Coalbed methane (CBM) drilling and completion technologies (DCTs) are significant basis for achieving efficient CBM exploration and exploitation. Characteristics of CBM reservoirs vary in different regions around the world, thereby, it is crucial to develop, select and apply the optimum DCTs for each different CBM reservoir. This paper firstly reviews the development history of CBM DCTs throughout worldwide and clarifies its overall development tendency. Secondly, different well types and its characteristics of CBM exploitation are summarized, and main application scopes of these well types are also discussed. Then, the key technologies of CBM drilling (directional drilling tools, measurement while drilling, geo-steering drilling, magnetic guidance drilling, underbalanced drilling and drilling fluids), and the key technologies of CBM completion (open-hole, cavity and under-ream completion, cased-hole completion, screen pipe completion and horizontal well completion) are summarized and analyzed, it is found that safe, economic and efficient development of CBM is inseparable from the support of advanced technologies. Finally, based on the current status of CBM development, the achievements, existing challenges and future prospects are summarized and discussed from the perspective of CBM DCTs.

Fully rotary drilling is one of many useful technologies used for the exploitation of petroleum and geothermal resources, but fully rotating drill-strings are extremely complicated. Therefore, according to the Hamilton principle, a non-linear coupled bottom hole assembly (BHA)-bit-formation-wellbore model is proposed for BHAs with bent-housing positive displacement motor using the finite element method to investigate the dynamic behavior and steering ability under fully rotary drilling. The impact force, acceleration, axial loading, torque, and dynamic stress were simulated, and factors influencing the dynamic steering forces were investigated. The results indicate that the impact force, acceleration, axial loading, torque, and dynamic stress under fully rotary drilling are much higher than under conventional drilling. The numerical simulation and field test in well B confirmed that the rotation of the drill-string is conducive to the hold-on of the deviation angle. With the increase in the weight-on-bit, bend angle, and stabilizer height, the deflecting force on a drill bit increases. Conversely, with the increase in stabilizer diameter, the deflecting force on the drill bit decreases; the lower the deflecting force, the better the effectiveness of hold-on. With increasing deviation angle, the deflecting force on the drill bit first decreases and then increases. The present model can provide a theoretical basis for wellbore trajectory control and optimization design of BHA.

The transient temperature of the wellbore plays an important role in the selection of downhole tools during the drilling of deep shale gas horizontal wells. This study established a transient temperature field model of horizontal wells based on the convection heat transfer between wellbore and formation and the principle of energy conservation. The model verification shows that the root mean squared error (RMSE) between the measured annular temperature neat bit and the predicted value is 0.54 °C, indicating high accuracy. A well in Chongqing, China, is taken as an example to study the effects of bottom hole assembly (BHA), drill pipe size, drilling fluid density, flow rate, inlet temperature of drilling fluid, and drilling fluid circulation time on the temperature distribution in wellbore annulus. It is found that the increase in annular temperature is about 1 °C/100 m in the horizontal section when a positive displacement motor (PDM) is used. A Φ139.7 mm drill pipe is more favorable for cooling than Φ139.7 mm + Φ127 mm drill pipe. Reducing drilling fluid density and flow rate and inlet temperature is beneficial to reduce bottom hole temperature. Bit-breaking rock, bit hydraulic horsepower, and drill pipe rotation will increase the bottom hole temperature. The research results can provide theoretical guidance for temperature prediction, selection of proper drill tools, and adjustment of relevant parameters in deep shale gas horizontal wells.

The Sichuan Basin has abundant deep and ultra-deep natural gas resources, making it a primary target for exploration and the development of China’s oil and gas industry. However, during the drilling of ultra-deep wells in the Sichuan Basin, complex geological conditions frequently lead to gas kicks, posing significant challenges to well control and safety. Compared to traditional kick detection methods, artificial intelligence technology can improve the accuracy and timeliness of kick detection. However, there are limited real-world kick data available from drilling operations, and the datasets are extremely imbalanced, making it difficult to train intelligent models with sufficient accuracy and generalization capabilities. To address this issue, this paper proposes a kick data augmentation method based on a time-series generative adversarial network (TimeGAN). This method generates synthetic kick samples from real datasets and then employs a long short-term memory (LSTM) neural network to extract multivariate time-series features of surface drilling parameters. A multilayer perceptron (MLP) network is used for data classification tasks, constructing an intelligent kick detection model. Using real drilling data from ultra-deep wells in the SY block of the Sichuan Basin, the effects of k-fold cross-validation, data dimensionality, various imbalanced data handling techniques, and the sample imbalance ratio on the model’s kick detection performance are analyzed. Ablation experiments are also conducted to assess the contribution of each module in identifying kick. The results show that TimeGAN outperforms other imbalanced data handling techniques. The accuracy, recall, precision, and F1-score of the kick identification model are highest when the sample imbalance ratio is at 1 but decrease as the imbalance ratio increases. This indicates that maintaining a balance between positive and negative samples is essential for training a reliable intelligent kick detection model. The trained model is applied during the drilling of seven ultra-deep wells in Sichuan, demonstrating its effectiveness and accuracy in real-world kick detection.