Method, device and storage medium for determining reservoir crossflow channel location

Abstract

The present application discloses a method, device and storage medium for determining the location of a crossflow channel in a reservoir, which belongs to the technical field of oil and gas extraction and carbon sequestration. The method includes: in the process of injecting a preset gas into a target reservoir, determining the presence of a crossflow channel in the target reservoir; gridding the area where the target reservoir is located to obtain multiple reservoir grid areas; obtaining the first reservoir gas flow rate and first reservoir pressure value corresponding to each reservoir grid area at the current time step, and the second reservoir gas flow rate and second reservoir pressure value corresponding to each reservoir grid area at the previous time step; based on the first reservoir gas flow rate, first reservoir pressure value, second reservoir gas flow rate and second reservoir pressure value, determining the target reservoir grid area covered by the crossflow channel in the multiple reservoir grid areas to obtain the location of the crossflow channel in the target reservoir. The present application can accurately determine the location of the crossflow channel in the target reservoir.

Description

Technical Field

[0001] The present application relates to the technical field of oil and gas extraction and carbon sequestration, and in particular to a method, device and storage medium for determining the position of a crossflow channel. Background Art

[0002] At present, due to the increasing emission of carbon dioxide, the greenhouse effect is becoming increasingly stronger, which has accelerated the pace of global warming. In order to achieve carbon emission reduction and alleviate the urgent situation of global warming, carbon dioxide can be isolated from the atmosphere and injected into oil and gas reservoirs, so that carbon dioxide can be stored while achieving oil and gas production. In addition to oil and gas reservoirs, carbon dioxide can also be stored in other types of geological reservoirs such as saline layers, coal seams, and shale. However, during the process of oil and gas production and carbon dioxide storage, the permeability and heterogeneity of the reservoir will cause carbon dioxide to flow preferentially in high permeability paths, thereby forming crossflow channels. The emergence of crossflow channels will affect the efficiency of oil and gas production and the storage efficiency of carbon dioxide, and may even cause carbon dioxide to flow to adjacent production wells or storage wells, interfering with normal injection and production operations.

[0003] Generally speaking, existing techniques typically determine the location of flow channels within a reservoir based on technicians' rough judgment of the reservoir interior and operational experience. However, this process relies solely on technicians' judgment and operational experience, lacking scientific data support, resulting in low accuracy in determining the location of flow channels. Summary of the Invention

[0004] The purpose of the embodiments of the present application is to provide a method, apparatus, device and storage medium for determining the location of a crossflow channel in a reservoir, so as to solve the problem of low accuracy in determining the location of a crossflow channel in the prior art.

[0005] In order to achieve the above-mentioned object, the first aspect of the present application provides a method for determining the location of a reservoir crossflow channel, the method comprising:

[0006] During the process of injecting a preset gas into the target reservoir, determining that a crossflow channel exists in the target reservoir;

[0007] Divide the area where the target reservoir is located into grids to obtain multiple reservoir grid areas;

[0008] Obtaining the first reservoir gas flow rate and the first reservoir pressure value corresponding to each reservoir grid area at the current time step, and the second reservoir gas flow rate and the second reservoir pressure value corresponding to each reservoir grid area at the previous time step;

[0009] According to the first reservoir gas flow rate, the first reservoir pressure value, the second reservoir gas flow rate and the second reservoir pressure value, the target reservoir grid area covered by the crossflow channel in the multiple reservoir grid areas is determined to obtain the position of the crossflow channel in the target reservoir.

[0010] In an embodiment of the present application, determining the presence of a crossflow channel in a target reservoir includes: obtaining reservoir characteristic parameters, gas injection parameters, and reservoir pressure parameters of the target reservoir, wherein the reservoir characteristic parameters include a permeability heterogeneity index and a reservoir gas production, the gas injection parameters include a total gas injection volume and a reservoir gas flow rate, and the reservoir pressure parameters include a reservoir pressure difference; determining the sum of the products of the permeability heterogeneity index, the total gas injection volume, the reservoir gas flow rate, the reservoir pressure difference, and the daily gas production, respectively, and corresponding preset weight coefficients to obtain a crossflow risk value for the target reservoir; and determining the presence of a crossflow channel in the target reservoir when the crossflow risk value is greater than a preset crossflow risk threshold.

[0011] In an embodiment of the present application, based on the first reservoir gas flow rate, the first reservoir pressure value, the second reservoir gas flow rate and the second reservoir pressure value, the target reservoir grid area covered by the crossflow channel in multiple reservoir grid areas is determined to obtain the position of the crossflow channel in the target reservoir, including: determining a first difference between the first reservoir gas flow rate and the second reservoir gas flow rate, and a second difference between the first reservoir pressure value and the first reservoir pressure value; when it is determined that the first difference is greater than a preset gas flow rate threshold and the second difference is greater than a preset reservoir pressure threshold, determining the target reservoir grid area covered by the crossflow channel in multiple reservoir grid areas to obtain the position of the crossflow channel in the target reservoir.

