Method and system for tight gas reservoir water invasion early warning based on ant tracking

Abstract

The application discloses a method and system for tight gas reservoir water invasion early warning based on ant tracking. The method comprises the following steps: constructing a target connected body percolation capacity model; determining a dominant percolation channel from a target region to a target well in the target connected body percolation capacity model through an ant bionic connection algorithm; and determining a water invasion early warning index of the dominant percolation channel from the target region to the target well. The application can more efficiently and simply find the dominant percolation channel of the tight gas reservoir, provide more accurate water invasion early warning information, and thus improve the efficiency and success rate of gas reservoir development.

Description

Technical Field

[0001] This application relates to the fields of gas reservoir development and water intrusion early warning technology, specifically to a method and system for water intrusion early warning of tight gas reservoirs based on ant tracking. Background Technology

[0002] Tight gas reservoirs are a type of deep-buried gas reservoir characterized by ultra-low permeability and high adsorption. They are characterized by poor reservoir properties, large burial depth, high gas adsorption capacity, and complex formation mechanisms. In actual exploration, the complexity and difficulty in understanding the formation mechanisms of tight gas reservoirs lead to significant exploration challenges. Among these challenges, dynamic prediction of tight gas reservoirs and early warning of water breakthrough in gas wells are key difficulties in natural gas exploration and development. Traditional methods for assessing the degree of water invasion and water production type in gas reservoirs are based on the daily water production at the wellhead. However, this method has weak quantitative significance and significant lag, making it impossible to accurately determine the water invasion status and water production classification in advance. Summary of the Invention

[0003] The purpose of this application is to provide a method and system for early warning of water intrusion in tight gas reservoirs based on ant tracking, in order to solve the problem of low accuracy in dynamic prediction and early warning of tight gas reservoirs in the prior art.

[0004] To achieve the above objectives, the first aspect of this application provides a method for early warning of water intrusion in tight gas reservoirs based on ant tracking, the method comprising:

[0005] Construct a model of the seepage capacity of the target connected body;

[0006] The dominant seepage channels from the target region to the target well in the seepage capacity model of the target connected body are determined by the ant-inspired biomimetic connectivity algorithm.

[0007] Determine the water intrusion early warning index of the dominant seepage channel from the target area to the target well.

[0008] In this embodiment of the application, constructing the seepage capacity model of the target connected body includes:

[0009] Obtain the reservoir matrix model, fracture network equivalent model, fault equivalent model, and initial threshold;

[0010] An initial interconnected body seepage capacity model is established based on the reservoir matrix model, fracture network equivalent model, fault equivalent model, and initial threshold.

[0011] Classify and label the connected regions in the initial connected volume seepage capacity model;

[0012] Determine the objective function for the target region based on constraints;

[0013] Based on a gradient-free optimization algorithm, the initial connected body seepage capacity model is updated with a threshold according to the objective function to obtain the target connected body seepage capacity model.

[0014] In this embodiment of the application, the classification and labeling of connected regions in the initial connected flow capacity model includes:

[0015] Determine whether the density of the region to be classified is greater than the preset density;

[0016] If the density of the region to be classified is greater than the preset density, the region to be classified is determined as a connected region.

[0017] If the density of the region to be classified is not greater than the preset density, the region to be classified is determined as a disconnected region.

[0018] In this embodiment of the application, the constraints include well connectivity, water breakthrough in single-well production, and perforation section information. The objective function for determining the target area based on the constraints includes:

[0019] Based on the perforation section information, determine the well test connectivity between any two wells in the target area and the water production status of any single well.

[0020] Candidate function values ​​are determined based on the well test connectivity between any two wells and the water breakthrough situation of any single well.

[0021] The candidate function with the smallest candidate function value is determined as the objective function.

[0022] In this embodiment of the application, determining the well test connectivity between any two wells in the target area and the water breakthrough status of any single well based on the perforation section information includes:

[0023] Based on the perforation section information, determine whether the well test connectivity between any two wells in the target area meets the first preset constraint condition, and whether the water production of any single well meets the second preset constraint condition.

[0024] Candidate function values ​​are determined based on the well test connectivity between any two wells and the water breakthrough status of any single well, including:

[0025] The sum of the number of well pairs whose well connectivity in the target area does not meet the first preset constraint and the number of single wells whose water production does not meet the second preset constraint is determined as the candidate function value.

[0026] In this embodiment of the application, determining whether the well connectivity between any two wells in the target area meets the first preset constraint condition, and whether the water breakthrough of any single well meets the second preset constraint condition, based on the perforation section information, includes:

[0027] Determine whether the perforated sections of any two wells are connected;

[0028] If the perforated sections of any two wells are connected, it is determined that the well test connectivity of any two wells satisfies the first preset constraint condition.

