Method, device and equipment for predicting ultimate recoverable reserves of fractured well
By constructing an integrated geological reservoir model and data-driven methods, combined with fracture stress sensitivity and long-term conductivity models, the problem of low EUR prediction accuracy in fractured wells was solved, enabling rapid and accurate prediction and optimization design of final recoverable reserves.
Patent Information
- Application Number
- CN202510576035.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-06
- Publication Date
- 2026-11-06
AI Technical Summary
Existing methods for predicting the final recoverable reserves of fractured wells fail to effectively consider the changes in actual fracture morphology and conductivity over time, resulting in low prediction accuracy and efficiency.
A fully integrated geological reservoir model was constructed, combining a fracture stress-sensitive model and a long-term conductivity model. By simulating different fracturing operation parameters, the final recoverable reserves prediction model was trained, and data-driven methods such as neural networks were used to optimize the prediction.
It enables rapid and accurate prediction of the final recoverable reserves of fractured wells, helps optimize fracturing design, and improves the accuracy and efficiency of prediction.
Smart Images
Figure CN123044260A_ABST
Abstract
Description
Technical Field
[0001] The embodiments of the present invention relate to the field of oil and gas exploration and development technology, and in particular to a method, apparatus and equipment for predicting the final recoverable reserves of a fractured well. Background Technology
[0002] Ultimate Recoverable Reserves (EUR) are used to predict the total amount of oil and gas a well or gas well can produce throughout its entire lifecycle. This metric is crucial for assessing the commercial value and development potential of oil and gas wells. Currently, horizontal well staged fracturing technology is widely used in different types of oil and gas reservoirs, such as tight sandstone oil and gas, tight carbonate oil and gas, shale oil and gas, and deep coalbed methane, significantly increasing fracture volume and post-fracturing production. For oil and gas, the predicted EUR after horizontal well staged fracturing is critical to fracturing design, affecting the optimization of well pattern parameters, fracture parameters, and fracturing process parameters, as well as the economic benefits.
[0003] Currently, the prediction of EUR (Effective Fluid Regulator) in fractured wells is mainly based on model-driven methods. This involves setting up rectangular fractures within the oil and gas reservoir based on geological modeling, with the fracture height remaining constant and equal to the effective reservoir thickness. Then, the EUR is predicted for different fracture lengths, conductivity, and number of fractures. However, because the fracture parameters in these model-driven methods are idealized and do not consider actual fracture morphology, the prediction accuracy is relatively low. Summary of the Invention
[0004] The purpose of this invention is to provide at least one method, apparatus, and equipment for predicting the final recoverable reserves of fractured wells, in order to solve the problem of low prediction accuracy of existing methods.
[0005] To address the aforementioned technical problems, at least one embodiment of this application provides a method for predicting the final recoverable reserves of a fractured well, comprising:
[0006] A fully integrated geological reservoir model of the target block was constructed, which coupled a fracture stress sensitivity model and a long-term conductivity model.
[0007] A fully integrated model was used to simulate the target block under different fracturing operation parameters to obtain the final recoverable reserves of the target block under different fracturing operation parameters.
[0008] Using the geological parameters, well network parameters, fracture parameters, and fracturing operation parameters of the target block as input data, and the final recoverable reserves corresponding to the fracturing operation parameters as the expected output data, the final recoverable reserves prediction model is trained to obtain the trained final recoverable reserves prediction model.
[0009] The final recoverable reserves of the target well under different fracturing scales are predicted using a trained final recoverable reserves prediction model.
[0010] In some embodiments, the method further includes:
[0011] The goal of fracturing design is to achieve the preset limit value of the final recoverable reserves of the target well, or to maximize the final recoverable reserves per unit input. Based on the trained final recoverable reserves prediction model, the optimal combination of fracturing construction parameters is determined.
[0012] In some embodiments, a fully integrated geological reservoir model of the target block is constructed, including:
[0013] Based on the seismic data, well logging data, well engineering data, geostress data, geological data, and fracturing operation data of the target block, an integrated preliminary model of the target block is established.
[0014] Artificial fractures were simulated based on geological models and different fracturing construction parameters to obtain artificial fracture models of the target block.
[0015] Based on the integrated preliminary model and the artificial fracture model, the superposition effect of induced stress caused by hydraulic fracturing and its influence on permeability are coupled to obtain an integrated updated model that couples the fracture stress sensitivity model.