[0012] In an embodiment of the present application, the target reservoir grid area covered by the crossflow channel in multiple reservoir grid areas is determined according to the first reservoir gas flow rate, the first reservoir pressure value, the second reservoir gas flow rate and the second reservoir pressure value to obtain the position of the crossflow channel in the target reservoir, including: based on a pre-constructed crossflow channel determination model, the target reservoir grid area covered by the crossflow channel in multiple reservoir grid areas is determined according to the first reservoir gas flow rate, the first reservoir pressure value, the second reservoir gas flow rate and the second reservoir pressure value to obtain the position of the crossflow channel in the target reservoir.

[0013] In an embodiment of the present application, the method also includes: obtaining the sealed gas volume, oil and gas production, unsealed gas volume, water production and reservoir pressure difference corresponding to the current time step; determining a first pre-reward value, a second pre-reward value, a third pre-reward value, a fourth pre-reward value and a fifth pre-reward value, wherein the first pre-reward value is determined according to the sealed gas volume and the first pre-reward value is positively correlated with the sealed gas volume, the second pre-reward value is determined according to the oil and gas production and the second pre-reward value is positively correlated with the oil and gas production, the third pre-reward value is determined according to the unsealed gas volume and is positively correlated with the unsealed gas volume, the fourth pre-reward value is determined according to the water production and is positively correlated with the water production, and the fifth pre-reward value is determined according to the water production. Five pre-reward values are determined based on the reservoir pressure difference and are positively correlated with the reservoir pressure difference; a first product value of the first preset weight value and the first pre-reward value, a second product value of the second preset weight value and the second pre-reward value, a third product value of the third preset weight value and the third pre-reward value, a fourth product value of the fourth preset weight value and the fourth pre-reward value, and a fifth product value of the fifth preset weight value and the fifth pre-reward value are determined respectively; a target reward value corresponding to the current time step is determined based on the first product value, the second product value, the third product value, the fourth product value, and the fifth product value; and model parameters of the crossflow channel determination model are updated based on the target reward value to obtain an updated crossflow channel determination model.

[0014] In an embodiment of the present application, determining the target reward value corresponding to the current time step based on the first product value, the second product value, the third product value, the fourth product value, and the fifth product value includes: determining the sum of the first product value and the second product value to obtain the first reward value; determining the third product value, the fourth product value, and the fifth product value to obtain the second reward value; and determining the difference between the first reward value and the second reward value to obtain the target reward value corresponding to the current time step.

[0015] In an embodiment of the present application, the crossflow channel determination model is a reinforcement learning model.

[0016] A second aspect of the present application provides a device for determining the location of a crossflow channel, comprising: a memory configured to store instructions; and a processor configured to call instructions from the memory and implement the above-mentioned method for determining the location of a crossflow channel in a reservoir when executing the instructions.

[0017] A third aspect of the present application provides a device for determining the position of a crossflow channel, comprising: the apparatus for determining the position of a crossflow channel in a reservoir according to the above-mentioned apparatus.

[0018] A fourth aspect of the present application provides a machine-readable storage medium having stored thereon instructions for causing a machine to execute the above-mentioned method for determining the location of a reservoir crossflow channel.

[0019] The above technical solution determines the presence of a crossflow channel in the target reservoir during the process of injecting a preset gas into the target reservoir; then, the area where the target reservoir is located is gridded to obtain multiple reservoir grid areas; based on this, the first reservoir gas flow rate and real-time reservoir pressure value corresponding to each reservoir grid area at the current time step, the reference reservoir pressure value of each reservoir grid area, and the second reservoir gas flow rate corresponding to the previous time step are obtained; further, based on the first reservoir gas flow rate, the real-time reservoir pressure value, the second reservoir gas flow rate, and the reference reservoir pressure value, the target reservoir grid area covered by the crossflow channel in the multiple reservoir grid areas is determined to obtain the position of the crossflow channel in the target reservoir. In this way, the gas flow rate and reservoir pressure value in the target reservoir are used as the judgment basis for determining the position of the crossflow channel in the target reservoir. While reducing dependence on technical personnel, it is also supported by scientific data and can accurately determine the position of the crossflow channel in the target reservoir.