[0029] Determine whether water has been encountered in the perforated section of any single well;

[0030] If water is encountered in the perforated section of any single well, the production water encounter situation of any single well is determined to meet the second preset constraint condition.

[0031] In this embodiment of the application, the dominant seepage channels from the target region to the target well in the target connected body seepage capacity model are determined by the ant-inspired bionic connectivity algorithm, including:

[0032] The effective connected components of the target connected component seepage capacity model are simplified into attribute meshes.

[0033] The biomimetic ant moves through the attribute grid by randomly walking;

[0034] The probability of the bionic ant choosing each path is determined by accumulating probability.

[0035] The path with the highest probability is selected as the dominant seepage channel from the target area to the target well.

[0036] In this embodiment, the probability of each path satisfies formulas (1) and (2):

[0037]

[0038]

[0039] Where i and j are arbitrary path nodes, P ij Let P be the probability that the bionic ant chooses path ij, and let P be the cumulative probability that the bionic ant chooses path ij. ij | represents the distance between the i-th and j-th nodes, F ij Let η be the density attribute of the connected component between path node i and path node j. ij The concentration of pheromones in path ij.

[0040] In this embodiment of the application, the water intrusion early warning index satisfies formula (3):

[0041]

[0042] Where Y is the flood intrusion warning index; A is the water volume multiple; k is an arbitrary grid; F k represents the attribute value of the corresponding grid; N is the total number of grids in the path; norm(·) is the normalization function.

[0043] The second aspect of this application provides a system for early warning of water intrusion in tight gas reservoirs based on ant tracking, comprising:

[0044] The memory is configured to store instructions; and

[0045] The processor is configured to retrieve instructions from memory and, when executing the instructions, to implement the aforementioned method for early warning of water intrusion in tight gas reservoirs based on ant tracking.

[0046] This application first constructs a target interconnected flow capacity model, then uses an ant-inspired bionic connectivity algorithm to determine the dominant flow channels from the target area to the target well, and finally determines the water intrusion early warning index of the dominant flow channels from the target area to the target well. This approach can more efficiently and conveniently find the dominant flow channels in tight gas reservoirs, providing more accurate water intrusion early warning information, thereby improving the efficiency and success rate of gas reservoir development.

[0047] Other features and advantages of the embodiments of this application will be described in detail in the following detailed description section. Attached Figure Description

[0048] The accompanying drawings are provided to further illustrate the embodiments of this application and form part of the specification. They are used together with the following detailed description to explain the embodiments of this application, but do not constitute a limitation on the embodiments of this application. In the drawings:

[0049] Figure 1 The flowchart illustrates a method for early warning of water intrusion in tight gas reservoirs based on ant tracking, according to an embodiment of this application.

[0050] Figure 2 The flowchart illustrates a method for early warning of water intrusion in tight gas reservoirs based on ant tracking according to a specific embodiment of this application.

[0051] Figure 3 A schematic diagram illustrating the water intrusion path result of the advantageous seepage channel according to a specific embodiment of this application is shown.

[0052] Figure 4 The diagram illustrates the structure of a system for early warning of water intrusion in tight gas reservoirs based on ant tracking, according to an embodiment of this application. Detailed Implementation

[0053] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only for illustration and explanation of the embodiments of this application and are not intended to limit the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0054] It should be noted that if the embodiments of this application involve directional indicators (such as up, down, left, right, front, back, etc.), the directional indicators are only used to explain the relative positional relationship and movement of the components in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indicators will also change accordingly.

[0055] Furthermore, if the embodiments of this application involve descriptions such as "first" or "second," these descriptions are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, features defined with "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the technical solutions of various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. If the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed in this application.

[0056] Figure 1 A flowchart illustrating a method for early warning of water intrusion in tight gas reservoirs based on ant tracking, according to an embodiment of this application, is shown schematically. Figure 1 As shown in the embodiments of this application, a method for early warning of water intrusion in tight gas reservoirs based on ant tracking is provided. The method may include the following steps:

[0057] Step 101: Construct a seepage capacity model for the target connected body;

[0058] Step 102: Determine the dominant seepage channels from the target region to the target well in the target connected body seepage capacity model using the ant-inspired bionic connectivity algorithm;

[0059] Step 103: Determine the water intrusion early warning index of the dominant seepage channel from the target area to the target well.

[0060] In this embodiment, dynamic prediction of tight gas reservoirs and early warning of water breakthrough in gas wells are key challenges in natural gas exploration and development. Traditional methods for assessing the degree of water intrusion and water production type in gas reservoirs rely on daily water production at the wellhead. However, this method has weak quantitative significance and significant time lag, making it unable to accurately predict the water intrusion status and water production classification in advance. Therefore, this embodiment uses a biomimetic algorithm to construct a permeability model of a target connected body and simulates biological behavior to learn the spatial behavioral trajectory of high-permeability areas. This can provide guidance for providing a water intrusion early warning index, thereby offering more accurate water intrusion early warning information.