[0016] Based on the integrated update model, the long-term conductivity model is coupled to obtain a fully integrated model that couples the crack stress sensitivity model and the long-term conductivity model.
[0017] In some embodiments, the long-term conductivity model is generated by simulating the long-term conductivity of the main fracture and branch fractures under different closure stresses and sand concentrations using a physical model.
[0018] In some embodiments, well pattern parameters include horizontal section length, well spacing, cluster spacing, fracture length, and conductivity.
[0019] In some embodiments, geological parameters include permeability, porosity, hydrocarbon saturation, and formation pressure.
[0020] In some embodiments, the final recoverable reserves prediction model is built based on a neural network model, a random forest model, a Naive Bayes model, or a support vector machine model.
[0021] At least one embodiment of this application also provides a device for predicting the final recoverable reserves of a fractured well, comprising:
[0022] The building module is used to construct a fully integrated geological reservoir model of the target block. The fully integrated model couples the fracture stress sensitivity model and the long-term conductivity model.
[0023] The generation module is used to simulate the target block with different fracturing operation parameters using a fully integrated model, and obtain the final recoverable reserves of the target block under different fracturing operation parameters.
[0024] The training module is used to train the final recoverable reserves prediction model by taking the geological parameters, well network parameters, fracture parameters and fracturing operation parameters of the target block as input data and the final recoverable reserves corresponding to the fracturing operation parameters as the expected output data, so as to obtain the trained final recoverable reserves prediction model.
[0025] The prediction module is used to predict the final recoverable reserves of the target well under different fracturing scales using a trained final recoverable reserves prediction model.
[0026] At least one embodiment of this application also provides an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the above-described method for predicting the final recoverable reserves of a fractured well.
[0027] At least one embodiment of this application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for predicting the final recoverable reserves of fractured wells.
[0028] The embodiments of this application provide a method, apparatus, and equipment for predicting the final recoverable reserves of fractured wells. This involves constructing a fully integrated geological reservoir model of the target block, which couples a fracture stress-sensitive model and a long-term conductivity model. The fully integrated model is used to simulate different fracturing operation parameters for the target block, obtaining the corresponding final recoverable reserves under these parameters. Using the geological parameters, well network parameters, fracture parameters, and fracturing operation parameters of the target block as input data, and the final recoverable reserves corresponding to the fracturing operation parameters as the expected output data, the final recoverable reserves prediction model is trained to obtain a trained model. This trained model is then used to predict the final recoverable reserves of the target well under different fracturing scales. Based on a dual-drive approach of model and data, the final recoverable reserves of the target well can be predicted quickly and accurately. Attached Figure Description
[0029] One or more embodiments are illustrated by way of example with reference to the accompanying drawings, and these illustrative descriptions do not constitute a limitation on the embodiments.
[0030] Figure 1 This is a flowchart of a method for predicting the final recoverable reserves of a fractured well, provided in one embodiment of this application;
[0031] Figure 2 This is a schematic diagram of an integrated numerical simulation model of geological reservoirs provided in one embodiment of this application;
[0032] Figure 3 This is a schematic diagram of post-compression EUR data-driven modeling provided in one embodiment of this application;
[0033] Figure 4 This is a flowchart of a method for predicting the final recoverable reserves of a fractured well, provided in another embodiment of this application;
[0034] Figure 5 This is a schematic diagram of a device for predicting the final recoverable reserves of a fractured well, provided in one embodiment of this application;
[0035] Figure 6 This is a schematic diagram of the structure of an electronic device provided in one embodiment of this application. Detailed Implementation
[0036] To enable those skilled in the art to better understand the technical solutions of this disclosure, and to fully understand and implement the process of how this disclosure applies technical means to solve technical problems and achieve corresponding technical effects, the technical solutions in the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, not all embodiments. The embodiments of this disclosure and the various features within them can be combined with each other without conflict, and the resulting technical solutions are all within the protection scope of this disclosure. All other embodiments obtained by those skilled in the art based on the embodiments of this disclosure without creative effort should fall within the protection scope of this disclosure.
[0037] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.
[0038] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.
