Processes

Research

Jump to: Review

25 pages, 6088 KiB

Open AccessArticle

Production Prediction and Influencing Factors Analysis of Horizontal Well Plunger Gas Lift Based on Interpretable Machine Learning

by Jinbo Liu, Haowen Shi, Jiangling Hong, Shengyuan Wang, Yingqiang Yang, Honglei Liu, Jiaojiao Guo, Zelin Liu and Ruiquan Liao

Processes 2024, 12(9), 1888; https://doi.org/10.3390/pr12091888 - 3 Sep 2024

Viewed by 649

Abstract

With the development of unconventional natural gas resources, plunger gas lift technology has gained widespread application. Accurately predicting gas production from unconventional gas reservoirs is a crucial step in evaluating the effectiveness of plunger gas lift technology and optimizing its design. However, most [...] Read more.

With the development of unconventional natural gas resources, plunger gas lift technology has gained widespread application. Accurately predicting gas production from unconventional gas reservoirs is a crucial step in evaluating the effectiveness of plunger gas lift technology and optimizing its design. However, most existing prediction methods are mechanism-driven, incorporating numerous assumptions and simplifications that make it challenging to fully capture the complex physical processes involved in plunger gas lift technology, ultimately leading to significant errors in capacity prediction. Furthermore, engineering design factors and production system factors associated with plunger gas lift technology can contribute to substantial deviations in gas production forecasts. This study employs three powerful regression algorithms, XGBoost, Random Forest, and SVR, to predict gas production in plunger gas lift wells. This method comprehensively leverages various types of data, including collected engineering design, production system, and production data, directly extracting the underlying patterns within the data through machine learning algorithms to establish a prediction model for gas production in plunger gas lift wells. Among these, the XGBoost algorithm stands out due to its robustness and numerous advantages, such as high accuracy, ability to effectively handle outliers, and reduced risk of overfitting. The results indicate that the XGBoost algorithm exhibits impressive performance, achieving an R² (coefficient of determination) value of 0.87 for six-fold cross-validation and 0.85 for the test set. Furthermore, to address the “black box” problem (the inability to know the internal working structure and workings of the model and to directly understand the decision-making process), which is commonly associated with conventional machine learning models, the SHAP (Shapley additive explanations) method was utilized to globally and locally interpret the established machine learning model, analyze the main factors (such as starting time of wells, gas–liquid ratio, catcher well inclination angle, etc.) influencing gas production, and enhance the credibility and transparency of the model. Taking plunger gas lift wells in southwest China as an example, the effectiveness and practicality of this method are demonstrated, providing reliable data support for shale gas production prediction, and offering valuable guidance for actual on-site production. Full article

(This article belongs to the Special Issue Artificial Intelligent Techniques in the Optimal Operation of Oil and Gas Production Systems)

► Show Figures

Figure 1

24 pages, 5184 KiB

Open AccessArticle

Mathematical Model of the Migration of the CO₂-Multicomponent Gases in the Inorganic Nanopores of Shale

by Xiangji Dou, Hong Li, Sujin Hong, Mingguo Peng, Yanfeng He, Kun Qian, Luyao Guo and Borui Ma

Processes 2024, 12(8), 1679; https://doi.org/10.3390/pr12081679 - 11 Aug 2024

Viewed by 654

Abstract

Nanopores in shale reservoirs refer to extremely small pores within the shale rock, categorised into inorganic and organic nanopores. Due to the differences in the hydrophilicity of the pore walls, the gas migration mechanisms vary significantly between inorganic and organic nanopores. By considering [...] Read more.

