Traumatic pseudoaneurysm is a rare lesion with a high risk of rupture, and represents one of the most difficult lesions to treat, either surgically or endovascularly. Herein, we describe the case of a 32-year-old man with a traumatic pseudoaneurysm of the internal carotid artery, which was treated by overlapped flow diverters (Tubridge). The patient recovered well, and the follow-up angiography at four months showed complete occlusion of the pseudoaneurysm and patency of the internal carotid artery and the ophthalmic artery.

Unconventional reservoirs are characterized by intricate fluid-phase behaviors, and physics-based shale oil well productivity prediction models often exhibit substantial deviations due to oversimplified theoretical frameworks and challenges in parameter acquisition. Under these circumstances, data-driven approaches leveraging actual production datasets have emerged as viable alternatives for productivity forecasting. Nevertheless, conventional data-driven architectures suffer from structural simplicity, limited capacity for processing low-dimensional feature spaces, and exclusive applicability to intra-sequence learning paradigms (e.g., production-to-production sequence mapping). This fundamentally conflicts with the underlying principles of mechanistic modeling, which emphasize pressure-to-production sequence transformations. To address these limitations, we propose a hybrid deep learning architecture integrating convolutional neural networks with bidirectional gated recurrent units (CNN-BiGRU). The model incorporates dedicated input pathways: fully connected layers for feature embedding and convolutional operations for high-dimensional feature extraction. By implementing a sequence-to-sequence (seq2seq) architecture with encoder–decoder mechanisms, our framework enables cross-domain sequence learning, effectively bridging pressure dynamics with production profiles. The CNN-BiGRU model was implemented on the TensorFlow framework, with rigorous validation of model robustness and systematic evaluation of feature importance. Hyperparameter optimization via grid searching yielded optimal configurations, while field applications demonstrated operational feasibility. Comparative analysis revealed a mean relative error (MRE) of 16.11% between predicted and observed production values, substantiating the model’s predictive competence. This methodology establishes a novel paradigm for machine learning-driven productivity prediction in unconventional reservoir engineering.

Conventional shale gas productivity prediction techniques consider fracture conductivity to be a fixed value, but in actual production processes, conductivity changes with time. Therefore, this paper proposed a capacity prediction method that considers time-dependent conductivity and validates its accuracy using commercial simulators. First, relevant parameters were obtained by fitting the improved long-term conductivity test, and then the shale gas seepage model was established using the EDFM method. The laboratory test results showed that the order of significance affecting the conductivity retention rate was fracturing fluid viscosity > sand concentration > fracturing fluid retention time; the calculation results of the production prediction model show that the flow and the pressure curves that corresponded to constant conductivity and variable conductivity were to some extent different. In the presence of complex fractures and natural fractures, the increase in the variable conductivity production curve was smaller than that of the constant conductivity production curve. This study provides some guidance for field production.

Multi-cluster perforation staged fracturing in horizontal wells has become an important means of completion stimulation for unconventional oil and gas reservoirs. However, the non-uniform propagation of multi-cluster hydraulic fractures remains one of the key challenges restricting efficient reservoir stimulation. In this study, based on the finite element method and considering factors such as frictional pressure drop along the wellbore for power-law fluid, perforation friction, and stress interference, a fracture propagation model with dynamic multi-stage flow distribution coupling formation, perforation, and wellbore flow was constructed. The effects of non-uniform perforation schemes, total number of perforations, and perforation non-uniformity coefficient on multi-cluster fracture propagation behavior were systematically investigated, and the characteristics of dynamic flow distribution were clarified. The results show that the order of fluid intake uniformity among different perforation schemes is as follows: spindle-shaped perforation, uniform perforation, and Tapered perforation. Reducing the number of perforations and decreasing the perforation non-uniformity coefficient can improve the uniformity of fracture propagation to a certain extent. The findings of this study can provide a theoretical basis and practical reference for efficient fracturing stimulation of shale oil in the Cangdong Sag.

Hydraulic fracturing is an important means of developing unconventional oil and gas layers. The fracture conductivity of tight sandstone reservoirs after fracture is affected by many factors, such as the interaction between the fracturing fluid, water, and rocks; the fracturing materials; and the construction parameters. This paper improves the experimental process of the long-term conductivity test and provides insight into conductivity prediction and optimization based on the response surface test method. The test process is conducted in the following manner: (1) inject nitrogen to evaluate the fracture conductivity before fracturing fluid damage; (2) inject fracturing fluid to simulate shut-in; and (3) inject nitrogen again to evaluate fracture conductivity after the damage ability of the fracturing fluid. The single factor test results show that the lower the sand concentration is, the higher the fracturing fluid viscosity will be, and the longer the fracturing fluid retention time is, the greater the damage to the conductivity of the fracturing fluid will be. The response surface test results show that the order of factors affecting the retention of conductivity is fracturing fluid viscosity > sand concentration > fracturing fluid retention time. There is a certain interaction between sand concentration and fluid viscosity, and there is also a certain interaction between fluid viscosity and fluid retention time, but these interactions are not significant; when the fracturing fluid retention time is longer, there will be an interaction between the sand concentration and the fracturing fluid retention time. In addition, based on the model used to optimize the fracturing construction parameters from the perspective of proppant conductivity damage, the optimal solution is when the viscosity of the fracturing fluid is 1 mPa.s, the paved-sand content is 8.49 kg/m², and the retention time of the fracturing fluid is 10 h. The maximum retention rate of the flow conductivity is 63.19%.