[0039] Horizontal well staged fracturing technology has been widely applied to various types of oil and gas reservoirs, such as tight sandstone oil and gas, tight carbonate oil and gas, shale oil and gas, and deep coalbed methane, significantly increasing fracture volume and post-fracturing production. Furthermore, it has applications in hot dry rock and energy storage, greatly improving thermal and energy storage efficiency. For oil and gas, predicting the ultimate recovery (EUR) after horizontal well staged fracturing is crucial for fracturing design, as it relates to the optimization of well pattern parameters, fracture parameters, and fracturing process parameters, as well as economic benefits. However, due to the numerous influencing factors on post-fracturing EUR, such as geological parameters like permeability, porosity, oil and gas saturation, and formation pressure, as well as well pattern parameters and fracture geometry parameters like horizontal section length, well spacing, cluster spacing (number of fractures), fracture length, and conductivity, accurate prediction is challenging.
[0040] Currently, the main method for predicting the EUR (Earnings Per Second) of fractured wells is model-driven, integrating geological modeling with reservoir simulation. The main approach involves setting up rectangular fractures within the reservoir based on geological modeling, with a constant fracture height equal to the effective reservoir thickness. Then, the post-fracture production and EUR are examined under different fracture lengths, conductivity, and number of fractures (for simplicity, the cumulative production over 20 years after fracturing can be simulated; for oil and gas wells, this is generally converted to hydrocarbon equivalents). However, for well factories, if horizontal section lengths and well spacing are not predetermined, well network parameters need to be incorporated into the reservoir model for the EUR simulation. Clearly, this model-driven method has several limitations. For example, the fracture parameter settings are relatively idealized, failing to consider actual wedge-shaped fracture morphology, the time-varying nature of fracture conductivity, or the time-varying nature of conductivity in complex fracture morphologies and secondary fractures (which exhibit a significantly different conductivity reduction pattern from the main fracture). Therefore, the accuracy of current methods for EUR prediction is relatively low, and their prediction efficiency is also relatively low.
[0041] To address the low prediction accuracy of existing technologies, this application proposes a model- and data-driven method for predicting the final recoverable reserves (EUR) of fractured wells. This aims to improve the accuracy of EUR prediction for new fractured wells and assist researchers in optimizing well plant fracturing development schemes. First, an integrated geological and reservoir numerical simulation initial model is established. Then, an integrated numerical simulation model is formed by coupling induced stress and long-term conductivity models through artificial fracture simulation and a physical model. Finally, post-fracture EUR is simulated and calculated under different construction parameters. A surrogate model is generated using a data-driven method for post-fracture EUR prediction and fracturing construction parameter optimization. Specific embodiments will be provided below to further illustrate the method. The following details are for illustrative purposes only and are not essential for implementing this solution.
[0042] Example 1:
[0043] Figure 1 This is a flowchart illustrating a method for predicting the final recoverable reserves of fractured wells according to an embodiment of this application. The method for predicting the final recoverable reserves of fractured wells in this embodiment can be applied to electronic devices with communication, computing, and data storage capabilities. For example... Figure 1 As shown, the method for predicting the final recoverable reserves of fractured wells provided in this embodiment may include:
[0044] S101. Construct a fully integrated geological reservoir model for the target block. The fully integrated model couples the fracture stress sensitivity model and the long-term conductivity model.
[0045] This embodiment further expands the integration of geological modeling and reservoir simulation to include geological modeling, hydraulic fracturing simulation, and reservoir simulation. In other words, the previously idealized fracture parameters are transformed into realistic fracture morphology and parameters through fracturing simulation, resulting in a more accurate and reliable EUR (Effective Urge Scale) prediction for the reservoir. Simultaneously, the superposition effect of induced stress caused by fracturing and its impact on permeability (obtainable from core stress sensitivity experiments) are coupled into the geological model, further increasing the accuracy of fracturing EUR prediction. Furthermore, based on the fracturing simulation results, long-term fracture conductivity tests are conducted on the main fracture and the deflector fractures. It is important to note that the latter experiences higher effective stress and lower sand concentration; therefore, its conductivity decreases more rapidly, meaning the deflector fracture will fail more quickly.
[0046] The fully integrated geological reservoir model in this embodiment couples a fracture stress-sensitive model and a long-term conductivity model, which helps improve the accuracy of EUR prediction. Its model construction can be referenced from... Figure 2 As shown.
[0047] S102. A fully integrated model is used to simulate the target block under different fracturing operation parameters to obtain the final recoverable reserves of the target block under different fracturing operation parameters.
