The technical focus of drilling operations is changing to oil and gas reservoirs with higher difficulty factors such as low permeability and fracture. During the drilling process, drilling operations in deep complex formations are prone to overflow and leakage complications. Leakage and overflow problems will change the performance of the drilling fluid in the wellbore, impacting the wellbore pressure, and causing complex accidents such as stuck drilling and collapse. In order to improve the level of control over the risk of wellbore overflow and leakage, it is necessary to predict the mud overflow and leakage situation and to arrange and control the risk of leakage and overflow that may occur in advance to ensure the safety of drilling. By using a genetic algorithm to optimize the multi-layer feedforward neural network, this paper establishes a GA-BP Neural Network Drilling overflow and leakage prediction model based on multi-parameter fusion. Through the optimization training of 14 parameters that may affect the occurrence of complex downhole accidents, the mud overflow and leakage are predicted. The prediction results of the model are compared with the prediction results of a conventional BP neural network, and verified by the real drilling data. The results show that the MAE, MSE, and RMSE of the GA-BP neural network model are improved by 2.91%, 4.48%, and 10.93%, respectively, compared with the BP neural network model, and the prediction quality is higher. Moreover, the amount of mud overflow and leakage predicted by using the GA-BP neural network matches well with the pattern of mud overflow and leakage data in real drilling, which proves the effectiveness and accuracy of the GA-BP neural network in overflow and leakage prediction.

Kicks can lead to well control risks during petroleum drilling, and even more serious kicks may lead to serious casualties, which is the biggest threat factor affecting the safety in the process of petroleum drilling. Therefore, how to detect kicks early and efficiently has become a focus practical problem. Traditional machine learning models require a large amount of labeled data, such kicked sample, and it is difficult to label data, which requires a lot of labor and time. To address the above issues, the deep forest is extended to a transfer learning model to improve the generalization ability. In this paper, a transfer learning model is built to detect kicks early. The source domain model adopts the deep forest model. Deep forest is an ensemble learning model with a hierarchical structure similar to deep learning. Each layer contains a variety of random forests. It is an integration of the model in depth and breadth. In the case of a small sample size (20–60 min), kick can be identified 10 min in advance. The deep forest model is established as the source domaining model, and a cascade forest is added at the last layer according to the transfer learning algorithm to form the classification model of this paper. The experimental results show that the kick prediction accuracy of the model is 80.13% by a confusion matrix. In the target domain, the proposed model performs better than other ensemble learning algorithms, and the accuracy is 5% lower than other SOTA transfer learning algorithms.

Oil drilling is the core process of oil and natural gas resources exploitation. Well overflow is one of the biggest threats to safety drilling. Prediction of the overflow in advance can effectively avoid the occurrence of this kind of accident. However, the drilling history has unbalanced distribution, and labeling data is a time-consuming and laborious job. To address this issue, an overflow-prediction algorithm based on semi-supervised learning is designed in this paper, which can accurately predict overflow 10 min in advance when the labeled data are limited. Firstly, a three-step feature-selection algorithm is conducted to extract 22 features, and the time series samples are constructed through a 500-width sliding window with step size 1. Then, the Mean Teacher model with Jitter noise is employed to train the labeled and unlabeled data at the same time, in which a fused CNN-LSTM network is built for time-series prediction. Compared with supervised learning and other semi-supervised learning frameworks, the results show that the proposed model based on only 200 labeled samples is able to achieve the same effect as supervised learning method using 1000 labeled samples, and the prediction accuracy can reach 87.43% 10 min in advance. With the increase in the proportion of unlabeled samples, the performance of the model can sustain a rise within a certain range.

Oil drilling has always been considered a vital part of resource exploitation, and during which overflow is the most common and tricky threat that may cause blowout, a catastrophic accident. Therefore, to prevent further damage, it is necessary to detect overflow as early as possible. However, due to the unbalanced distribution and the lack of labeled data, it is difficult to design a suitable solution. To address this issue, an improved Transformer Framework based on self-supervised learning is proposed in this paper, which can accurately detect overflow 20 min in advance when the labeled data are limited and severely imbalanced. The framework includes a self-supervised pre-training scheme, which focuses on long-term time dependence that offers performance benefits over fully supervised learning on downstream tasks and makes unlabeled data useful in the training process. Next, to better extract temporal features and adapt to multi-task training process, a Transformer-based auto-encoder with temporal convolution layer is proposed. In the experiment, we used 20 min data to detect overflow in the next 20 min. The results show that the proposed framework can reach 98.23% accuracy and 0.84 F1 score, which is much better than other methods. We also compare several modifications of our framework and different pre-training tasks in the ablation experiment to prove the advantage of our methods. Finally, we also discuss the influence of important hyperparameters on efficiency and accuracy in the experiment.

To address the issue of sealing failure of cement materials commonly used as wellbore plugging agents in CO₂ geological storage, this study proposes a composite wellbore plugging method that combines cement and Sn58Bi alloy. In this method, a composite sealing structure of “cement–Sn58Bi alloy–cement” is constructed within the wellbore. To evaluate the performance of this method, a series of pressure-bearing and gas-tightness experimental devices were designed, and experiments were conducted to assess the pressure-bearing capacity and gas sealing performance of the composite plugs. Additionally, optical microscopy was employed to observe and analyze the microstructure of the plugs. The effects of alloy proportion and temperature on the sealing performance of the composite plugs were systematically investigated. The experimental results indicate that both the pressure-bearing capacity and gas-tightness performance of the plugs are influenced by the alloy content and ambient temperature. Specifically, when the temperature increased from 30 °C to 60 °C, the pressure-bearing capacity decreased by an average of 28.3%; when further increased from 60 °C to 90 °C, it decreased by an average of 21.1%. In contrast, the gas-tightness performance exhibited an opposite trend, with the breakthrough pressure increasing by an average of 25.7% and 22.0%, respectively, over the same temperature intervals. Moreover, increasing the alloy proportion in the composite plugs enhanced both their pressure-bearing and gas-tightness performances. This study provides theoretical support for the application of composite plugs in CO₂ geological storage.

During drilling, the driller cannot continuously and reliably regulate manipulated variables such as surface weight on bit (WOBs), surface revolutions per minute (RPMs), and mud pump flow rate. This results in optimal drilling parameters that cannot be obtained in real time, which will affect drilling safety and efficiency. Therefore, we consider an integrated coupling model to simultaneously describe the response of rate of penetration (ROP) and bottom hole pressure (BHP). With this model, we design an economic model predictive control with zone tracking (ZEMPC) algorithm combining the optimization and control layers to reduce the hydraulic mechanical specific energy (HMSE) while accurately regulating the BHP and ensuring efficient hole cleaning during operation. This algorithm is compared with another hierarchical control structure. The upper layer of this structure implements steady-state optimization for HMSE, and the optimal set value of BHP and ROP is dynamically tracked in the lower layer using nonlinear model predictive control (NMPC). A performance comparison reveals that both control algorithms can track formation pressure with acceptable accuracy, and the concentration of bottom hole cuttings is less than 5% during improving ROP. ZEMPC based on $l_{1}$ norm constraint can better improve the economic performance of key variables by increasing control redundancy and is not affected by the decision cycle. The robustness of the two algorithms is studied in case of errors in mud density and friction parameters. It is found that the ZEMPC based on the $l_{1}$ norm constraint is less sensitive to error when the model is mismatched.