Search Results (35)

The extraction of land gas resources requires efficient methods to address the issue of pipeline obstruction due to the accumulation of natural gas hydrates. The existing ground heating, downhole throttling, and decompression measures are energy-intensive. The metal-reinforced composite heat-insulation pipe serves as the production string for terrestrial natural gas wells, effectively minimizing temperature loss of natural gas within the wellbore. This innovation eliminates the need for ground heating equipment and downhole throttling devices in large-scale gas well production, thereby fundamentally achieving environmentally sustainable natural gas extraction, energy conservation, and cost reduction. This research simulates the operational circumstances and environmental characteristics of the Sulige gas field. Utilizing predictions and analyses of the formation characteristics of natural gas hydrate, the gas–solid two-phase flow DPM model, RNG k-ε turbulence model, heat transfer characteristics, and population balance model are employed to examine the concentration distribution, pressure distribution, velocity distribution, and heat transfer characteristics of natural gas hydrate within the vertical tube of the structure. The findings indicate that a reduction in natural gas production or an increase in hydrate volume fraction leads to significant accumulation of hydrate adjacent to the tube wall, while the concentration distribution of hydrate is more uniform at elevated production conditions. The pressure distribution of hydrate under each operational state exhibits a pattern characterized by a high central concentration that progressively diminishes towards the periphery. The unit pressure drop of hydrate markedly escalates with an increase in flow rate. As the ambient temperature of the formation rises or the flow rate escalates, the thermal loss of the hydrate along the pipeline diminishes, resulting in an elevated exit temperature. Minimizing the thermal conductivity of the composite pipe can significantly decrease the temperature loss of the hydrate along the pipeline, greatly aiding in hydrate inhibition during the extraction of natural gas from terrestrial wells. This paper’s research offers theoretical backing for the enduring technical application of metal-reinforced composite insulating pipes in terrestrial gas fields, including the Sulige gas field. Full article

Traditional dynamic storage calculation methods face challenges such as difficult data acquisition and prolonged testing periods. To address the industry’s need for rapid yet accurate estimation of single-well dynamic reserves in tight sandstone gas formations, a deep learning architecture combining convolutional neural network (CNN) and long short-term memory (LSTM) network is proposed. This model enables fast and accurate reserve evaluation, outperforming other machine learning methods in overall capability while achieving a symmetric improvement in both training efficiency and prediction accuracy—reaching up to 95.9%. Based on this model, dynamic reserves of gas wells in the Sulige Gas Field were predicted. The single-well dynamic reserve test showed a relative error of less than 10%, and the method demonstrated strong stability and high precision in localized multi-well group tests, with errors distributed symmetrically within a narrow margin. All results satisfy engineering standards. The feasibility of the method has been verified, proving it can deliver fast and accurate gas well dynamic reserve predictions, greatly reduce evaluation costs, and enhance work efficiency. Full article

To reveal the regulatory mechanisms and differences in sensitivity of hydrodynamic forces and sediment parameters to the sedimentary evolution of braided river channel bars, this study takes the Sulige Gas Field as a case study and conducts 21 sets of sedimentary numerical simulation experiments using the controlled variable method. The three parameters of discharge, slope gradient, and sediment grain size were fixed, while the target variable was adjusted iteratively. After the river reaches a steady state, quantitative statistics of the area and length-width ratio of 547 identified channel bars are carried out, and sensitivity evaluation is performed by combining principal component analysis and multiple linear regression. The results show that the sedimentary evolution of braided rivers follows a unified evolutionary law, the evolution of channel bars is synergistically regulated by parameter combinations. Under the action of single factors, an increase in discharge promotes the axial extension and scale expansion of channel bars; an increase in grain size enhances the morphological stability of channel bars; slope gradient controls the erosion-deposition balance through gravitational potential energy. The parameter sensitivity is ranked as slope gradient, discharge, sediment grain size. Full article

Tight gas reservoirs present unique forecasting challenges due to steep decline rates, nonlinear production dynamics, and sensitivity to operational conditions. Conventional decline-curve methods and reservoir simulations are limited either by oversimplifying assumptions or by the need for extensive input data, although univariate deep learning models fail to fully capture external influences on well performance. To address these limitations, this study develops a transfer learning–enhanced N-BEATSx (Neural Basis Expansion Analysis Time Series with exogenous variables) framework for multivariate forecasting of tight gas well production. The model integrates exogenous variables, particularly casing pressure, with production histories to jointly represent reservoir behavior and operational effects. A pretraining dataset, comprising more than 100,000-day records from Block S of the Sulige Gas Field, was used to initialize the model, which was subsequently applied in a zero-shot setting to wells A1 and A2. Comparative analysis with the transfer learning-enhanced N-BEATS model demonstrates that N-BEATSx achieves consistently higher accuracy, with RMSE reductions of 23.9%, 39.1%, and 33.1% for Well A1 in short-, medium-, and long-term forecasts, respectively. These advances establish N-BEATSx as a robust tool for multivariate production forecasting, with direct industrial value in optimizing resource allocation, guiding development strategies, and enhancing operational decision-making in unconventional gas fields. Full article