[0048] Considering that simulating EUR (Effective Recovery Rate) requires 20 years or even longer, while the effective period of fracturing is certainly not that long, the average effective period of fracturing in the target block can be statistically analyzed on-site. In reservoir simulation, if the second effective period begins, the long-term conductivity of fractures at different scales can be redesigned to be the same as the first effective period, and so on, until the simulation of 20 or even 30 years is completed. Orthogonal experimental design can simulate EUR under different fracturing operation parameters to obtain the final recoverable reserves of the target block under different fracturing operation parameters. Based on the above simulation process, a post-fracturing EUR database can be constructed. The database can include input data such as geological parameters, well pattern parameters, fracture parameters, and fracturing operation parameters, as well as the corresponding final recoverable reserves under each fracturing operation parameter as output data.
[0049] S103. Using the geological parameters, well network parameters, fracture parameters, and fracturing operation parameters of the target block as input data, and the final recoverable reserves corresponding to the fracturing operation parameters as the expected output data, the final recoverable reserves prediction model is trained to obtain the trained final recoverable reserves prediction model.
[0050] The well network parameters in this embodiment may include horizontal section length, well spacing, cluster spacing, fracture length, and conductivity; the geological parameters in this embodiment may include permeability, porosity, hydrocarbon saturation, and formation pressure; the final recoverable reserves prediction model in this embodiment may be constructed based on a neural network model, a random forest model, a Naive Bayes model, or a support vector machine model.
[0051] In this implementation, the data obtained from the database in step S102 can be used for model training. Specifically, the geological parameters, well network parameters, fracture parameters, and fracturing operation parameters of the target block are used as input data, and the final recoverable reserves corresponding to the fracturing operation parameters are used as the expected output data to train the final recoverable reserves prediction model. The modeling process of the final recoverable reserves prediction model in this embodiment, i.e., the post-fracturing EUR data-driven model, can be referred to... Figure 3 As shown. For example, 80% of the data can be used as the training set, 10% as the validation set, and 10% as the test set. The validation set is used for hyperparameter optimization, and the test set is used for data-driven model accuracy evaluation and optimization.
[0052] S104. Use the trained final recoverable reserves prediction model to predict the final recoverable reserves of the target well under different fracturing scales.
[0053] After obtaining a trained final recoverable reserves prediction model, it can be used to predict the final recoverable reserves of the target well under different fracturing scales. Specifically, the geological parameters, well pattern parameters, fracture parameters, and fracturing operation parameters of the target well can be input into the trained final recoverable reserves prediction model to obtain the final recoverable reserves corresponding to the fracturing operation parameters. Changing the fracturing operation parameters will yield the final recoverable reserves of the target well under different fracturing scales.
[0054] Furthermore, in order to optimize fracturing construction parameters and help researchers optimize the design of fracturing development schemes for well factories, the goal of fracturing design can be to achieve a preset limit value for the final recoverable reserves of the target well, or to maximize the final recoverable reserves per unit input. Based on a trained final recoverable reserves prediction model, the optimal combination of fracturing construction parameters can be determined.
[0055] The method for predicting the final recoverable reserves of fractured wells provided in this embodiment constructs a fully integrated geological reservoir model of the target block, which couples a fracture stress-sensitive model and a long-term conductivity model. The fully integrated model is used to simulate different fracturing operation parameters for the target block, obtaining the corresponding final recoverable reserves under different fracturing operation parameters. Using the geological parameters, well pattern parameters, fracture parameters, and fracturing operation parameters of the target block as input data, and the final recoverable reserves corresponding to the fracturing operation parameters as the expected output data, the final recoverable reserves prediction model is trained to obtain a trained final recoverable reserves prediction model. This trained final recoverable reserves prediction model is then used to predict the final recoverable reserves of the target well under different fracturing scales. Based on a dual-drive approach of model and data, the final recoverable reserves of the target well can be predicted quickly and accurately.
[0056] Example 2:
[0057] Based on the above embodiments, this embodiment further details how to construct a fully integrated geological reservoir model for a target block. The method for predicting the final recoverable reserves of fractured wells provided in this embodiment involves constructing a fully integrated geological reservoir model for the target block, which specifically includes: establishing an integrated preliminary model of the target block based on seismic data, well logging data, well engineering data, geostress data, geological data, and fracturing operation data; simulating artificial fractures based on the geological model and different fracturing operation parameters to obtain an artificial fracture model for the target block; coupling the induced stress superposition effect caused by fracturing and its impact on permeability based on the integrated preliminary model and the artificial fracture model to obtain an integrated updated model coupled with a fracture stress-sensitive model; and coupling a long-term conductivity model based on the integrated updated model to obtain a fully integrated model coupled with both the fracture stress-sensitive model and the long-term conductivity model.