[0061] In this embodiment, the spatial distribution of tight gas reservoir strata is complex, and the connectivity capacity model is influenced by the reservoir matrix, fracture network, and faults. Typically, constructing a three-dimensional connectivity model relies on the prior knowledge of geological experts, a method susceptible to subjective human factors and difficult to accurately characterize subsequent dominant seepage channels. Therefore, this embodiment constructs a target connectivity seepage capacity model, which can reasonably couple heterogeneous attribute parameters. The target connectivity seepage capacity model refers to a connectivity seepage capacity model constructed based on a reservoir matrix model, a fracture network equivalent model, and a fault equivalent model. In one example, the target connectivity seepage capacity model can automatically obtain the thresholds of the reservoir matrix model, the fracture network equivalent model, and the fault equivalent model using a gradient-free optimization algorithm. By constructing the target connectivity seepage capacity model, it is less reliant on the prior knowledge of experts, thus accurately characterizing geological connectivity information with complex structures to identify dominant seepage channels.

[0062] In this embodiment, the biomimetic algorithm is a random search technique that simulates the process of natural evolution or biological cluster behavior. It features independence from gradient information, high stability, autonomous decision-making, and adaptability. Biomimetic algorithms are suitable for solving large-scale complex optimization problems and can effectively avoid the "curse of dimensionality" and "local optimum traps," thereby obtaining a globally optimized solution. Representative biomimetic algorithms include genetic algorithms, artificial neural networks, ant colony biomimetic algorithms, and fish swarm biomimetic algorithms. Among them, the ant colony biomimetic algorithm is an optimal path tracing algorithm based on biomimetic ants searching for the globally optimal solution, simulating the collective intelligence of ants foraging. The ant biomimetic connectivity algorithm in this embodiment is used to determine the dominant seepage channel from the target area to the target well. The target area and the target well are the starting and ending points of the dominant seepage channel to be found, which are inputs received by the processor. The dominant seepage channel is the optimal seepage channel from the target area to the target well. The dominant seepage channel is influenced by the combined effects of fault zones and high-permeability bodies, exhibiting multi-attribute characteristics. By employing an ant-inspired biomimetic connectivity algorithm, and from a biomimetic perspective, imbuing the ant system with geological connotations, a matrix for analyzing dominant seepage channels based on the ant colony biomimetic algorithm is established. Through the random movement and repeated "foraging" of biomimetic ants, the dynamic changes in the seepage capacity model of the target connected body are analyzed. Finally, based on the simulation results, evaluation criteria are formulated, and a quantitative evaluation of the dominant seepage channels is given, that is, based on the dominant seepage channels, the water intrusion warning index of the channel is determined.

[0063] This application embodiment first constructs a target connected body seepage capacity model, then uses the ant biomimetic connectivity algorithm to determine the dominant seepage channel from the target area to the target well, and finally determines the water invasion early warning index of the dominant seepage channel from the target area to the target well. This can more efficiently and conveniently find the dominant seepage channel of tight gas reservoirs, so as to provide more accurate water invasion early warning information, thereby improving the efficiency and success rate of gas reservoir development.

[0064] In this embodiment of the application, step 101, constructing the seepage capacity model of the target connected body, may include:

[0065] Obtain the reservoir matrix model, fracture network equivalent model, fault equivalent model, and initial threshold;

[0066] An initial interconnected body seepage capacity model is established based on the reservoir matrix model, fracture network equivalent model, fault equivalent model, and initial threshold.

[0067] Classify and label the connected regions in the initial connected volume seepage capacity model;

[0068] Determine the objective function for the target region based on constraints;

[0069] Based on a gradient-free optimization algorithm, the initial connected body seepage capacity model is updated with a threshold according to the objective function to obtain the target connected body seepage capacity model.

[0070] In this embodiment, the reservoir matrix model is a geological model that quantitatively expresses the distribution and changes of various reservoir geological features in three-dimensional space, based on comprehensive data from drilling, core samples, seismic data, external logging, well testing, and development dynamics, guided by structural geology, reservoir sedimentology, petroleum geology, and geostatistics. The described reservoir features include the aggregate morphology, scale, continuity, connectivity, internal structure, porosity, distribution of reservoir physical parameters, and interlayer distribution. The fracture network equivalent model is a model obtained by using modeling tools to perform three-dimensional modeling of underground reservoir fractures based on seismic and drilling data. A geological fault is a structure in which the Earth's crust fractures under stress, resulting in significant relative displacement of rock blocks on both sides of the fracture surface; the fault equivalent model is a model constructed based on geological faults. In this embodiment, the independent reservoir matrix model, fracture network model, and fault equivalent model are coupled into a target interconnected flow capacity model based on constraints and a gradient-free optimization algorithm, which can more accurately characterize geological connectivity information with complex structures.