Nanopores in shale reservoirs refer to extremely small pores within the shale rock, categorised into inorganic and organic nanopores. Due to the differences in the hydrophilicity of the pore walls, the gas migration mechanisms vary significantly between inorganic and organic nanopores. By considering the impact of irreducible water and the variations in effective migration pathways caused by pore pressure and by superimposing the weights of different migration mechanisms, a mathematical model for the migration of CO₂-multicomponent gases in inorganic nanopores of shale reservoirs has been established. The aim is to accurately clarify the migration laws of multi-component gases in shale inorganic nanopores. Additionally, this paper analyses the contributions of different migration mechanisms and studies the effects of various factors, such as pore pressure, pore size, component ratios, stress deformation, and water film thickness, on the apparent permeability of the multi-component gases in shale inorganic nanopores. The research results show that at high pressure and large pore size (pore pressure greater than 10 MPa, pore size greater than 4 nm), slippage flow dominates, while at low pressure and small pore size (pore pressure less than 10 MPa, pore size less than 4 nm), Knudsen diffusion dominates. With the increase of the stress deformation coefficient, the apparent permeability of gas gradually decreases. When the stress deformation coefficient is less than 0.05 MPa⁻¹, the component ratio significantly impacts bulk apparent permeability. However, when the coefficient exceeds 0.05 MPa⁻¹, this influence becomes negligible. The research results provide a theoretical basis and technical support for accurately predicting shale gas productivity, enhancing shale gas recovery, and improving CO₂ storage efficiency. Full article

(This article belongs to the Special Issue Artificial Intelligent Techniques in the Optimal Operation of Oil and Gas Production Systems)

► Show Figures

Figure 1

16 pages, 1722 KiB

Open AccessArticle

A TCN-BiGRU Density Logging Curve Reconstruction Method Based on Multi-Head Self-Attention Mechanism

by Wenlong Liao, Chuqiao Gao, Jiadi Fang, Bin Zhao and Zhihu Zhang

Processes 2024, 12(8), 1589; https://doi.org/10.3390/pr12081589 - 29 Jul 2024

Viewed by 635

Abstract

In the process of oil and natural gas exploration and development, density logging curves play a crucial role, providing essential evidence for identifying lithology, calculating reservoir parameters, and analyzing fluid properties. Due to factors such as instrument failure and wellbore enlargement, logging data [...] Read more.

In the process of oil and natural gas exploration and development, density logging curves play a crucial role, providing essential evidence for identifying lithology, calculating reservoir parameters, and analyzing fluid properties. Due to factors such as instrument failure and wellbore enlargement, logging data for some well segments may become distorted or missing during the actual logging process. To address this issue, this paper proposes a density logging curve reconstruction model that integrates the multi-head self-attention mechanism (MSA) with temporal convolutional networks (TCN) and bidirectional gated recurrent units (BiGRU). This model uses the distance correlation coefficient to determine curves with a strong correlation to density as a model input parameter and incorporates stratigraphic lithology indicators as physical constraints to enhance the model’s reconstruction accuracy and stability. This method was applied to reconstruct density logging curves in the X depression area, compared with several traditional reconstruction methods, and verified through core calibration experiments. The results show that the reconstruction method proposed in this paper exhibits high accuracy and generalizability. Full article

(This article belongs to the Special Issue Artificial Intelligent Techniques in the Optimal Operation of Oil and Gas Production Systems)

► Show Figures

Figure 1

23 pages, 2056 KiB

Open AccessArticle

Feasibility Study on the Applicability of Intelligent Well Completion

by Alexander Sleptsov, Lyudmila Medvedeva, Oksana Marinina and Olga Savenok

Processes 2024, 12(8), 1565; https://doi.org/10.3390/pr12081565 - 26 Jul 2024

Viewed by 658

Abstract

The relevance of assessing the applicability of intelligent wells using autonomous inflow control devices lies in the active development of the relevant sector of the oil and gas industry and the limited understanding of the economic efficiency of intelligent wells. The use of [...] Read more.