[0058] The integrated preliminary model can be established based on multi-source data such as seismic, drilling, logging, testing, and post-fracturing production. A preliminary static geological model (including a geometric model, physical property parameter model, and geostress model) is established, and a numerical simulation model is created by coupling dynamic seepage mechanisms. Based on the geological model (including the geostress model) and different fracturing construction parameters, the artificial fracture simulation module is used to simulate the morphology and geometric parameters of the fractures after fracturing, especially the morphology and conductivity of the main supporting fracture and the deflecting branch fractures.
[0059] Based on the net pressure under different construction scales, the corresponding induced stress transmission law is calculated using formulas related to solid mechanics, including the transmission range and the corresponding changes in geostress magnitude. This mainly refers to the induced stress at the minimum horizontal principal stress, while the induced stress at the maximum horizontal principal stress can also be calculated using established formulas. Based on the induced stress simulation results, the stress resulting from the superposition of induced stresses at different distances along the vertical fracture wall is calculated. Then, the permeability and its changes under the corresponding stress are simulated and calculated, thus correcting the geological model of the target well layer.
[0060] The long-term conductivity model in this embodiment is generated by simulating the long-term conductivity of the main fracture and branch fractures under different closure stresses and sand concentrations using a physical model.
[0061] Based on the above embodiments, the method for predicting the final recoverable reserves (EUR) of fractured wells provided in this embodiment further establishes an integrated preliminary model of the target block based on seismic data, well logging data, well engineering data, geostress data, geological data, and fracturing operation data. Artificial fractures are simulated based on the geological model and different fracturing operation parameters to obtain an artificial fracture model of the target block. Based on the integrated preliminary model and the artificial fracture model, the induced stress superposition effect caused by fracturing and its impact on permeability are coupled to obtain an integrated updated model coupled with a fracture stress-sensitive model. Based on the integrated updated model, a long-term conductivity model is coupled to obtain a fully integrated model coupling the fracture stress-sensitive model and the long-term conductivity model, which helps to further improve the accuracy of EUR prediction.
[0062] Example 3:
[0063] Based on the above embodiments, the following will further illustrate the model- and data-driven EUR prediction method for fractured wells provided in this application through specific examples. The specific process can be found in [reference needed]. Figure 4 As shown. Specifically, it can include:
[0064] (1) Establish an integrated geological reservoir model
[0065] Based on multi-source data such as seismic, drilling, logging, testing, and post-pressure production, a preliminary static geological model (including geometric model, physical property parameter model, and geostress model) is established, and a numerical simulation model is established by coupling dynamic seepage mechanism.
[0066] (2) Artificial crack modeling
[0067] Based on geological models (including geostress models) and different fracturing construction parameters, the artificial fracture simulation module was used to study the morphology and geometric parameters of the fractures after fracturing, especially the morphology and conductivity of the main supporting fracture and the deflecting branch fractures.
[0068] (3) Coupled crack stress-sensitive model
[0069] Based on steps (1) and (2), the induced stress transmission law is calculated according to the formulas related to solid mechanics based on the net pressure under different construction scales, including the transmission range and the corresponding changes in the magnitude of geostress. Here, it mainly refers to the induced stress on the minimum horizontal principal stress, while the induced stress on the maximum horizontal principal stress can also be calculated using mature formulas. Based on the induced stress simulation results, the stress after superposition of induced stresses at different distances from the vertical fracture wall is calculated, and then the permeability and its changes under the corresponding stress are simulated and calculated. The geological model of the target well layer is modified. Based on the results of steps (2)-(3), the geological model obtained in step (1) is modified accordingly.
[0070] (4) Simulation of long-term flow conduction in the fracture
[0071] Based on step (3), the long-term conductivity of the main crack and branch cracks under different closure stresses and sand concentrations is simulated using a physical model. The simulation generally lasts for about 14 days, and the closure stress should be converted to the effective closure stress. This is a completely different concept from the previous 50-hour test for each effective closure stress.
[0072] (5) Complete establishment of oil and gas reservoir model
[0073] The results of steps (3) and (4) are put into the preliminary oil and gas reservoir model of step (1) to establish the final oil and gas reservoir model that incorporates the actual fracture morphology and the time-varying conductivity of fractures at different scales.
[0074] Among them, the wedge-shaped crack support morphology setting can be finely simulated based on unstructured mesh, while the crack width needs to be enlarged by a certain scale, but the permeability needs to be reduced proportionally to ensure that the crack conductivity remains constant.