[0071] Specifically, to construct the target connected body seepage model, the first step is to initialize the connected body seepage capacity model, obtain the reservoir matrix model, fracture network equivalent model, fault equivalent model, and initial thresholds, thus establishing the initial connected body seepage capacity model. The thresholds in the initial connected body seepage capacity model are the initial thresholds of the reservoir matrix model, fracture network equivalent model, and fault equivalent model. In one example, the initial thresholds of the reservoir matrix model, fracture network equivalent model, and fault equivalent model can be set as α, β, and γ, respectively. The established initial connected body seepage capacity model can satisfy formula (4):

[0072] The interconnected flow model = α × reservoir matrix model + β × fracture network equivalent model + γ × fault equivalent model; (4).

[0073] After establishing the initial connected flow capacity model, the processor can classify and label the connected regions of the initial connected flow capacity model, and then determine the objective function of the target region based on the constraints. In one example, the processor can use the connectivity of the wells in the connected regions, the water breakthrough status of single wells, and the perforation section information as the objective function for optimizing the constraints. The objective function is the function with the smallest number of non-compliance conditions, derived from multiple candidate functions. The value of a candidate function is the number of non-compliance conditions. The smaller the value of a candidate function, the better its corresponding threshold. Therefore, the processor needs to select the candidate function with the smallest value that meets the conditions as the objective function. Then, based on a gradient-free optimization algorithm, the processor updates the threshold of the initial connected flow capacity model according to the threshold corresponding to the objective function to obtain the target connected flow capacity model. This target connected flow capacity model is the optimal model.

[0074] This application embodiment takes into account factors such as well-to-well connectivity and water-bearing wells, and uses a gradient-free optimization algorithm to automatically obtain the thresholds of reservoir matrix model, fracture equivalent model and fault equivalent model. It does not rely too much on the prior knowledge of experts, thereby accurately characterizing geological connectivity information with complex structures in order to find advantageous seepage channels.

[0075] In this embodiment of the application, classifying and labeling the connected regions of the initial connected flow capacity model may include:

[0076] Determine whether the density of the region to be classified is greater than the preset density;

[0077] If the density of the region to be classified is greater than the preset density, the region to be classified is determined as a connected region.

[0078] If the density of the region to be classified is not greater than the preset density, the region to be classified is determined as a disconnected region.

[0079] Specifically, the initial connected flow capacity model is classified and labeled with connected regions, that is, the initial connected flow capacity model is divided into connected regions and non-connected regions. The preset density refers to the density value that distinguishes between connected and non-connected regions. The region to be classified is the region that needs to be judged and classified. If the density of the region to be classified is greater than the preset density, it indicates that the density of the region to be classified is high, and it can be identified as a connected region. If the density of the region to be classified is not greater than, i.e., less than or equal to, the preset density, it indicates that the density of the region to be classified is low, and it can be identified as a non-connected region. This classification method allows for a simple and efficient classification and labeling of connected regions in the initial connected flow capacity model.

[0080] In this embodiment of the application, the constraints may include well connectivity, water breakthrough status of single well production, and perforation section information. The objective function for determining the target area based on the constraints may include:

[0081] Based on the perforation section information, determine the well test connectivity between any two wells in the target area and the water production status of any single well.

[0082] Candidate function values ​​are determined based on the well test connectivity between any two wells and the water breakthrough situation of any single well.

[0083] The candidate function with the smallest candidate function value is determined as the objective function.

[0084] The constraints in this application embodiment may include well connectivity, single-well water breakthrough, and perforation section information. Well connectivity refers to whether any two wells are connected, single-well water breakthrough refers to whether a single well can produce water, and perforation is the process of using specialized perforation tools to penetrate the casing and cement sheath of the oil and gas reservoir according to the development plan requirements, forming a connecting channel between the wellbore and the oil and gas reservoir. Each well has a perforation section. The perforation section information can be used to determine the well connectivity between any two wells and the single-well water breakthrough. Based on the well connectivity between any two wells and the single-well water breakthrough, the number of constraints that are not met can be determined, thereby obtaining the corresponding candidate function values. Finally, the processor selects the smallest candidate function from multiple candidate function values ​​as the objective function to update the threshold of the initial interconnected flow capacity model.

