Early prediction of casing-running sticking is essential, as the mitigation of stuck-pipe incidents often incurs significant time and economic costs. Previous studies have largely relied on purely theoretical torque and drag models that are constrained by simplified assumptions, preventing them from fully leveraging available field data and often leading to insufficient prediction accuracy. To address this challenge, we developed a hybrid mechanistic-data-driven intelligent model for hook-load prediction and casing-sticking risk assessment. The model combines mechanical models with ensemble learning algorithms, incorporating both mechanically derived parameters (theoretical hook load, casing–borehole compatibility, casing-bottom deflection and tilt angle) as well as operational and casing structural features. To evaluate its cross-field generalizability, the proposed model was trained on 13,449 samples from 14 wells across three oilfields and tested on 3961 samples from an independent well in a separate Oilfield. Three ensemble algorithms (XGBoost, Random Forest, and LightGBM) were evaluated, among which XGBoost achieved the highest predictive accuracy (RMSE = 3.50, MAE = 2.51, R² = 0.97) and was selected for subsequent friction-factor-based casing sticking risk assessment. A genetic-algorithm-based optimization framework was further developed to minimize sticking risk by optimizing the centralizer configuration under a friction constraint. The proposed sticking-risk assessment and optimization strategy was validated through field implementation. This mechanistic-data-driven intelligent model outperforms traditional theoretical approaches in predictive accuracy, interpretability, and engineering applicability, providing a practical and explainable tool for casing-running risk mitigation and design optimization in complex three-dimensional wells.

To address the challenges of accurately predicting and controlling the annular equivalent circulating density (ECD) in ultra-deepwater gas hydrate-bearing formations of the Qiongdongnan Basin, where joint production of hydrates and shallow gas through dual horizontal wells faces a narrow safe pressure window and hydrate decomposition effects, this study develops an ECD prediction model that incorporates riser drilling operations. The model couples four sub-models, including the static equivalent density of drilling fluid, annular pressure loss, wellbore temperature–pressure field, and hydrate decomposition rate, and is solved iteratively using MatlabR2024a. The results show that hydrate cuttings begin to decompose in the upper section of the riser (at a depth of approximately 600 m), causing a reduction of about 2 °C in wellhead temperature, a decrease of 0.15 MPa in bottomhole pressure, and an 8 kg/m³ reduction in ECD at the toe of the horizontal section. Furthermore, sensitivity analysis indicates that increasing the rate of penetration (ROP), drilling fluid density, and flow rate significantly elevates annular ECD. When ROP exceeds 28 m/h, the initial drilling fluid density is greater than 1064 kg/m³, or the drilling fluid flow rate is higher than 21 L/s, the risk of formation loss becomes considerable. The model was validated against field data from China’s first hydrate trial production, achieving a prediction accuracy of 93%. This study provides theoretical support and engineering guidance for safe drilling and hydraulic parameter optimization in ultra-deepwater hydrate-bearing formations.