[0075] It should be noted that the long-term conductivity test time for fractures is generally 14 days, and needs to be extended to a longer period of 3 or even 5 years, which is the effective period of fracturing. The conductivity measured in laboratory experiments over time can be extrapolated to 3 or even 5 years. If the conductivity decreases to 0 in less than 3 or 5 years, the decrease rate between the 13th and 14th day in the laboratory can be used as the monthly or annual decrease rate.
[0076] (6) Simulation of EUR after compression
[0077] Considering that simulating EUR (Effective Fluctuation Regime) requires 20 years or even longer, while the effective period of fracturing is certainly not that long, the average effective period of fracturing in the target block can be statistically analyzed on-site. In reservoir simulation, if the second effective period begins, the long-term conductivity of fractures at different scales can be redesigned to be the same as the first effective period, and so on, until the simulation of 20 or even 30 years is completed. Orthogonal experimental design is used to simulate EUR under different fracturing operation parameters.
[0078] (7) Establishment of EUR database after compression
[0079] The input data (geological parameters, well network parameters, fracture parameters, fracturing construction parameters) and output data (EUR) of the simulated EUR in step (6) are all stored in specific fields of the database.
[0080] (8) Data-driven modeling
[0081] Commonly used data-driven models such as neural network models, random forests, Naive Bayes, and SVM models can be applied. 80% of the data in step (6) is used as the training set, 10% as the validation set, and 10% as the test set. The validation set is used for hyperparameter optimization, and the test set is used for data-driven model accuracy evaluation and optimization.
[0082] (9) Application of EUR model for fractured wells based on model and data dual-drive
[0083] Based on the target well, the learning model of step (8) is applied to predict the EUR under different fracturing scales of the target well. Then, the goal of fracturing design is to reach a certain limit value of the EUR of a single well or to maximize the EUR per unit input within a certain EUR range. In this way, the optimized combination of fracturing construction parameters is obtained.
[0084] In summary, to address the current issues of low accuracy and long prediction cycles for post-fracture EUR (Effective Urge) in horizontal wells, this application presents a model- and data-driven method for predicting EUR in fractured wells. This method aims to quickly and accurately provide post-fracture EUR prediction values. An integrated geological and reservoir numerical simulation initial model is established. Through artificial fracture simulation and a physical model, coupled with induced stress and long-term conductivity models, an integrated numerical simulation model is formed. This model simulates and calculates post-fracture EUR under different construction parameters. A surrogate model is generated using a data-driven approach for post-fracture EUR prediction and optimization of fracturing construction parameters. The method provided in this application will effectively improve the intelligent decision-making and management level of well sites, providing a scientific basis for improving the quality and efficiency of shale oil and gas development.
[0085] Example 4:
[0086] Another embodiment of this application relates to a device for predicting the final recoverable reserves of a fractured well. The implementation details of this device are described below. The following details are for ease of understanding and are not essential for implementing this solution. A schematic diagram of the device for predicting the final recoverable reserves of a fractured well in this embodiment can be seen as follows: Figure 5 As shown, it includes: a construction module 501, a generation module 502, a training module 503, and a prediction module 504.
[0087] At least one embodiment of this application also provides a device for predicting the final recoverable reserves of a fractured well, comprising:
[0088] Module 501 is used to construct a fully integrated geological reservoir model of the target block. The fully integrated model couples the fracture stress sensitivity model and the long-term conductivity model.
[0089] The generation module 502 is used to simulate the target block with different fracturing construction parameters using a fully integrated model, and to obtain the final recoverable reserves of the target block under different fracturing construction parameters.
[0090] Training module 503 is used to train the final recoverable reserves prediction model with geological parameters, well network parameters, fracture parameters and fracturing construction parameters of the target block as input data and the final recoverable reserves corresponding to the fracturing construction parameters as the expected output data, so as to obtain the trained final recoverable reserves prediction model.
[0091] Prediction module 504 is used to predict the final recoverable reserves of the target well under different fracturing scales using a trained final recoverable reserves prediction model.
[0092] The apparatus of this embodiment can be used to perform Figure 1 The technical solutions of the method embodiments shown are similar in principle and in effect, and will not be described again here.
[0093] In some optional implementations, the prediction module 504 is also used to determine an optimized combination of fracturing construction parameters based on a trained final recoverable reserves prediction model, with the goal of achieving a preset limit value for the final recoverable reserves of the target well, or maximizing the final recoverable reserves per unit input.