[0085] In this embodiment of the application, determining the well test connectivity between any two wells in the target area and the water breakthrough status of any single well based on the perforation section information may include:

[0086] Based on the perforation section information, determine whether the well test connectivity between any two wells in the target area meets the first preset constraint condition, and whether the water production of any single well meets the second preset constraint condition.

[0087] Determining candidate function values ​​based on the well test connectivity between any two wells and the water breakthrough status of any single well can include:

[0088] The sum of the number of well pairs whose well connectivity in the target area does not meet the first preset constraint and the number of single wells whose water production does not meet the second preset constraint is determined as the candidate function value.

[0089] Specifically, the constraints can include a first constraint and a second constraint. The first constraint is for determining the connectivity of the well test, and the second constraint is for determining the water breakthrough status of a single well. The candidate function value is the number of wells that do not meet the constraints. Adding the number of well pairs whose connectivity does not meet the first constraint and the number of single wells whose water breakthrough status does not meet the second constraint yields the candidate function value, i.e., candidate function value = N1 + N2, where N1 is the number of well pairs whose connectivity does not meet the first constraint and N2 is the number of single wells whose water breakthrough status does not meet the second constraint.

[0090] In this embodiment of the application, determining whether the well connectivity between any two wells in the target area meets the first preset constraint condition, and whether the water breakthrough of any single well meets the second preset constraint condition, based on the perforation section information, may include:

[0091] Determine whether the perforated sections of any two wells are connected;

[0092] If the perforated sections of any two wells are connected, it is determined that the well test connectivity of any two wells satisfies the first preset constraint condition.

[0093] Determine whether water has been encountered in the perforated section of any single well;

[0094] If water is encountered in the perforated section of any single well, the production water encounter situation of any single well is determined to meet the second preset constraint condition.

[0095] Specifically, the processor can determine whether the well test connectivity of any two wells meets the first constraint condition based on whether their perforated sections are connected. If the perforated sections of any two wells are connected, the processor determines that the well test connectivity of any two wells meets the first preset constraint condition. The processor can also determine whether the production water breakthrough of any single well meets the second constraint condition based on whether water is encountered in the perforated section of any single well. If water is encountered in the perforated section of any single well, the processor determines that the production water breakthrough of any single well meets the second preset constraint condition. Determining the constraint condition through the perforated section is a simpler method.

[0096] In this embodiment of the application, step 102, determining the dominant seepage channel from the target region to the target well in the target connected body seepage capacity model using the ant-inspired bionic connectivity algorithm, may include:

[0097] The effective connected components of the target connected component seepage capacity model are simplified into attribute meshes.

[0098] The biomimetic ant moves through the attribute grid by randomly walking;

[0099] The probability of the bionic ant choosing each path is determined by accumulating probability.

[0100] The path with the highest probability is selected as the dominant seepage channel from the target area to the target well.

[0101] In this embodiment, after determining the seepage capacity model of the target connected body, the dominant seepage channels from the target area to the target well can be determined using an ant-inspired algorithm. The path from the target area to the target well can include multiple paths. Based on the target connected body seepage model, the effective connected body is simplified into an attribute grid, providing effective "foraging" paths for the bionic ants. Each path has a corresponding pheromone concentration, and the reciprocal of the grid attribute density is used as the distance between adjacent grids to encourage the bionic ants to take high-permeability paths. The bionic ants then move forward in a random walk manner within the attribute grid, and the selection of the next node is based on probability, considering factors such as the connected body density attribute and the distance between attribute grid nodes. The probability P of the bionic ant choosing each path can then be determined using a cumulative probability method.

[0102] In this embodiment, the probability of each path satisfies formulas (1) and (2):

[0103]

[0104]

[0105] Where i and j are arbitrary path nodes, P ij Let P be the probability that the bionic ant chooses path ij, and let P be the cumulative probability that the bionic ant chooses path ij. ij | represents the distance between the i-th and j-th nodes, F ij Let η be the density attribute of the connected component between path node i and path node j. ij The concentration of pheromones in path ij.

[0106] After calculating the probability P of each path, the path with the highest probability P is selected as the dominant seepage channel from the target area to the target well. To avoid slow algorithm convergence, the paths traversed by a single biomimetic ant during the entire "foraging" process are added to a taboo list and are not repeated. This improves the computational efficiency of the ant-inspired algorithm.

[0107] In this embodiment, the processor can add pheromones to the paths traversed by bionic ants that successfully reach the water, thus updating the pheromone levels. No pheromones are added to the paths traversed by bionic ants that fail to reach the water. Furthermore, during each pheromone update, the pheromone from the previous stage is evaporated with probability μ, and this evaporation formula satisfies formula (5):

[0108] η l+1 =(1-μ)η l (5)

[0109] Where, η l+1 For the latest pheromone concentration, η l The concentration of pheromones in the previous stage is given by μ, which represents the set probability.

