas wells is one of the most expensive activities in the petroleum sector, and increasing drilling speed is crucial for reducing costs, minimizing non-productive time (NPT), and improving efficiency. To address this challenge, a data-driven predictive model for mechanical drilling speed was developed using an artificial intelligence approach. Several machine learning algorithms – including decision trees, support vector regression, k-nearest neighbors, neural networks, XGBoost, and LightGBM – were selected to thoroughly investigate the nonlinear relationship between drilling data and the rate of penetration (ROP). These models were trained, evaluated, and compared, with results indicating that the LightGBM algorithm provided the most accurate ROP predictions. Building on this, the LightGBM model was further refined using cross-validation techniques and a genetic algorithm (GA) to optimize its hyperparameters, resulting in even greater accuracy. The research findings demonstrate that the GA-LightGBM algorithm achieves high precision in ROP prediction on the test set (MAE = 2.39, MSE = 10.53, R2 = 0.93). This model effectively predicts mechanical drilling speed in various well sections, thereby aiding in optimizing the drilling process, improving production efficiency, and reducing costs.