Fracture pressure is an important reference for wellbore stability analysis and hydraulic fracturing. Considering the low prediction accuracy, significant deviations, and limited applicability of traditional methods for predicting formation fracture pressure, this paper proposes an intelligent prediction method for fracture pressure using conventional well logging data based on the Stacking ensemble algorithm. The base learners of the model include RF, KNN, and LSTM algorithms with low correlation. The meta-learner adopts the XGBoost algorithm. The effectiveness of the model is validated using the fracture pressure data from Dagang Oilfield. The prediction results indicate that the stacking algorithm outperforms individual algorithms. After optimization with genetic algorithm, the R² of the stacking model is 0.989, RMSE is 0.009%, and MAE is 0.32%. The global sensitivity analysis results show that AC and DEN in the well logging data have higher sensitivity to the fracture pressure. When using intelligent fracture pressure prediction methods, it is essential to ensure the accuracy of AC and DEN data. The work demonstrates the reliability and effectiveness of the method proposed for the intelligent prediction of fracturing pressure using conventional well logging data through Stacking ensemble algorithm to overcome the limitations of traditional methods.

Reservoir rocks of the Pearl River Mouth Basin’s Lufeng Sag have low porosity (average porosity 12.6%) and low permeability (average permeability 16.5 mD), requiring hydraulic fracturing to obtain economic production of oil and gas. To contribute to the understanding of these reservoirs, and to promote successful production in the region, we analyzed the mechanical properties of tight sandstone. Moreover, we introduced the shear/tensile strength factor, in combination with the fracture toughness and horizontal stress difference coefficient, as an innovative approach to characterize the ease of forming a complex fracture network after reservoir fracturing. Based on this, we established a fracability evaluation model suitable for offshore low-permeability sandstone reservoirs by an analytic hierarchy process from the perspective of whether the reservoir can form an effective transformation volume and complex fracture network after fracturing. The results indicate that the primary minerals of the target reservoir are quartz and clay minerals, and the natural fractures are not developed. The mechanical properties exhibit a high Young’s modulus (ranging from 30.4 to 34.4 GPa) and high compressive strength (with cohesion between 41 and 45 MPa and an angle of internal friction between 31.0 and 33.5°). The relatively low tensile strength and fracture toughness values are conducive to fracture initiation and extension during the fracturing process. Through the fracability evaluation model constructed in this paper, the depth interval at 4155.1–4172.1 m is identified as a high-quality fractured layer. The results of this study not only provide theoretical guidance for target well and formation selection in the Lufeng Sag, but also have important practical implications for increasing oil and gas production from tight sandstone reservoirs.

Clearly determining the magnitude of fracture pressure is a crucial indicator for fracturing design. Traditional methods for predicting fracture pressure suffer from challenges such as difficulties in obtaining required data, low prediction accuracy, and local limitations in application. In light of these issues, the article proposes a fracture pressure prediction model based on reinforcement learning and XGBoost utilizing geophysical well logging data. Based on the relevance analysis, optimal input parameters, including DEPTH, DEN, AC, GR, CRL, and RT, are selected from geophysical well logging data. We have developed a framework for a fracture pressure prediction model based on XGBoost, wherein hyperparameters are fine-tuned using an improved Q-learning algorithm. The optimized XGBoost model for fracture pressure prediction attains outstanding performance metrics, including an R ² value of 0.992, a root mean square error of 0.006%, and a mean absolute error of 0.539%. In direct comparison with grid search, Bayesian optimization, and ant colony optimization, the improved Q-learning algorithm emerges as the most effective optimization approach. The predictions generated by the proposed method exhibit remarkable consistency with fracture pressure data measured on-site. This approach successfully addresses the shortcomings encountered with traditional fracture pressure prediction methods, such as inadequate accuracy, demanding data prerequisites, and constrained applicability.

Wellbore leakage mostly occurs in structurally developed fractured formations. Analyzing the real-time leakage rate during the drilling process plays an important role in identifying the leakage mechanism and its rules on-site. Based on the principles of fluid mechanics and using Herschel-Bulkley (H-B) drilling fluid, by reasonably simplifying the drilling fluid performance parameters, fracture roughness characteristic parameters, pressure difference between the wellbore and formation, and the radial extension length of drilling fluid, the radial leakage model is improved to improve the calculation accuracy. Using the Euler format in numerical analysis to solve the model and with the help of numerical analysis software, the radial leakage law of this flow pattern in the fractures is obtained. The results show that the deformation coefficient of the fracture index, fracture aperture, pressure difference, leakage rate, and cumulative leakage rate are positively correlated. The larger the curvature of the fracture, the rougher the fracture, and the smaller the leakage rate and cumulative leakage rate. The larger the consistency coefficient of the drilling fluid, the greater the additional resistance between the fractures, and the smaller the leakage rate and cumulative leakage rate. As the extending length of the fracture increases, the invasion of drilling fluid decreases, the leakage rate slows down, and eventually reaches zero, with the maximum cumulative leakage rate.