[0110] In this embodiment of the application, the water intrusion early warning index can satisfy formula (3):

[0111]

[0112] Where Y is the flood intrusion warning index; A is the water volume multiple; k is an arbitrary grid; F k represents the attribute value of the corresponding grid; N is the total number of grids in the path; norm(·) is the normalization function.

[0113] Specifically, based on the grid attributes of the dominant seepage channels corresponding to each well area, a water intrusion early warning index can be constructed for the development well area, thereby reducing the risk of water breakthrough in the well area. By constructing a target connected body seepage capacity model and determining the dominant seepage channels using an ant-inspired bionic connectivity algorithm, the determination of the water intrusion early warning index can be made more accurate.

[0114] Figure 2 The flowchart illustrating a method for early warning of water intrusion in tight gas reservoirs based on ant tracking, according to a specific embodiment of this application, is shown schematically. Figure 2 As shown in a specific embodiment of this application, a method for early warning of water intrusion in tight gas reservoirs based on ant tracking is provided. The method may include the following steps:

[0115] Step 201: Obtain the reservoir matrix model, fracture network equivalent model, and fault equivalent model;

[0116] Step 202: Obtain the constraint conditions of the perforation section (i.e., perforation section information), the water-bearing wells (the water-bearing status of a single well), and the well test connectivity pairs (i.e., the well test connectivity between any two wells);

[0117] Step 203: Establish the reservoir matrix model connectivity, fracture network equivalent model connectivity, and fault equivalent model connectivity through a gradient-free optimization algorithm to obtain the connectivity permeability model (i.e., the target connectivity permeability model).

[0118] Step 204: Determine the dominant seepage channels using the ant-inspired bionic connectivity algorithm;

[0119] Step 205: Determine the water intrusion early warning index of the dominant seepage channels.

[0120] This application's embodiments first use reservoir matrix models, fracture network equivalent models, and fault equivalent models, employing tracer analysis of well connectivity, single-well water breakthrough, and perforation intervals as optimization constraints. A gradient-free optimization algorithm automatically determines the threshold parameters of the target connected body's seepage capacity model, thereby obtaining the seepage capacity models of the connected body and the target connected body based on the three models. Then, using an ant-inspired biomimetic connectivity algorithm, from a biomimetic perspective, the geological connotations of the ant system are endowed to determine the dominant seepage channels from the target area to the target well, completing the dynamic change analysis of the target connected body's seepage model. Finally, the water intrusion early warning index of the dominant seepage channels from the target area to the target well is determined, providing a quantitative evaluation. This allows for a more efficient and convenient search for dominant seepage channels in tight gas reservoirs, providing more accurate water intrusion early warning information, thereby improving the efficiency and success rate of gas reservoir development.

[0121] Figure 3 A schematic diagram illustrating the advantageous seepage channel water intrusion path result according to a specific embodiment of this application is shown. Figure 3 As shown, a water intrusion early warning index analysis is conducted using a selected tight gas reservoir working area as an example. First, the seepage capacity model of the target connected body is obtained by integrating the reservoir matrix model, fracture network equivalent model, and fault equivalent model according to steps 201 to 203. Then, the ant-inspired bionic connectivity algorithm is constructed according to step 204 to establish the dominant seepage channels for the designated wells in the gas reservoir working area. Finally, the water intrusion early warning index analysis of the dominant seepage channels is performed on the development wells in the gas reservoir working area according to step 205, i.e., the above formula (3), to obtain the water intrusion early warning index of the gas reservoir working area. Figure 3 As shown, the above method can efficiently and accurately locate the dominant seepage channels named B9 and C7, thereby obtaining the water intrusion warning index from the target area to B9 and C7. Table 1 schematically illustrates an embodiment according to this application. Figure 3 The water intrusion warning index for the dominant seepage channels in wells B9 and C7 is shown in Table 1.

[0122] Table 1

[0123] well name Path average Number of path grids Average / Grid Early warning index B9 0.95 69 0.014 0.81 C7 0.93 106 0.009 0.52

[0124] Figure 4 This diagram schematically illustrates a structural block diagram of a tight gas reservoir water intrusion early warning system based on ant tracking, according to an embodiment of this application. Figure 4 As shown in the embodiments of this application, a system for early warning of water intrusion in tight gas reservoirs based on ant tracking is also provided, including:

[0125] Memory 410 is configured to store instructions; and

[0126] The processor 420 is configured to retrieve instructions from the memory 410 and, when executing the instructions, to implement the aforementioned method for early warning of water intrusion into tight gas reservoirs based on ant tracking.