The relevance of assessing the applicability of intelligent wells using autonomous inflow control devices lies in the active development of the relevant sector of the oil and gas industry and the limited understanding of the economic efficiency of intelligent wells. The use of autonomous inflow control devices allows for a change in the composition of flow to the well, thus contributing to delaying the breakthrough of undesirable formation fluids, but at the same time, such an effect affects the dynamics of formation fluid production, which undoubtedly has a huge impact on the economic effect of the project. The analysis of scientific publications on the topic of “intelligent well completion” as a downhole production monitoring and remote production control system has shown that the vast majority of researchers pay attention to the evaluation of technological efficiency, ignoring the economic aspects of the proposed solutions. This study considered the dependence of the economic effect on the geological reservoir and technological well characteristics for variant 1—intelligent horizontal well (HW) completion using autonomous inflow control devices and variant 2—conventional horizontal well completion using the open hole. Calculations of production levels and dynamics in the two variants were performed on a created sector hydrodynamic model of a horizontal well operating in the depletion mode. The analysis of the obtained results allowed us to determine the applicability criteria of the proposed configuration of formation and well characteristics at the object of study, as well as to establish general dependencies of the net discounted income of an intelligent well. As a result of this study, it was determined that the economic efficiency of intelligent well completion with the use of autonomous inflow control devices relative to conventional well completion increases with decreasing permeability and drawdown pressure on the reservoir and reaches maximum values at the object of study at the thickness of the oil-saturated part of the reservoir about 5–6 m and the location of the wellbore in it at 35–40% of the thickness of the oil-saturated part below the gas–oil contact (GOC). This article covers the research gap in evaluating the economic efficiency of intelligent HW completion using AICD relative to conventional HW completion in oil rims. Full article

(This article belongs to the Special Issue Artificial Intelligent Techniques in the Optimal Operation of Oil and Gas Production Systems)

► Show Figures

Figure 1

16 pages, 5104 KiB

Open AccessArticle

Experimental Study on Gas Production Capacity of Composite Reservoir Depletion in Deep Carbonate Gas Reservoirs

by Yuan Li, Qing Qian, Anhai Zhong, Feng Yang, Mingjing Lu, Yuzhe Zhang and Ana Jiang

Processes 2024, 12(8), 1546; https://doi.org/10.3390/pr12081546 - 24 Jul 2024

Viewed by 462

Abstract

Deep carbonate gas reservoirs exhibit diverse reservoir types and complex seepage patterns. To study the gas production capabilities of different composite reservoir types, we classified the reservoirs of the fourth member of the Dengying Formation in the Anyue Gas Field into high-quality reservoirs [...] Read more.

Deep carbonate gas reservoirs exhibit diverse reservoir types and complex seepage patterns. To study the gas production capabilities of different composite reservoir types, we classified the reservoirs of the fourth member of the Dengying Formation in the Anyue Gas Field into high-quality reservoirs (HRs) and poor-quality reservoirs (PRs) based on high-pressure mercury injection (HPMI) experiment results. By varying the differential pressure of the depletion experiment and the connection method, as well as the permeability and water saturation of the composite core, the effects of well location deployment, permeability ratio of the high-quality reservoir and poor-quality reservoir (PRHPR), gas well production pressure difference (GWPPD), and water saturation on the depletion gas production characteristics of the composite reservoir were studied. The research results show that (1) deploying wells on HR enables high gas production rates and ultimate recovery rates; (2) only when the PRHPR falls within a reasonable range (21.88–43.19) can the “dynamic recharge” capability of PR and the high permeability of HR be coordinated to achieve high gas recovery rates; (3) a GWPPD of 3 MPa is optimal, resulting in fast gas production rates and high ultimate recovery rates for PR; (4) high water saturation (≥50%) leads to premature water breakthrough at the well bottom, decreased gas production rate, and sealing of HR and PR reserves by formation water. Combining experimental results with field production data is our next research focus. Our future research focus will be on integrating experimental results with field production data to provide solid theoretical support for the efficient development of this type of gas reservoir. Full article

(This article belongs to the Special Issue Artificial Intelligent Techniques in the Optimal Operation of Oil and Gas Production Systems)

► Show Figures

Figure 1

12 pages, 4391 KiB

Open AccessArticle

Optimization Design of Deep-Coalbed Methane Deliquification in the Linxing Block, China

by Bing Zhang, Wenbo Jiang, Haifeng Zhang and Yongsheng An

Processes 2024, 12(7), 1318; https://doi.org/10.3390/pr12071318 - 25 Jun 2024

Viewed by 1018

Abstract

The production of deep-coalbed methane (CBM) wells undergoes four stages sequentially: drainage depressurization, unstable gas production, stable gas production, and gas production decline. Upon entering the stable production stage, the recovery rate of deep CBM wells is constrained by bottom hole flowing pressure [...] Read more.