[0094] In some optional implementations, the construction module 501 is used to construct a fully integrated geological reservoir model of the target block, which may specifically include:
[0095] Based on the seismic data, well logging data, well engineering data, geostress data, geological data, and fracturing operation data of the target block, an integrated preliminary model of the target block is established.
[0096] Artificial fractures were simulated based on geological models and different fracturing construction parameters to obtain artificial fracture models of the target block.
[0097] Based on the integrated preliminary model and the artificial fracture model, the superposition effect of induced stress caused by hydraulic fracturing and its influence on permeability are coupled to obtain an integrated updated model that couples the fracture stress sensitivity model.
[0098] Based on the integrated update model, the long-term conductivity model is coupled to obtain a fully integrated model that couples the crack stress sensitivity model and the long-term conductivity model.
[0099] In some alternative implementations, the long-term conductivity model is generated by simulating the long-term conductivity of the main fracture and branch fractures under different closure stresses and sand concentrations using a physical model.
[0100] In some alternative implementations, well pattern parameters include horizontal section length, well spacing, cluster spacing, fracture length, and conductivity.
[0101] In some alternative implementations, geological parameters include permeability, porosity, hydrocarbon saturation, and formation pressure.
[0102] In some alternative implementations, the final recoverable reserves prediction model is built based on a neural network model, a random forest model, a Naive Bayes model, or a support vector machine model.
[0103] It is worth mentioning that all modules involved in this embodiment are logical modules. In practical applications, a logical unit can be a physical unit, a part of a physical unit, or a combination of multiple physical units. Furthermore, to highlight the innovative aspects of this application, this embodiment does not introduce units that are not closely related to solving the technical problems proposed in this application; however, this does not mean that other units are absent in this embodiment.
[0104] Example 5:
[0105] Another embodiment of this application relates to an electronic device, such as... Figure 6 As shown, it includes: at least one processor 601; and a memory 602 communicatively connected to the at least one processor 601; wherein the memory 602 stores instructions that can be executed by the at least one processor 601, the instructions being executed by the at least one processor 601 to enable the at least one processor 601 to execute the final recoverable reserves prediction method for fractured wells in the above embodiments.
[0106] The memory and processor are connected via a bus, which can include any number of interconnecting buses and bridges, connecting various circuits of one or more processors and memories. The bus can also connect various other circuits, such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and will not be described further herein. The bus interface provides an interface between the bus and the transceiver. The transceiver can be a single element or multiple elements, such as multiple receivers and transmitters, providing a unit for communicating with various other devices over a transmission medium. Data processed by the processor is transmitted over the wireless medium via an antenna, which further receives data and transmits it to the processor.
[0107] The processor manages the bus and general processing, and can also provide various functions, including timing, peripheral interfaces, voltage regulation, power management, and other control functions. The memory can be used to store data used by the processor during operation. The processor can include, but is not limited to, one or more processors or microprocessors. Each processor can be implemented as an Application Specific Integrated Circuit (ASIC), Digital Signal Processor (DSP), Digital Signal Processing Device (DSPD), Programmable Logic Device (PLD), Field Programmable Gate Array (FPGA), controller, microcontroller, microprocessor, or other electronic component to perform the methods described in the above embodiments.
[0108] Example 6:
[0109] Another embodiment of this application relates to a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the above-described method embodiments. That is, those skilled in the art will understand that all or part of the steps in the methods of the above embodiments can be implemented by a program instructing related hardware. The program is stored in a storage medium and includes several instructions to cause a device (which may be a microcontroller, chip, etc.) or a processor to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.
[0110] Computer-readable storage media may also store at least one computer-executable program / instruction, such as computer-readable instructions. Computer-readable storage media include, but are not limited to, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and / or cache memory. Computer-readable storage media may include, for example, read-only memory (ROM), hard disk, flash memory, etc. For example, a non-transitory computer-readable storage medium may be connected to a computing device such as a computer, and then, when the computing device executes the computer-readable instructions stored on the computer-readable storage medium, the various methods described above can be performed.
[0111] In addition, the computer device may include (but is not limited to) a data bus, an input / output (I / O) bus, a display, and input / output devices (e.g., keyboard, mouse, speakers, etc.).
[0112] The processor can communicate with external devices via the I / O bus through wired or wireless networks.