[0127] In one embodiment of this application, the processor 420 may be configured to:

[0128] Construct a model of the seepage capacity of the target connected body;

[0129] The dominant seepage channels from the target region to the target well in the seepage capacity model of the target connected body are determined by the ant-inspired biomimetic connectivity algorithm.

[0130] Determine the water intrusion early warning index of the dominant seepage channel from the target area to the target well.

[0131] Furthermore, the processor 420 can also be configured as follows:

[0132] The construction of the target connected body seepage capacity model includes:

[0133] Obtain the reservoir matrix model, fracture network equivalent model, fault equivalent model, and initial threshold;

[0134] An initial interconnected body seepage capacity model is established based on the reservoir matrix model, fracture network equivalent model, fault equivalent model, and initial threshold.

[0135] Classify and label the connected regions in the initial connected volume seepage capacity model;

[0136] Determine the objective function for the target region based on constraints;

[0137] Based on a gradient-free optimization algorithm, the initial connected body seepage capacity model is updated with a threshold according to the objective function to obtain the target connected body seepage capacity model.

[0138] Furthermore, the processor 420 can also be configured as follows:

[0139] The classification and labeling of connected regions in the initial connected flow capacity model includes:

[0140] Determine whether the density of the region to be classified is greater than the preset density;

[0141] If the density of the region to be classified is greater than the preset density, the region to be classified is determined as a connected region.

[0142] If the density of the region to be classified is not greater than the preset density, the region to be classified is determined as a disconnected region.

[0143] Furthermore, the processor 420 can also be configured as follows:

[0144] The objective function for determining the target region based on constraints includes:

[0145] Based on the perforation section information, determine the well test connectivity between any two wells in the target area and the water production status of any single well.

[0146] Candidate function values ​​are determined based on the well test connectivity between any two wells and the water breakthrough situation of any single well.

[0147] The candidate function with the smallest candidate function value is determined as the objective function.

[0148] Furthermore, the processor 420 can also be configured as follows:

[0149] Based on perforation information, the following can be determined: Well test connectivity between any two wells in the target area and the water breakthrough status of any single well.

[0150] Based on the perforation section information, determine whether the well test connectivity between any two wells in the target area meets the first preset constraint condition, and whether the water production of any single well meets the second preset constraint condition.

[0151] Candidate function values ​​are determined based on the well test connectivity between any two wells and the water breakthrough status of any single well, including:

[0152] The sum of the number of well pairs whose well connectivity in the target area does not meet the first preset constraint and the number of single wells whose water production does not meet the second preset constraint is determined as the candidate function value.

[0153] Furthermore, the processor 420 can also be configured as follows:

[0154] Based on the perforation section information, determine whether the well test connectivity between any two wells in the target area meets the first preset constraint condition, and whether the water breakthrough of any single well meets the second preset constraint condition, including:

[0155] Determine whether the perforated sections of any two wells are connected;

[0156] If the perforated sections of any two wells are connected, it is determined that the well test connectivity of any two wells satisfies the first preset constraint condition.

[0157] Determine whether water has been encountered in the perforated section of any single well;

[0158] If water is encountered in the perforated section of any single well, the production water encounter situation of any single well is determined to meet the second preset constraint condition.

[0159] Furthermore, the processor 420 can also be configured as follows:

[0160] The dominant seepage pathways from the target region to the target well in the target connected body seepage capacity model, determined using the ant-inspired biomimetic connectivity algorithm, include:

[0161] The effective connected components of the target connected component seepage capacity model are simplified into attribute meshes.

[0162] The biomimetic ant moves through the attribute grid by randomly walking;

[0163] The probability of the bionic ant choosing each path is determined by accumulating probability.

[0164] The path with the highest probability is selected as the dominant seepage channel from the target area to the target well.

[0165] In this embodiment, the probability of each path satisfies formulas (1) and (2):

[0166]

[0167]

[0168] Where i and k are arbitrary path nodes, P ik Let P be the probability that the bionic ant chooses path ik, and let P be the cumulative probability that the bionic ant chooses path ij. ij | represents the distance between the i-th and j-th nodes, F ij Let η be the density attribute of the connected component between path node i and path node j. ij The concentration of pheromones in path ij.

[0169] In this embodiment of the application, the water intrusion early warning index satisfies formula (3):

[0170]

[0171] Where Y is the flood intrusion warning index; A is the water volume multiple; k is an arbitrary grid; F k The attribute value is the corresponding grid; N is the total number of grids in the path; norm() is the normalization function.

[0172] This application embodiment first constructs a target connected body seepage capacity model, then uses the ant biomimetic connectivity algorithm to determine the dominant seepage channel from the target area to the target well, and finally determines the water invasion early warning index of the dominant seepage channel from the target area to the target well. This can more efficiently and conveniently find the dominant seepage channel of tight gas reservoirs, so as to provide more accurate water invasion early warning information, thereby improving the efficiency and success rate of gas reservoir development.