The production of deep-coalbed methane (CBM) wells undergoes four stages sequentially: drainage depressurization, unstable gas production, stable gas production, and gas production decline. Upon entering the stable production stage, the recovery rate of deep CBM wells is constrained by bottom hole flowing pressure (BHFP). Reducing BHFP can further optimize CBM productivity, significantly increasing the production and recovery rate of CBM wells. This paper optimizes the deliquification process for deep CBM in the Linxing Block. By analyzing the production of deep CBM wells, an improved sucker rod pump deliquification process is proposed, and a method considering the flow in the tubing, annulus, and reservoir is established. Using the production data of Well GK-25D in the Linxing CBM field as an example, an optimized design of the improved rod pump deliquification process was undertaken, with design parameters including the depth of the sucker rod pump, the stroke length, and stroke rate. The results show that the improved process significantly lowers the pressure at the coalbed, enhancing CBM well production by 12.24%. The improved sucker rod pump process enriches deliquification technology for deep CBM, offering a new approach for its development and helping to maximize CBM well productivity. Full article

(This article belongs to the Special Issue Artificial Intelligent Techniques in the Optimal Operation of Oil and Gas Production Systems)

► Show Figures

Figure 1

23 pages, 9966 KiB

Open AccessArticle

Rapid Classification and Diagnosis of Gas Wells Driven by Production Data

by Zhiyong Zhu, Guoqing Han, Xingyuan Liang, Shuping Chang, Boke Yang and Dingding Yang

Processes 2024, 12(6), 1254; https://doi.org/10.3390/pr12061254 - 18 Jun 2024

Viewed by 761

Abstract

Conventional gas well classification methods cannot provide effective support for gas well routine management, and suffer from poor timeliness. In order to guide the on-site operation in liquid loading gas wells and improve the timeliness of gas well classification, this paper proposes a [...] Read more.

Conventional gas well classification methods cannot provide effective support for gas well routine management, and suffer from poor timeliness. In order to guide the on-site operation in liquid loading gas wells and improve the timeliness of gas well classification, this paper proposes a production data-driven gas well classification method based on the LDA-DA (Linear Discriminant Analysis–Discriminant Analysis) combination model. In this method, considering the requirements of routine management, gas wells are evaluated from two aspects: liquid drainage capacity (LDC) and liquid production intensity (LPI), and are classified into six types. Domain knowledge is used to perform the feature engineering on the on-site production data, and five features are set up to quantitatively evaluate the gas well and to create classification samples. On this basis, in order to specify the optimal data processing flow to establish the gas well classification map, four linear dimensionality reduction techniques, LDA, PCA, LPP, and ICA, are used to reduce the dimensionality of original classification samples, and then, four classical classification algorithms, NB, DA, KNN, and SVM, are trained and evaluated on the low-dimensional samples, respectively. The results show that the LDA space achieves the optimal sample separation and is chosen as the decision space for gas well classification. The DA algorithm obtains the top performance, i.e., the highest Average Macro F1-score of 95.619%, in the chosen decision space, and is employed to determine the classification boundaries in the decision space. At this point, the LDA-DA combination model for sample data processing is developed. Based on this model, gas well classification maps can be established by data mining, and the rapid evaluation and diagnosis of gas wells can be achieved. This method realizes instant and efficient production data-driven gas well classification, and can provide timely decision-making support for gas well routine management. It introduces new ideas for performing gas well classification, expanding the content and scope of the classification work, and presenting valuable insights for further research in this field. Full article

(This article belongs to the Special Issue Artificial Intelligent Techniques in the Optimal Operation of Oil and Gas Production Systems)

► Show Figures

Figure 1

14 pages, 2965 KiB

Open AccessArticle

Study on the Inner Mechanisms of Gas Transport in Matrix for Shale Gas Recovery with In Situ Heating Technology

by Zhongkang Li, Zantong Hu, Ying Li, Xiaojun Wu, Junqiang Tian and Wenjing Zhou

Processes 2024, 12(6), 1247; https://doi.org/10.3390/pr12061247 - 18 Jun 2024

Viewed by 547

Abstract

In order to improve the productivity of shale gas, in situ heating technology has been applied generally. However, this technology is limited by unknown properties in heated matrix, e.g., permeability. Therefore, a method for measuring the permeability of heated shale matrix particles was [...] Read more.

