No abstract

Shunbei Oilfield is a fractured carbonate reservoir with complex geological structures that are influenced by fault movements and prone to collapse and leak incidents. Precisely predicting leakage pressure is crucial for conducting fracturing operations in the later stages of production. However, current fracture-related leakage pressure prediction models mostly rely on statistical and mechanical methods, which require the consideration of factors such as fracture aperture and parameter selection, thereby leading to limitations in prediction efficiency and accuracy. To enhance the accuracy of reservoir leakage pressure prediction, this study leverages the advantages of artificial intelligence methods in dealing with complex nonlinear problems and proposes an optimized Long Short-Term Memory (LSTM) neural network prediction approach using the Particle Swarm Optimization (PSO) algorithm. Firstly, the Spearman correlation coefficient is used to evaluate the correlation between nine parameter features and leakage pressure. Subsequently, an LSTM network framework is constructed, and the PSO algorithm is applied to optimize its hyper-parameters, establishing an optimal model for leakage pressure prediction. Finally, the model’s performance is evaluated using the Coefficient of Determination (R2), Root Mean Squared Error (RMSE), and Mean Absolute Percentage Error (MAPE). The evaluation results demonstrate that the PSO-optimized LSTM model achieved an R2 of 0.828, RMSE of 0.049, and MAPE of 3.2, all of which outperformed the original model. The optimized LSTM model showed an average accuracy approximately 12.8% higher than that of the single LSTM model, indicating its higher prediction accuracy. The verification results from multiple development wells in this block further confirmed that the deep learning model established in this study surpassed traditional methods in prediction accuracy. Consequently, this approach is beneficial for drilling engineers and decision-makers to plan drilling operations more effectively and achieve accurate risk avoidance during the drilling process.

It is worthwhile to investigate abnormal performance of IPOs by incorporating investor sentiment. Using the method of Agent-based Computational Finance (ACF), we analyze the effect from different kinds of investor sentiment on IPOs first-day underpricing and long-term performance. The results show that individual investor's sentiment is positively correlated with the IPO's first-day underpricing and its long-run performance. In the long run, along with the rising of individual investor sentiment, IPOs' long-term performance will change from underperforming to outperforming. This conclusion provides a more reasonable explanation for the different IPOs longterm performance.

The plugging of nanopores in low-permeability coal reservoirs is an important factor that affects productivity reduction. However, the mechanism of plugging of the nanopores in coal reservoirs remains unclear. In this study, the coal samples from the Anze coalbed methane block of the North China Oilfield are used as the research object. Experiments are conducted on the mechanism of nanopore plugging by the variation of nanopore permeability based on the pressure oscillation method and the nanopore (scanning electron microscope) method. The research shows that the foreign working fluid invades a coal sample; the sample changes from being hydrophobic to being water absorbent within a certain period. The instability caused by the expansion of coal clay mineral particles promotes the dispersion and shedding of particles, and the migration of particles is accelerated under the shear stress of the working fluid. In addition, the viscosity and pressure difference of the working fluid are important factors that affect particle plugging. The viscosity of the fluid increased by two times, and permeability decreased by 1.21 times. As the pressure difference increases by two times, permeability can be reduced by up to two orders of magnitude. The findings of this study can help for better understanding of the mechanism of plugging of the nanopores in coal reservoirs and the reasons of production reduction in low-permeability coal reservoirs. Such findings provide theoretical support for the selection of the working fluid, and reasonable production pressure difference can effectively reduce the damage on coal permeability in a low-permeability coal reservoir.

No abstract