Named entity recognition, a fundamental task in natural language processing, faces challenges related to the sequence labeling framework widely used when dealing with nested entities. The span-based method transforms nested named entity recognition into span classification tasks, which makes it an efficient way to deal with overlapping entities. However, too much overlap among spans may confuse the model, leading to inaccurate classification performance. Moreover, the entity mentioned in the training dataset contains rich information about entities, which are not fully utilized. So, in this paper, a span-prototype graph is constructed to improve span representation and increase its distinction. In detail, we utilize the entity mentions in the training dataset to create a prototype for each entity category and add prototype loss to adapt the span to its similar prototype. Then, we feed prototypes and span into a graph attention network (GAT), enabling span to automatically learn from different prototypes, which integrate the information about entities into the span representation. Experiments on three common nested named entity recognition datasets, including ACE2004, ACE2005, and GENIA, show that the proposed method achieves 87.28%, 85.97%, and 79.74% F1 scores on ACE2004, ACE2005, and GENIA, respectively, performing better than baselines.

This paper carries out a study on the numerical simulation of borehole instability based on the disturbance state concept. By introducing the disturbance damage factor into the classical Mohr–Coulomb yield criterio, we establish a finite element hydro-mechanical coupling model of borehole instability and program the relevant field variable by considering elastic–plastic deformation in borehole instability, the distribution of the damage disturbance area, the variation of porosity and permeability with the disturbance damage factor, etc. Numerical simulation shows that the borehole stability is related to the action time of drilling fluid on the wellbore, stress anisotropy, the internal friction angle of rock, and borehole pressure. A higher horizontal stress difference helps suppress shear instability, and a higher rock internal friction angle enhances shear failure around the borehole along the maximum horizontal principal stress. When considering the effect of the internal friction angle of rock, the rock permeability, disturbance damage factor, and equivalent plastic strain show fluctuation characteristics. Under the high internal friction angle of rock, a strong equivalent plastic strain area and disturbance damage area occur in the direction of the maximum horizontal principal stress. Their cloud picture shows the mantis shape, where the bifurcation corresponds to the whiskers of the shear failure area in borehole instability. This study provides a theoretical basis for solving the problem of borehole instability during drilling engineering.

The influencing factors of wax deposition are numerous and complex, and accurately predicting the wax deposition rate is of great practical significance for the safe operation of pipelines and the formulation of reasonable pigging schemes. On the basis of mastering the prediction steps of the Elman neural network (ENN), the arithmetic optimization algorithm (AOA) was introduced to improve the Elman neural network and an optimization model was established, and the differences in prediction results between improved models (AOA-ENN model, PSO-ENN model, GA-ENN model) and the traditional ENN model were compared and analyzed through examples. The prediction results of three examples showed that the average relative errors of the AOA-ENN model are 2.5470%, 1.4974%, and 2.3819 %, respectively, while the average relative errors of the traditional ENN model are 19.0313%, 9.1568%, and 11.4836%, respectively. Therefore, the arithmetic optimization algorithm used in this paper has good reliability. For the three improved models, the AOA-ENN model has the highest prediction accuracy, followed by the PSO-ENN model and the GA-ENN model. Overall, the Elman neural network improved by an arithmetic optimization algorithm can be used for predicting wax deposition rate, which can provide new ideas for accurate prediction of wax deposition rate.

The production of tight gas wells decreases rapidly, and the traditional method is difficult to accurately predict the production of tight gas wells. At present, intelligent algorithms based on big data have been applied in oil and gas well production prediction, but there are still some technical problems. For example, the traditional error back propagation neural network (BP) still has the problem of finding the local optimal value, resulting in low prediction accuracy. In order to solve this problem, this paper establishes the output prediction method of BP neural network optimized with the sparrow search algorithm (SSA), and optimizes the hyperparameters of BP network such as activation function, training function, hidden layer, and node number based on examples, and constructs a high-precision SSA-BP neural network model. Data from 20 tight gas wells, the SSA-BP neural network model, Hongyuan model, and Arps model are predicted and compared. The results indicate that when the proportion of the predicted data is 20%, the SSA-BP model predicts an average absolute mean percentage error of 20.16%. When the proportion of forecast data is 10% of the total data, the SSA-BP algorithm has high accuracy and high stability. When the proportion of predicted data is 10%, the mean absolute average percentage error is 3.97%, which provides a new method for tight gas well productivity prediction.

Owing to the limitations of physical experiments on heavy oil, this study establishes a mathematical model for heavy oil–water two-phase flow based on the theory of multiphase flow, considering factors such as heavy oil viscosity, mixed flow velocity, and inlet water cut. Through transient calculations of 650 groups of heavy oil–water two-phase flows based on this model, six typical heavy oil–water two-phase flow patterns were identified by monitoring flow pattern cloud images, liquid holdup, and the probability density function (PDF) of liquid holdup: water-in-oil bubble flow, transitional flow, water-in-oil slug flow, oil-in-water bubble flow, oil-in-water very fine dispersed flow, and water-in-oil core-annular flow. Five sets of flow pattern maps for a heavy oil–water two-phase flow with different viscosities were established based on the inlet water cut and mixed flow velocity. The results showed that different heavy oil viscosities lead to different oil–water two-phase flow patterns. When the heavy oil viscosity is 100 mPa·s, the flow patterns include water-in-oil bubble flow, transitional flow, water-in-oil slug flow, oil-in-water bubble flow, and oil-in-water very fine dispersed bubble flow. When the heavy oil viscosity reaches 600 mPa·s, a water-in-oil core-annular flow appears, and the oil-in-water very fine dispersed bubble flow disappears. After the heavy oil viscosity exceeds 1100 mPa·s, the oil-in-water bubble flow disappears. Among the different flow patterns, the range of the water-in-oil slug flow is most affected by the viscosity and flow velocity. The greater the heavy oil viscosity, the larger the range. When the viscosity remained constant, a larger flow velocity resulted in a smaller range. The accuracy of the flow pattern predictions in the maps was verified by comparing them with field production data, confirming that the research results can provide a theoretical basis for understanding oil–water two-phase flow patterns in heavy oil wellbores.

In recent years, with the rapid development of salt cavern gas storage reservoir construction in China, the characteristics of salt rock reservoirs with strong non-homogeneity and many interlayers have brought challenges to the dynamic prediction of water solution cavity construction. Aiming to solve this problem, this paper constructs a three-dimensional non-homogeneous salt cavern reservoir water-soluble cavity building prediction model, which takes into full consideration the non-homogeneity of salt rock reservoirs, interlayers, reservoir temperatures, and water injection process parameters, among other factors. By comparing the calculation results of the software compiled by the model with those of other numerical simulation software, we show that the model can accurately reflect the influence of geological parameters on the cavity morphology under the condition of non-uniform geological parameters, with higher simulation accuracy, and ultimately analyze individual examples. It can provide important theoretical support and practical guidance for the construction of a salt cavern gas storage reservoir.