In order to improve the productivity of shale gas, in situ heating technology has been applied generally. However, this technology is limited by unknown properties in heated matrix, e.g., permeability. Therefore, a method for measuring the permeability of heated shale matrix particles was designed, and transport tests were conducted on the shale matrix at heating temperatures of 100~600 degrees centigrade. Through fitting the experimental data with numerical simulation results, pore structures and permeabilities at different heating temperature conditions were obtained and the corresponding transport properties were determined. The porosity and pore radius were positively correlated with the heating temperature, while the tortuosity was negatively correlated with the temperature of the heat treatment. Despite the weakening effect of Knudsen diffusion transport, slippage transport played a critical role in the transport function of the heated shale matrix, and the domination became stronger at higher heating temperatures. The study of gas transport in heated shale matrix provides a guarantee for the effective combination of in situ heating technology. Full article

(This article belongs to the Special Issue Artificial Intelligent Techniques in the Optimal Operation of Oil and Gas Production Systems)

► Show Figures

Figure 1

14 pages, 3937 KiB

Open AccessArticle

Optimization of Energy Consumption in Oil Fields Using Data Analysis

by Xingyuan Liang, Zhisheng Xing, Zhenduo Yue, He Ma, Jin Shu and Guoqing Han

Processes 2024, 12(6), 1090; https://doi.org/10.3390/pr12061090 - 26 May 2024

Viewed by 967

Abstract

In recent years, companies have employed numerous methods to lower expenses and enhance system efficiency in the oilfield. Energy consumption has constituted a significant portion of these expenses. This paper introduces a normalized consumption factor to effectively evaluate energy consumption in the oilfield. [...] Read more.

In recent years, companies have employed numerous methods to lower expenses and enhance system efficiency in the oilfield. Energy consumption has constituted a significant portion of these expenses. This paper introduces a normalized consumption factor to effectively evaluate energy consumption in the oilfield. Statistical analysis has been conducted on nearly 45,000 wells from six fields in China. Critical factors such as lifting method, daily production, pump depth, gas–oil ratio (GOR), and well deviation angle were evaluated individually. Results revealed that higher production could lead to lower normalized consumption for beam pumps, progressive cavity pumps, and electric submersible pump systems, thus enhancing system efficiency. Additionally, a higher GOR might result in lower normalized consumption for the beam pump system, while the deviation angle of the well showed negligible impact on the normalized consumption factor. This manuscript offers a method to assess the impacts of artificial lift methods on production and discusses suggestions for reducing consumption associated with each lifting method in the oilfield. Full article

(This article belongs to the Special Issue Artificial Intelligent Techniques in the Optimal Operation of Oil and Gas Production Systems)

► Show Figures

Figure 1

15 pages, 16102 KiB

Open AccessArticle

Performance and Formula Optimization of Graphene-Modified Tungsten Carbide Coating to Improve Adaptability to High-Speed Fluid Flow in Wellbore

by Minsheng Wang, Lingchao Xuan, Lei Wang and Jiangshuai Wang

Processes 2024, 12(4), 714; https://doi.org/10.3390/pr12040714 - 31 Mar 2024

Viewed by 913

Abstract

In order to improve the erosion resistance of steel PDC (Polycrystalline Diamond Compact) bit under high-speed fluid flow conditions underground, it is necessary to develop a high-performance erosion-resistant coating. In this paper, laser cladding was used to prepare the new coating by modifying [...] Read more.