[0173] This application also provides a machine-readable storage medium storing instructions that cause a machine to execute the above-described method for early warning of water intrusion in tight gas reservoirs based on ant tracking.

[0174] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0175] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0176] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0177] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0178] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0179] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, like read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0180] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0181] It should also be noted that 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 process, method, article, or apparatus. Unless otherwise specified, an element defined 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.

[0182] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for early warning of water intrusion in tight gas reservoirs based on ant tracking, characterized in that, The method includes: Construct a model of the seepage capacity of the target connected body; The dominant seepage channels from the target region to the target well in the target connected body seepage capacity model are determined by the ant-inspired biomimetic connectivity algorithm. Determine the water intrusion early warning index of the dominant seepage channel from the target area to the target well; The construction of the target connected body seepage capacity model includes: Obtain the reservoir matrix model, fracture network equivalent model, fault equivalent model, and initial threshold; An initial interconnected flow capacity model is established based on the reservoir matrix model, the fracture network equivalent model, the fault equivalent model, and the initial threshold. The initial interconnected flow capacity model is used to classify and label the connected regions. Determine the objective function for the target region based on the constraints; Based on the gradient-free optimization algorithm, the initial connected body seepage capacity model is updated with a threshold according to the objective function to obtain the target connected body seepage capacity model. The method of determining the dominant seepage channels from the target region to the target well in the target connected body seepage capacity model using the ant-inspired bionic connectivity algorithm includes: The effective connected components of the target connected component seepage capacity model are simplified into attribute meshes; The biomimetic ant moves through the attribute grid by randomly wandering; The probability of the bionic ant choosing each path is determined by accumulating probabilities. The path with the highest probability is selected as the dominant seepage channel from the target area to the target well. Wherein, the water intrusion early warning index for determining the dominant seepage channel from the target area to the target well satisfies formula (3): ；（3） in, The aforementioned water intrusion early warning index; Multiples of the water volume; For any grid; For the corresponding grid's attribute value; This represents the total number of grid cells along the path. This is a standardized function.

2. The method according to claim 1, characterized in that, The process of classifying and labeling connected regions in the initial connected flow capacity model includes: Determine whether the density of the region to be classified is greater than the preset density; If the density of the region to be classified is greater than the preset density, the region to be classified is determined as a connected region. If the density of the region to be classified is not greater than the preset density, the region to be classified is determined as a disconnected region.

3. The method according to claim 1, characterized in that, The constraints include well connectivity, water breakthrough in single-well production, and perforation information. The objective function for determining the target region based on the constraints includes: Based on the perforation section information, determine the well test connectivity between any two wells in the target area and the water production status of any single well. Candidate function values ​​are determined based on the well test connectivity between any two wells and the water breakthrough in the production of any single well. The candidate function with the smallest candidate function value is determined as the target function.

4. The method according to claim 3, characterized in that, The step of determining the well test connectivity between any two wells in the target area and the water breakthrough status of any single well based on the perforation section information includes: Based on the perforation section information, determine whether the well test connectivity between any two wells in the target area meets the first preset constraint condition, and whether the water production of any single well meets the second preset constraint condition. The process of determining candidate function values ​​based on the well test connectivity between any two wells and the water breakthrough status of any single well includes: The sum of the number of well pairs whose well connectivity in the target area does not meet the first preset constraint and the number of single wells whose water production does not meet the second preset constraint is determined as the candidate function value.

5. The method according to claim 4, characterized in that, The step of determining whether the well connectivity between any two wells in the target area meets the first preset constraint condition and whether the water breakthrough of any single well meets the second preset constraint condition based on the perforation section information includes: Determine whether the perforated sections of any two wells are connected; If the perforated sections of any two wells are connected, it is determined that the well test connectivity of any two wells satisfies the first preset constraint condition. Determine whether water has been encountered in the perforated section of any single well; If water is encountered in the perforated section of any single well, it is determined that the water production situation of the single well meets the second preset constraint condition.

6. The method according to claim 1, characterized in that, The probability of each path satisfies formulas (1) and (2): ；（1） ；（2） in, , For any path node, Select a path for the bionic ant The probability, Select a path for the bionic ant The cumulative probability, For the first The and the first The distance between nodes Path node and path node path The density property of the connected components between them, For path The concentration of pheromones.

7. A system for early warning of water intrusion in tight gas reservoirs based on ant tracking, characterized in that, include: The memory is configured to store instructions; as well as A processor is configured to retrieve the instructions from the memory and, when executing the instructions, to implement the method for early warning of water intrusion in tight gas reservoirs based on ant tracking according to any one of claims 1 to 6.

Images