[0113] In one embodiment, the at least one computer-executable instruction may also be compiled into or comprise a software product / computer program product, wherein one or more computer-executable instructions are executed by a processor to perform the steps of the various functions and / or methods in the embodiments described herein.
[0114] Those skilled in the art will understand that the above embodiments are specific embodiments for implementing this application, and in practical applications, various changes can be made to them in form and detail without departing from the spirit and scope of this application.
[0115] In the embodiments provided in this disclosure, it should be understood that the disclosed apparatus and methods can also be implemented in other ways. The apparatus embodiments described above are merely illustrative; for example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.
[0116] It should be noted that, in this disclosure, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element limited by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.
[0117] While the embodiments disclosed herein are as described above, the foregoing content is merely for the purpose of facilitating understanding of this disclosure and is not intended to limit this disclosure. Any person skilled in the art to which this disclosure pertains may make any modifications and changes in form and detail of the implementation without departing from the spirit and scope of this disclosure; however, the scope of patent protection of this disclosure shall still be determined by the scope defined in the appended claims.
Claims
1. A method for predicting the final recoverable reserves of a fractured well, characterized in that, include: A fully integrated geological reservoir model of the target block is constructed, which couples a fracture stress sensitivity model and a long-term conductivity model. The fully integrated model was used to simulate the target block under different fracturing operation parameters to obtain the final recoverable reserves of the target block under different fracturing operation parameters. Using the geological parameters, well network parameters, fracture parameters, and fracturing operation parameters of the target block as input data, and the final recoverable reserves corresponding to the fracturing operation parameters as the expected output data, the final recoverable reserves prediction model is trained to obtain the trained final recoverable reserves prediction model. The trained final recoverable reserves prediction model is used to predict the final recoverable reserves of the target well under different fracturing scales.
2. The method according to claim 1, characterized in that, The method further includes: The target of fracturing design is to achieve the final recoverable reserves of the target well reaching a preset limit value, or to maximize the final recoverable reserves per unit input. Based on the trained final recoverable reserves prediction model, an optimized combination of fracturing construction parameters is determined.
3. The method according to claim 1, characterized in that, The constructed geological reservoir fully integrated model of the target block includes: Based on the seismic data, well logging data, well engineering data, geostress data, geological data, and fracturing operation data of the target block, an integrated preliminary model of the target block is established; Artificial fracture models of the target block were obtained by simulating artificial fractures based on geological models and different fracturing construction parameters. Based on the integrated preliminary model and the artificial fracture model, the superposition effect of induced stress caused by hydraulic fracturing and its influence on permeability are coupled to obtain an integrated updated model that couples the fracture stress-sensitive model. Based on the integrated update model, the long-term conductivity model is coupled to obtain a fully integrated model that couples the crack stress sensitivity model and the long-term conductivity model.
4. The method according to claim 3, characterized in that, The long-term conductivity model is generated by simulating the long-term conductivity of the main fracture and branch fractures under different closure stresses and sand concentrations using a physical model.
5. The method according to any one of claims 1 to 5, characterized in that, The well network parameters include horizontal section length, well spacing, cluster spacing, fracture length, and conductivity.
6. The method according to any one of claims 1 to 5, characterized in that, The geological parameters include permeability, porosity, hydrocarbon saturation, and formation pressure.
7. The method according to any one of claims 1 to 5, characterized in that, The final recoverable reserves prediction model is constructed based on a neural network model, a random forest model, a Naive Bayes model, or a support vector machine model.
8. A device for predicting the final recoverable reserves of a fractured well, characterized in that, include: A construction module is used to construct a fully integrated geological reservoir model of the target block, wherein the fully integrated model is coupled with a fracture stress sensitivity model and a long-term conductivity model; The generation module is used to simulate the target block with different fracturing operation parameters using the fully integrated model, and to obtain the final recoverable reserves of the target block under different fracturing operation parameters. The training module is used to train the final recoverable reserves prediction model with the geological parameters, well network parameters, fracture parameters and fracturing construction parameters of the target block as input data and the final recoverable reserves corresponding to the fracturing construction parameters as the expected output data, so as to obtain the trained final recoverable reserves prediction model. The prediction module is used to predict the final recoverable reserves of the target well under different fracturing scales using the trained final recoverable reserves prediction model.
9. An electronic device, characterized in that, include: At least one processor; as well as, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the final recoverable reserves prediction method for fractured wells as described in any one of claims 1 to 7.
10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the method for predicting the final recoverable reserves of fractured wells as described in any one of claims 1 to 7.