This study focuses on the tight sandstone reservoirs of the He 8 Member (Lower Permian Shihezi Formation) in the western Sulige area, Ordos Basin. Multiple analytical methods were integrated, including core observation, thin-section analysis, X-ray diffraction (XRD), and rock mechanics experiments, to systematically evaluate the reservoir’s petrology, pore microstructure, physical properties, and fracture formation mechanisms. Results indicate that the reservoir is primarily composed of quartz arenite (78%), characterized by low porosity (avg. 5.5%) and permeability (avg. 0.15 mD). The pore system comprises dissolution pores, lithic dissolution pores, intergranular pores, and intercrystalline pores. Depositional microfacies significantly influence reservoir quality. Subaqueous distributary channel sands exhibit the best properties (porosity > 5%), followed by mouth bar deposits. The reservoir experienced intense compaction and siliceous cementation, which considerably reduced primary porosity. In contrast, dissolution and tectonic fracturing processes significantly enhanced reservoir quality. Rock mechanics tests reveal that highly heterogeneous rocks are more prone to fracturing under differential stress (σ₁–σ₃). These fractures considerably improve the flow capacity of tight reservoirs. Full article

This study proposes a multi-task learning-based production capacity prediction model aimed at improving the prediction accuracy for gas wells in multi-layer tight sandstone reservoirs of the Sulige gas field under small-sample conditions. The model integrates mutation theory and progressive hierarchical feature extraction to achieve adaptive nonlinear feature extraction and autonomous feature selection tailored to different prediction tasks. Using the daily average production of each gas-bearing layer during the first month after well commencement and the cumulative production of each gas-bearing layer over the first year as targets, the model was applied to predict the production capacity of 66 gas wells. Compared with single-task models and classical machine learning methods, the proposed multi-task model significantly improves prediction accuracy, reducing the root mean squared error (RMSE) by over 40% and increasing the coefficient of determination (R²) to 0.82. Experimental results demonstrate the model’s effectiveness in environments with limited training data, offering a reliable approach for productivity prediction in complex multi-layer tight sandstone reservoirs. Full article

Complex engineering systems—such as ultra-long horizontal wells in energy exploitation and distributed rail transit infrastructure—operate under harsh physical and environmental conditions, where accurate physical modeling and real-time parameter estimation are essential for ensuring safety, efficiency, and reliability. Traditional empirical and black-box data-driven approaches often fail to account for the underlying physical mechanisms, thereby limiting interpretability and generalizability. To address this, we propose a unified framework that integrates physics-informed scenario-based modeling with data-driven parameter inversion. In the first stage, critical system parameters—such as friction coefficients in drill string movement or contact forces in rail–wheel interactions—are explicitly formulated based on mechanical theory, leveraging symmetries and boundary conditions to improve model structure and reduce computational complexity. In the second stage, model parameters are identified or updated through inverse modeling using historical or real-time field data, enhancing predictive performance and engineering insight. The proposed methodology is demonstrated through two representative cases. The first involves friction estimation during tripping operations in the SU77-XX-32H5 ultra-long horizontal well of the Sulige Gas Field, where a mechanical load model is constructed and field-calibrated. The second applies the framework to rail transit systems, where wheel–rail friction is estimated from dynamic response signals to support condition monitoring and wear prediction. The results from both scenarios confirm that incorporating physical symmetry and data-driven inversion significantly enhances the accuracy, robustness, and interpretability of engineering analyses across domains. Full article

