Rate of penetration (ROP) is crucial for evaluating drilling efficiency, with accurate prediction essential for enhancing performance and optimizing parameters. In practice, complex and variable downhole environments pose significant challenges for mechanistic ROP equations, resulting in prediction difficulties and low accuracy. Recently, data-driven machine learning models have been widely applied to ROP prediction. However, these models often lack mechanistic constraints, limiting their performance to specific conditions and reducing their real-world applicability. Additionally, geological variability across wells further hinders the transferability of conventional intelligent models. Thus, combining mechanistic knowledge with intelligent models and enhancing model stability and transferability are key challenges in ROP prediction research. To address these challenges, this paper proposes a Mechanism-Data Fusion and Transfer Learning method to construct an intelligent prediction model for ROP, achieving accurate ROP predictions. A multilayer perceptron (MLP) was selected as the base model, and training was performed using data from neighboring wells and partial data from the target well. The Two-stage TrAdaBoost.R2 algorithm was employed to enhance model transferability. Additionally, drilling mechanistic knowledge was incorporated into the model’s loss function as a constraint to achieve a fusion of mechanistic knowledge and data-driven approaches. Using MAPE as the measure of accuracy, compared with conventional intelligent models, the proposed ROP prediction model improved prediction accuracy on the target well by 64.51%. The model transfer method proposed in this paper has a field test accuracy of 89.71% in an oilfield in China. These results demonstrate the effectiveness and feasibility of the proposed transfer learning method and mechanistic–data integration approach.

As oil and gas exploration extends to deep, ultra-deep, and unconventional reservoirs, high drilling costs persist. Drill bit performance, as the critical rock-breaking component, directly governs efficiency and economics. While optimal bit selection boosts rate of penetration (ROP) and cuts costs, traditional expert-dependent methods struggle to address complex formation bit parameter interactions, suffering from low accuracy and poor adaptability. With artificial intelligence gaining traction in petroleum engineering, machine learning-based bit selection has emerged as a key solution. This study focuses on polycrystalline diamond compact (PDC) bits and proposes an intelligent bit selection method based on graph neural networks (GNNs), utilizing drilling records from over 100 wells encompassing 40 multidimensional features. Through comparative analysis of four intelligent models—random forest, gradient boosting (XGBoost), gated recurrent unit (GRU), and the GNN, the results demonstrate that the GNN achieves superior performance with an R² (coefficient of determination) of 0.932 and MAPE (mean absolute percentage error) of 6.88%. The GNN significantly outperforms conventional models in rock-breaking performance prediction. By establishing this GNN model for ROP and footage per run prediction, this study achieves intelligent bit selection that substantially enhances drilling efficiency, reduces operational costs, and provides scientifically reliable technical support for drilling operations in complex formation conditions.

In the context of carbon neutrality and emission reduction goals, energy consumption optimization in the oil and gas industry is crucial for reducing carbon emissions and improving energy efficiency. As a key component in drilling operations, optimizing the energy consumption of drilling pumps has significant potential for energy savings. However, due to the complex and variable geological conditions, diverse operational parameters, and inherent nonlinear relationships in the drilling process, accurately predicting energy consumption presents considerable challenges. This study proposes a novel Long Short-Term Memory Attention model for precise prediction of drilling pump energy consumption. By integrating Long Short-Term Memory (LSTM) networks with the Attention mechanism, the model effectively captures complex nonlinear relationships and long-term dependencies in energy consumption data. Comparative experiments with traditional LSTM and Convolutional Neural Network (CNN) models demonstrate that the LSTM-Attention model outperforms these models across multiple evaluation metrics, significantly reducing prediction errors and enhancing robustness and adaptability. The proposed model achieved Mean Absolute Error (MAE) values ranging from 5.19 to 10.20 and R² values close to one (0.95 to 0.98) in four test scenarios, demonstrating excellent predictive performance under complex conditions. The high-precision prediction of drilling pump energy consumption based on this method can support energy optimization and provide guidance for field operations.

Accurate prediction of the rate of penetration (ROP) in deep and ultra-deep wells remains a major challenge due to complex downhole conditions and limited real-time data. To address the issues of physical inconsistency and weak generalization in conventional da-ta-driven approaches, this study proposes a mechanism-guided and attention-enhanced deep learning framework. In this framework, drilling physical principles such as energy balance are reformulated into differentiable constraint terms and directly incorporated in-to the loss function of deep neural networks, ensuring that model predictions strictly ad-here to drilling physics. Meanwhile, attention mechanisms are integrated to improve feature selection and temporal modeling: for tree-based models, we investigate their implicit attention to key parameters such as weight on bit (WOB) and torque; for sequential models, we design attention-enhanced architectures (e.g., LSTM and GRU) to capture long-term dependencies among drilling parameters. Validation on 49,284 samples from 11 deep and ultra-deep wells in China (depth range: 1226–8639 m) demonstrates that the synergy between mechanism constraints and attention mechanisms substantially improves ROP prediction accuracy. In blind-well tests, the proposed method achieves a mean absolute percentage error (MAPE) of 9.47% and an R² of 0.93, significantly outperforming traditional methods under complex deep-well conditions. This study provides reliable intelligent decision support for optimizing deep and ultra-deep well drilling operations. By improving prediction accuracy and enabling real-time anomaly detection, it enhances operational safety and efficiency while reducing drilling risks. The proposed approach offers high practical value for field applications and supports the intelligent development of the oil and gas industry.

Managed pressure drilling (MPD) is the core technology for developing formations with high pressure and narrow density windows. It precisely maintains the bottomhole pressure (BHP) within the safe operating window defined by formation pore pressure and fracture pressure by actively regulating the wellbore pressure profile. If pressure control becomes unstable, it can easily trigger gas kicks or lost circulation, posing a severe threat to operational safety. However, existing model predictive control (MPC) schemes have significant limitations: pure data-driven models exhibit poor generalization under complex conditions, while control algorithms based on traditional mechanistic models struggle to meet the stringent real-time requirements of field control cycles due to high-complexity numerical iteration processes. To balance control precision and real-time performance, this paper proposes a physics-informed model predictive control framework (PINC-MPC). During the training phase, physical prior knowledge such as the law of mass conservation is embedded into the neural network as constraints to construct a physically consistent deep surrogate model, enabling it to characterize complex wellbore characteristics. In the control phase, this surrogate model replaces the time-consuming numerical solving process of the mechanistic model within the MPC loop, achieving near-real-time state prediction and rolling optimization while ensuring physical fidelity. Experimental results indicate that PINC-MPC demonstrates superior control performance. Its median single-step solving time is only 16.81 ms, achieving an 11.1-fold acceleration compared to the mechanistic model-based scheme (187.3 ms). In a 5000 s full-cycle closed-loop control experiment, the total time required for the former is only 1.68 s, while the latter reaches 18.73 s, representing an efficiency improvement of approximately 91%. In terms of control accuracy, the integrated absolute error (IAE), reflecting the total deviation of the control process, significantly decreased from 63.40 MPa·s for the industrial successive linearization MPC (SLMPC) to 12.90 MPa·s, an improvement of 79.7%. Especially in extreme dynamic conditions such as simulated pump shutdowns for pipe connections and sudden gas kicks, the framework demonstrates excellent predictive ability and response efficiency. It can proactively trigger compensation actions to keep BHP fluctuations within 0.30 MPa, significantly outperforming the traditional SLMPC method. The research results prove that PINC-MPC provides an efficient, precise, and robust nonlinear control strategy for MPD systems, offering important engineering reference value for enhancing the automation level of intelligent drilling systems.