In order to improve the erosion resistance of steel PDC (Polycrystalline Diamond Compact) bit under high-speed fluid flow conditions underground, it is necessary to develop a high-performance erosion-resistant coating. In this paper, laser cladding was used to prepare the new coating by modifying tungsten carbide with graphene. And the effects of tungsten carbide content and graphene content on the coating performance have been thoroughly studied and analyzed to obtain the optimal covering layer. The research results indicate that, for new coatings, 60% tungsten carbide and 0.3% graphene are the optimal ratios. After adding tungsten carbide, the hardness has significantly improved. However, when the tungsten carbide content further increases more than 30%, the increase in hardness is limited. In addition, when the content of graphene is more than 0.3%, the branched structure becomes thicker. In detail, this is a phenomenon where the segregation of Cr, Si, and W becomes very obvious again, and the segregation of Fe occurs at the Ni enrichment site. The research results contribute to the development and optimization of high-quality erosion-resistant coatings under the high-speed flow conditions in wellbore. These are of great significance for improving the efficiency of oil and gas exploration and development. Full article

(This article belongs to the Special Issue Artificial Intelligent Techniques in the Optimal Operation of Oil and Gas Production Systems)

► Show Figures

Figure 1

10 pages, 776 KiB

Open AccessArticle

A Production Prediction Model of Tight Gas Well Optimized with a Back Propagation (BP) Neural Network Based on the Sparrow Search Algorithm

by Zhengyan Zhao, Zongxiao Ren, Shun’an He, Shanjie Tang, Wei Tian, Xianwen Wang, Hui Zhao, Weichao Fan and Yang Yang

Processes 2024, 12(4), 632; https://doi.org/10.3390/pr12040632 - 22 Mar 2024

Cited by 1 | Viewed by 900

Abstract

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 [...] Read more.

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. Full article

(This article belongs to the Special Issue Artificial Intelligent Techniques in the Optimal Operation of Oil and Gas Production Systems)

► Show Figures

Figure 1

27 pages, 10005 KiB

Open AccessArticle

A Novel Ensemble Machine Learning Model for Oil Production Prediction with Two-Stage Data Preprocessing

by Zhe Fan, Xiusen Liu, Zuoqian Wang, Pengcheng Liu and Yanwei Wang

Processes 2024, 12(3), 587; https://doi.org/10.3390/pr12030587 - 14 Mar 2024

Cited by 2 | Viewed by 1736

Abstract

Petroleum production forecasting involves the anticipation of fluid production from wells based on historical data. Compared to traditional empirical, statistical, or reservoir simulation-based models, machine learning techniques leverage inherent relationships among historical dynamic data to predict future production. These methods are characterized by [...] Read more.

Petroleum production forecasting involves the anticipation of fluid production from wells based on historical data. Compared to traditional empirical, statistical, or reservoir simulation-based models, machine learning techniques leverage inherent relationships among historical dynamic data to predict future production. These methods are characterized by readily available parameters, fast computational speeds, high precision, and time–cost advantages, making them widely applicable in oilfield production. In this study, time series forecast models utilizing robust and efficient machine learning techniques are formulated for the prediction of production. We have fused the two-stage data preprocessing methods and the attention mechanism into the temporal convolutional network-gated recurrent unit (TCN-GRU) model. Firstly, the random forest (RF) algorithm is employed to extract key dynamic production features that influence output, serving to reduce data dimensionality and mitigate overfitting. Next, the mode decomposition algorithm, complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), is introduced. It employs a decomposition–reconstruction approach to segment production data into high-frequency noise components, low-frequency regular components and trend components. These segments are then individually subjected to prediction tasks, facilitating the model’s ability to capture more accurate intrinsic relationships among the data. Finally, the TCN-GRU-MA model, which integrates a multi-head attention (MA) mechanism, is utilized for production forecasting. In this model, the TCN module is employed to capture temporal data features, while the attention mechanism assigns varying weights to highlight the most critical influencing factors. The experimental results indicate that the proposed model achieves outstanding predictive performance. Compared to the best-performing comparative model, it exhibits a reduction in RMSE by 3%, MAE by 1.6%, MAPE by 12.7%, and an increase in R² by 2.6% in Case 1. Similarly, in Case 2, there is a 7.7% decrease in RMSE, 7.7% in MAE, 11.6% in MAPE, and a 4.7% improvement in R². Full article

(This article belongs to the Special Issue Artificial Intelligent Techniques in the Optimal Operation of Oil and Gas Production Systems)