With the rapid development of the coalbed methane (CBM) industry in China, coal seam No. 8 of the Benxi Formation in the Ordos Basin has emerged as a key target for CBM development due to its abundant deep reserves. However, wellbore instability during deep CBM extraction has become increasingly problematic, with the degradation of coal mechanical strength caused by drilling fluid invasion being identified as a critical factor affecting drilling safety and operational efficiency. This study focuses on coal seam No. 8 of the Benxi Formation in the Sulige Gas Field, Ordos Basin. Through experimental analyses of the coal’s mineral composition, microstructure, hydration expansion properties, and mechanical strength variations, the mechanism underlying drilling fluid invasion-induced mechanical strength degradation is elucidated. The experimental results reveal that coal seam No. 8 of the Benxi Formation exhibits a high carbon content and a low absolute clay mineral content (approximately 6.11%), with minimal expansive minerals (e.g., mixed-layer illite–smectite accounts for 26.4%). Consequently, the coal demonstrates a low linear expansion rate and weak hydration dispersion properties, indicating that hydration expansion is not the dominant mechanism driving mechanical strength degradation. However, drilling fluid invasion significantly reduced coal’s Young’s modulus (from 1988.1 MPa to 1676.1 MPa, a 15.69% decrease) and compressive strength (from 7.9 MPa to 6.5 MPa, a 17.72% drop), while markedly affecting its internal friction angle. Friction coefficient tests further demonstrate that the synergistic action of water molecules and additives decreases microcrack sliding resistance by 19.22% with simulated formation water and by 25.00% with drilling fluid, thereby promoting microcrack propagation and failure. This process ultimately leads to a degradation in mechanical strength. Hence, the enhancement of sliding effects induced by drilling fluid invasion is identified as the primary factor contributing to coal mechanical strength degradation, whereas hydration expansion plays a secondary role. To mitigate these effects, optimizing the design of drilling fluid systems and selecting suitable anti-collapse additives to reduce sliding effects are critical for minimizing wellbore instability risks in coal seams. These measures will ensure safer and more efficient drilling operations for deep CBM extraction. Full article

Polymer flooding is a critical enhanced oil recovery technique; however, the development of polymer channeling along dominant channels during its later stages can adversely affect the process by increasing comprehensive water cut and dispersing remaining oil, thereby diminishing development benefits. This study aims to address this challenge by investigating the identification methods and distribution patterns of dominant channels in polymer flooding to inform and optimize the development strategy. Through a series of experiments, we analyzed how factors such as permeability, heterogeneity, reservoir thickness, and mineral composition influence the formation of dominant channels. We developed an identification method for dominant channels post-polymer flooding using a combination of reservoir engineering and mathematical analysis techniques. Our results highlight the significant role of rock and mineral composition, injection rate, and injection pressure in the formation of dominant channels. By integrating formation physical properties and production data from oil and water wells with the grey correlation method, we effectively identified dominant channels. This identification is crucial for guiding the development and adjustment of polymer flooding, enhancing oil recovery efficiency, and maximizing reservoir performance. Full article

The Sulige Gas Field is a typical low-permeability, low-pressure tight gas field, where pneumatic jetting is crucial for production. However, existing gas jet pumps have low efficiency, limiting field production and overall development. This paper explores the effect of adding water, at specific volume fractions, to the driving gas on pneumatic jet pump performance. Using Volume of Fluid (VOF) and Computational Fluid Dynamics (CFD) simulations, a three-dimensional fluid domain model was developed to analyze the flow field, turbulent kinetic energy, and energy conversion in the pump. Results show that the water volume fraction significantly impacts pump efficiency, with performance improving over natural gas as the driving medium. The optimal performance occurs at a 0.5 water volume fraction, with efficiency exceeding 40% and a dimensionless mass flow ratio of approximately 2.0. As the volumetric fraction of water increases, the optimal working point of the jet pump (the dimensionless mass flow ratio corresponding to the peak pump efficiency) gradually decreases. It drops from 2.0 at water volumetric fractions of 0.1 and 0.5, to 1.8 at 0.8, and further to 1.5 at 1.0. These findings provide valuable insights for optimizing pneumatic jet performance in the Sulige Gas Field. Full article

Sandstone bodies are distributed across a large area in the northeastern part of the Sulige gas field in the Ordos Basin. However, the production characteristics of gas wells in different areas are significantly different, and the success rate of drilling effective reservoirs is low. Therefore, studies on the patterns of natural gas enrichment are urgently needed. In this study, from the perspective of tectonic evolution, the mudstone sonic transit time method was used to calculate the denudation thickness of the study area in the Late Cretaceous; the denudation thickness was between 820 m and 1200 m, and the paleo-tectonic map of the top of He 8, which was the main layer at that time, was restored and analyzed in comparison with the present structure at the top of He 8, revealing that tectonic evolution has a controlling effect on the migration, accumulation and dispersion of natural gas after formation. During the critical period of hydrocarbon accumulation at the end of the Early Cretaceous, the short-axis nose uplift zone remaining in the central and western regions, and the long-axis nose uplift zone remaining in the central and eastern regions were favorable areas for natural gas migration and accumulation. The up-dip direction has lithological traps, and the gas reservoirs have survived to the present day. The short-axis nose uplift zone and anticline at the western margin disappeared through tectonic adjustment; thus, the paleo-gas reservoirs that formed there were destroyed, and the natural gas was adjusted to new traps. Full article

