A data-driven bit projection system with motor yield prediction and advisory for directional drilling and well trajectory control

Abstract

In the evolving of the oil and gas industry, where innovation and technological advancement are paramount, directional drilling stands as a pioneering technique that has revolutionized the extraction of hydrocarbon resources from beneath the Earth's surface. For drilling with mud motor, accurate projection of bit position from the latest survey and comprehensive evaluation of the current motor yield (MY) are essential to avoiding early well trajectory deviation and optimizing future directional plans. Currently, these responsibilities primarily rest on the shoulders of directional drillers (DDs), consuming valuable drilling operation time and being subject to biased human judgments. In this study, a data-driven bit projection system for directional drilling optimization and well trajectory control is developed. A kinematic model is first constructed for the projection of bit inclination (INC), azimuth (AZI), and north-east-vertical (NEV) in drilling with mud motors. Moreover, in scenarios involving curve section slide drilling, a machine learning model is developed to predict instant MYs observed between surveys, which is trained and tested on a dataset comprising drilling over 350 Delaware Basin curve section stands. Ultimately, a low MY reasoning algorithm is proposed to identify the dominant factor that causes the suboptimal MY output and provides recommendations for upcoming drilling plans. The proposed system is validated using 1189 vertical stands, 240 curve stands, and 1837 lateral stands from 17 different wells. The validation results illustrate that the bit NEV projection error averages below 0.82 ft for 90-foot surveys in vertical/lateral sections. In curve sections, the average MY prediction error is 0.96° one hundred feet or 7.6% in the relative sense and the average 30-foot bit NEV projection error is 0.228 ft, with the predicted MY as input. Compared with the physics-based bottomhole assembly (BHA) bending model and other data-driven approaches in the literature, the proposed system sees a large improvement in MY prediction and the bit NEV projection accuracies. With the minimal input data requirements, fast computation speed, and accurate projection/prediction results, the proposed bit projection system holds the opportunity of application in the autonomous directional drilling system, real-time drilling job evaluations, and well trajectory optimization.