► Show Figures

Figure 1

14 pages, 4423 KiB

Open AccessArticle

Study on Micro-Pressure Drive in the KKM Low-Permeability Reservoir

by Heng Zhang, Mibang Wang, Wenqi Ke, Xiaolong Li, Shengjun Yang and Weihua Zhu

Processes 2024, 12(3), 571; https://doi.org/10.3390/pr12030571 - 14 Mar 2024

Viewed by 840

Abstract

Kazakhstan has abundant resources of low-permeability oil reservoirs, among which the KKM low-permeability oil reservoir has geological reserves of 3844 × 10⁴ t and a determined recoverable reserve of 1670 × 10⁴ t. However, the water flooding efficiency is only 68%, [...] Read more.

Kazakhstan has abundant resources of low-permeability oil reservoirs, among which the KKM low-permeability oil reservoir has geological reserves of 3844 × 10⁴ t and a determined recoverable reserve of 1670 × 10⁴ t. However, the water flooding efficiency is only 68%, and the recovery efficiency is as low as 32%. The development of the reservoir faces challenges such as water injection difficulties and low oil production from wells. In order to further improve the oil recovery rate of this reservoir, our team developed micro-pressure-driven development technology based on pressure-driven techniques by integrating theories of fluid mechanics and artificial intelligence. We also combined this with subsequent artificial lift schemes, resulting in a complete set of micro-pressure-driven process technology. The predicted results indicate that after implementing micro-pressure-driven techniques, a single well group in the KKM oilfield can achieve a daily oil production increase of 32.08 t, demonstrating a good development effect. Full article

(This article belongs to the Special Issue Artificial Intelligent Techniques in the Optimal Operation of Oil and Gas Production Systems)

► Show Figures

Figure 1

19 pages, 3459 KiB

Open AccessArticle

A Novel Prediction Model for Steam Temperature Field of Downhole Multi-Thermal Fluid Generator

by Yanfeng He, Zhiqiang Huang, Xiangji Dou, Yisong Zhang, Le Hua and Jing Guo

Processes 2024, 12(3), 485; https://doi.org/10.3390/pr12030485 - 27 Feb 2024

Viewed by 1067

Abstract

Aiming at the low efficiency of heavy-oil thermal recovery, a downhole multi-thermal fluid generator (DMTFG) can improve the viscosity reduction effect by reducing the heat loss of multi-thermal fluid in the process of wellbore transportation. The steam generated by the MDTFG causes damage [...] Read more.

Aiming at the low efficiency of heavy-oil thermal recovery, a downhole multi-thermal fluid generator (DMTFG) can improve the viscosity reduction effect by reducing the heat loss of multi-thermal fluid in the process of wellbore transportation. The steam generated by the MDTFG causes damage to the packer and casing, owing to the return upwards along the annular space passage of the oil casing. To mitigate this damage, a heat transfer model for multi-channel coiled tubing wells and a prediction model for the upward return of the steam temperature field in the annulus were established with the basic laws of thermodynamics. Models were further verified by ANSYS. The results indicate the following four conclusions. First of all, when the surface pressure is constant, the deeper the located DMTFG, the shorter the distance for the steam to return would be. It is easier to liquefy the steam. Second, the higher the temperature of the steam produced by the downhole polythermal fluid generator, the larger the upward distance of the steam would be. Third, the higher the steam pressure at the outlet of the downhole polythermal fluid generator, the smaller the distance of steam upward return would be. Finally, the larger the diameter of the multi-channel conversion piping, the greater the distance of the steam return would be. It is meaningful to provide valuable theoretical guidance for packer position designing in the field. Meanwhile, the study also provides a modeling basis for the subsequent study of artificial intelligence in the downhole temperature field. Full article

(This article belongs to the Special Issue Artificial Intelligent Techniques in the Optimal Operation of Oil and Gas Production Systems)

► Show Figures

Figure 1

18 pages, 4612 KiB

Open AccessArticle

Cooling Damage Characterization and Chemical-Enhanced Oil Recovery in Low-Permeable and High-Waxy Oil Reservoirs

by Xuanran Li, Lun Zhao, Ruijie Fei, Jincai Wang, Shanglin Liu, Minghui Li, Shujun Han, Fujian Zhou and Shuai Yuan

Processes 2024, 12(2), 421; https://doi.org/10.3390/pr12020421 - 19 Feb 2024

Viewed by 1246

Abstract

The well productivity of high-waxy reservoirs is highly influenced by temperature changes. A decrease in temperature can cause the precipitation of wax from the crude oil, leading to a decrease in the formation’s drainage capacity and a drop in oil production. In this [...] Read more.

