SPE Journal最新文献

The logging-while-drilling (LWD) ultradeep azimuthal electromagnetic tool plays a pivotal role in real-time drilling optimization operations. Established tool designs include arrays of coaxial and tilted coils that, during drilling operations, can be processed to a multicomponent magnetic induction data. These data can then be combined into different detection modes, which accentuate sensitivity to particular geological features. Leveraging the established coil design and definitions of various detection modes for an electromagnetic look-ahead (EMLA) tool, this study undertakes a comprehensive exploration of the disparities in detection performance and characterization of subsurface parameters. Through sensitivity analysis, the varying degrees of sensitivity exhibited by these detection modes concerning parameters such as subsurface formation resistivity, formation inclination, and electrical anisotropy have been investigated. The ensuing conclusions derived from an in-depth analysis are as follows: Detection Mode I exhibits remarkable prowess in delineating subsurface boundaries. Optimal exploration distances can be achieved through the judicious selection of source-receiver distances and frequencies. Detection Mode II displays heightened sensitivity to wellbore inclination and anisotropy, effectively elucidating subsurface resistivity anisotropy. This sensitivity is particularly pronounced at wellbore inclinations approaching 60°. Detection Mode III, while lacking directional capability, nonetheless furnishes fundamental insights into subsurface resistivity. Detection Mode IV demonstrates exceptional sensitivity to electrical anisotropy, particularly at higher wellbore inclinations, manifesting a conspicuous response to subsurface resistivity anisotropy. In summary, the diverse detection modes within the realm of ultradeep azimuthal electromagnetic technology each offer distinctive attributes, facilitating optimal mode selection to attain superior outcomes as per specific requisites. This research contributes significantly to an enhanced comprehension of the performance and applicability of the ultradeep azimuthal electromagnetic tool in the field of optimal drilling.

The grain size distribution along the well depth is of great significance for the prediction of the physical properties and the staged sand control design of the unconsolidated or weakly consolidated sandstone reservoir. In this paper, a new method for predicting the formation median grain size profile based on the combination model of extreme gradient boosting (XGBoost) and artificial neural network (ANN) is proposed. The machine learning algorithm and weighted combination model are applied to the prediction and analysis of reservoir grain size. The prediction model is improved from two aspects: First, the feature engineering of the XGBoost-ANN model is constructed by using the data of multiple sampling points on the logging curve. Second, the prediction accuracy is improved by increasing the dimension of the prediction model, that is, the XGBoost and ANN single-prediction models are weighted by the error reciprocal method and a combined prediction model containing multidimensional information is established. The research results show that compared with the single-point mapping model, the prediction accuracy of the multipoint mapping model considering the vertical geological continuity of the reservoir is higher than that of the single-point prediction and the coefficient of determination in the testing set can be improved up to 14.5%. The influence of different weighting methods on prediction performance is studied, and the prediction performance of original XGBoost, ANN, and XGBoost-ANN combined models is compared. The combined prediction model has a higher prediction accuracy than the single XGBoost and ANN models with the same number of sampling points and the coefficient of determination can be improved by up to 16.5%. The prediction accuracy and generalization ability of the XGBoost-ANN combined model are evaluated comprehensively. The combined model is used to design layered sand control of a well in an adjacent block, and good results have been achieved in production practice. This study provides a new method with high accuracy and efficiency for the prediction of unconsolidated sand median grain size profile.