During the development of multi-layer tight sandstone gas reservoirs in Ordos Basin, China, it has not been easy to calculate accurately the production of each individual layer in gas wells. However, production allocation provides a vital basis for evaluating dynamic reserves and drainage areas of gas wells and remaining gas distributions of gas layers. To improve the accuracy and reliability of production allocation of gas wells, a new model was constructed based on the seepage equation, material balance equation, and pipe string pressure equation. In particular, this new model introduced the seepage equation with an elliptical boundary to accurately capture the fluid flow characteristics within a lenticular tight gas reservoir. The new model can accurately calculate the production and reservoir pressure of each individual layer in gas wells. In addition, the new model was validated and applied in the Sulige gas field, Ordos Basin. The following conclusions were drawn: First, The gas production contribution rates of pay zones based on the new model are fairly close to the measurements of the production profile logging, with errors less than 10%. Second, The overall drainage area of a gas well lies among those of each pay zone, and the total dynamic reserves of the well are close to the sum of the dynamic reserves of pay zones. Third, Higher permeability may lead to higher initial gas production of the pay zone, but the ultimate gas production contributions of pay zones are affected jointly by permeability and dynamic reserves. Finally, The new model has been successfully applied to the SZ block of the Sulige gas field, in which the fine evaluation of dynamic reserves, drainage areas, gas production, recovery factors, and remaining gas distributions of different layers was delivered, and the application results provide technical support for the future well placement and enhanced gas recovery of the block. Full article

Effective production prediction is vital for optimizing energy resource management, designing efficient extraction strategies, minimizing operational risks, and informing strategic investment decisions within the energy sector. This paper introduces a Dual-Stage Attention Temporal Convolutional Network (DA-TCN) model to enhance the accuracy and efficiency of gas production forecasting, particularly for wells in tight sandstone reservoirs. The DA-TCN architecture integrates feature and temporal attention mechanisms within the Temporal Convolutional Network (TCN) framework, improving the model’s ability to capture complex temporal dependencies and emphasize significant features, resulting in robust forecasting performance across multiple time horizons. Application of the DA-TCN model to gas production data from two wells in Block T of the Sulige gas field in China demonstrated a 19% improvement in RMSE and a 21% improvement in MAPE compared to traditional TCN methods for long-term forecasts. These findings confirm that dual-stage attention not only increases predictive accuracy but also enhances forecast stability over short-, medium-, and long-term horizons. By enabling more reliable production forecasting, the DA-TCN model reduces operational uncertainties, optimizes resource allocation, and supports cost-effective management of unconventional gas resources. Leveraging existing knowledge, this scalable and data-efficient approach represents a significant advancement in gas production forecasting, delivering tangible economic benefits for the energy industry. Full article

Accurate production forecasting of tight gas reservoirs plays a critical role in effective gas field development and management. Recurrent-based deep learning models typically require extensive historical production data to achieve robust forecasting performance. This paper presents a novel approach that integrates transfer learning with the neural basis expansion analysis time series (N-BEATS) model to forecast gas well production, thereby addressing the limitations of traditional models and reducing the reliance on large historical datasets. The N-BEATS model was pre-trained on the M4 competition dataset, which consists of 100,000 time series spanning multiple domains. Subsequently, the pre-trained model was transferred to forecast the daily production rates of two gas wells over short-term, medium-term, and long-term horizons in the S block of the Sulige gas field, China’s largest tight gas field. Comparative analysis demonstrates that the N-BEATS transfer model consistently outperforms the attention-based LSTM (A-LSTM) model, exhibiting greater accuracy across all forecast periods, with root mean square error improvements of 19.5%, 19.8%, and 26.8% of Well A1 for short-, medium-, and long-term horizons, respectively. The results indicate that the pre-trained N-BEATS model effectively mitigates the data scarcity challenges that hinder the predictive performance of LSTM-based models. This study highlights the potential of the N-BEATS transfer learning framework in the petroleum industry, particularly for production forecasting in tight gas reservoirs with limited historical data. Full article

Depleted gas reservoirs are important places for the rebuilding of gas-storage reservoirs. In order to demonstrate the feasibility of constructing and operating such underground gas storage, a low-permeability gas-storage seepage model considering fracture development was developed and established. The model was solved using semi-analytical methods, and the pressure–response characteristics during natural gas injection were analyzed. The impact of gas injection volume on formation pressure has been clarified, and the calculation method for ultimate injection pressure has been determined. Additionally, through numerical simulation methods, the migration law of acidic gas during gas injection, the variation law of produced acidic gas concentration, and the main control factors affecting the concentration of the produced acidic gas were studied. Furthermore, measures to reduce the concentration of the acidic gas produced were proposed. Finally, injection and production plans were designed for typical depleted acidic gas reservoirs, simulating the operation of gas storage for 12 cycles. The results indicate that the quality of natural gas produced in the third cycle can meet the Class II standard for commercial natural gas. Through this study, the feasibility of constructing gas-storage facilities for acidic depleted gas reservoirs has been demonstrated, and injection and production strategies for this type of gas reservoir have been proposed. Full article