The well productivity of high-waxy reservoirs is highly influenced by temperature changes. A decrease in temperature can cause the precipitation of wax from the crude oil, leading to a decrease in the formation’s drainage capacity and a drop in oil production. In this study, the wax precipitation of crude oil is characterized by rheological properties tests and differential scanning calorimetry (DSC) thermal analysis. The wax damage characteristics of cores and the relative permeability curves at different temperatures were investigated through coreflood experiments. Furthermore, nanoemulsion is selected as a chemical agent for injection fluid. The nuclear magnetic resonance (NMR) scanning technique is used to investigate the effects of oil recovery enhancement at different pores by increasing temperature and adding nanoemulsion. By comparing the changes in T₂ spectra and the distribution pattern of residual oil before and after liquid injection, the results have shown that both increasing temperature and adding nanoemulsion have a significant effect on oil recovery. The improvement of micropores is less pronounced compared to macropores. The produced oil mainly comes from the large pores. When the temperature is lower than the crude oil dewaxing point temperature, there is a serious dewaxing plugging phenomenon in the pores. Additionally, by observing the pattern of residual oil distribution at the end of the NMR online drive, it is hereby classified into wax deposition retention type, weak water washing retention type, and immobilized type, each with its own distinct characteristics. Wettability alteration and interfacial tension reduction can help to improve the drainage capacity of high-wax oil reservoirs, which is the main mechanism of nanoemulsion for enhanced oil recovery. These findings are highly valuable for enhancing the comprehension of the impact of highly waxed crude oils on drainage capacity and the ultimate oil recovery rate, particularly in relation to wax precipitation deposition. Full article

(This article belongs to the Special Issue Artificial Intelligent Techniques in the Optimal Operation of Oil and Gas Production Systems)

► Show Figures

Figure 1

Review

Jump to: Research

19 pages, 378 KiB

Open AccessReview

Machine Learning in Reservoir Engineering: A Review

by Wensheng Zhou, Chen Liu, Yuandong Liu, Zenghua Zhang, Peng Chen and Lei Jiang

Processes 2024, 12(6), 1219; https://doi.org/10.3390/pr12061219 - 14 Jun 2024

Viewed by 1401

Abstract

With the rapid progress of big data and artificial intelligence, machine learning technologies such as learning and adaptive control have emerged as a research focus in petroleum engineering. They have various applications in oilfield development, such as parameter prediction, optimization scheme deployment, and [...] Read more.

With the rapid progress of big data and artificial intelligence, machine learning technologies such as learning and adaptive control have emerged as a research focus in petroleum engineering. They have various applications in oilfield development, such as parameter prediction, optimization scheme deployment, and performance evaluation. This paper provides a comprehensive review of these applications in three key scenarios of petroleum engineering, namely hydraulic fracturing and acidizing, chemical flooding and gas flooding, and water injection. This article first introduces the steps and methods of machine learning processing in these scenarios, then discusses the advantages, disadvantages, existing challenges, and future prospects of these machine learning methods. Furthermore, this article compares and contrasts the strengths and weaknesses of these machine learning methods, aiming to help researchers select and improve their methods. Finally, this paper identifies some potential development trends and research directions of machine learning in petroleum engineering based on the current issues. Full article

(This article belongs to the Special Issue Artificial Intelligent Techniques in the Optimal Operation of Oil and Gas Production Systems)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Artificial Intelligent Techniques in the Optimal Operation of Oil and Gas Production Systems

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (16 papers)

Research

Review

Further Information

Guidelines

MDPI Initiatives

Follow MDPI