[0020] Other features and advantages of the embodiments of the present application will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the following detailed description, they are used to explain the embodiments of the present application, but do not constitute a limitation of the embodiments of the present application. In the accompanying drawings:

[0022] Figure 1 A flow chart of a method for determining the location of a reservoir crossflow channel according to an embodiment of the present application is schematically shown. DETAILED DESCRIPTION

[0023] To make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the specific implementation methods described herein are only used to illustrate and explain the embodiments of the present application and are not used to limit the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0024] It should be noted that the acquisition, transmission, storage, use, and processing of data in the technical solution of this application are in compliance with the relevant provisions of national laws and regulations. In the embodiments of this application, certain software, components, models, and other existing solutions in the industry may be mentioned. These should be considered as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of this application, but it does not mean that the applicant has or will necessarily use such solutions.

[0025] It should be noted that if the embodiments of the present application involve directional indications (such as up, down, left, right, front, back, etc.), the directional indications are only used to explain the relative position relationship, movement status, etc. between the various components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indications will also change accordingly.

[0026] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present application, the descriptions of "first", "second", etc. are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of such features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the fact that they can be implemented by ordinary technicians in this field. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0027] Figure 1 The following schematically shows a flow chart of a method for determining the location of a reservoir crossflow channel according to an embodiment of the present application. Figure 1 As shown, an embodiment of the present application provides a method for determining the location of a reservoir crossflow channel. The method is described by taking the application of the method to a processor as an example. The method may include the following steps:

[0028] Step S101: during the process of injecting a preset gas into a target reservoir, determining whether a crossflow channel exists in the target reservoir.

[0029] Step S102 : Divide the area where the target reservoir is located into grids to obtain a plurality of reservoir grid areas.

[0030] Step S103, obtaining the first reservoir gas flow rate and first reservoir pressure value corresponding to each reservoir grid area at the current time step, and the second reservoir gas flow rate and second reservoir pressure value corresponding to each reservoir grid area at the previous time step.

[0031] Step S104, based on the first reservoir gas flow rate, the first reservoir pressure value, the second reservoir gas flow rate and the second reservoir pressure value, determine the target reservoir grid area covered by the crossflow channel in the multiple reservoir grid areas to obtain the location of the crossflow channel in the target reservoir.

[0032] It can be understood that the preset gas may include but is not limited to carbon dioxide. The target reservoir may include but is not limited to a reservoir into which the preset gas is injected. The time step can be a moment or a preset duration (for example, within 1s). The current time step can be the current moment or the current preset duration, and correspondingly, the previous time step can be the previous moment or the previous preset duration, and the previous time step is the previous time step adjacent to the current time step. The reservoir grid area can be a part of the area where the target reservoir is located, and the number of reservoir grid areas can be multiple (for example, 25). The reservoir gas flow rate is the flow rate of the gas inside the target reservoir. Different reservoir grid areas correspond to different first reservoir gas flow rates and real-time reservoir pressure values. The number of target reservoir grid areas can be multiple, and the target reservoir grid area is a plurality of reservoir grid areas where crossflow channels appear in the reservoir grid area, and the position of the crossflow channel can be represented by row and column numbers.

[0033] Specifically, during the process of injecting a preset gas into a target reservoir and confirming the presence of crossflow channels within the target reservoir, the target reservoir region is gridded into multiple reservoir grid regions, and a high-resolution target reservoir distribution map is generated. Furthermore, the target reservoir distribution map intuitively indicates the location of crossflow channels within each reservoir grid region. This allows target reservoir grid regions covered by crossflow channels to be marked within the target reservoir distribution map and their specific spatial coordinates or row and column numbers to accurately determine their locations.

[0034] The above-mentioned method for determining reservoir crossflow channels determines the presence of crossflow channels in the target reservoir during the process of injecting a preset gas into the target reservoir; then, the area where the target reservoir is located is gridded to obtain multiple reservoir grid areas; based on this, the first reservoir gas flow rate and real-time reservoir pressure value corresponding to each reservoir grid area at the current time step, the reference reservoir pressure value of each reservoir grid area, and the second reservoir gas flow rate corresponding to the previous time step are obtained; further, based on the first reservoir gas flow rate, the real-time reservoir pressure value, the second reservoir gas flow rate, and the reference reservoir pressure value, the target reservoir grid area covered by the crossflow channels in the multiple reservoir grid areas is determined to obtain the location of the crossflow channels in the target reservoir. In this way, the gas flow rate and reservoir pressure value in the target reservoir are used as the judgment basis for determining the location of the crossflow channels in the target reservoir. While reducing dependence on technical personnel, it is also supported by scientific data and can accurately determine the location of the crossflow channels in the target reservoir.

[0035] In one embodiment, determining the presence of a crossflow channel in a target reservoir may include: obtaining reservoir characteristic parameters, gas injection parameters, and reservoir pressure parameters of the target reservoir, wherein the reservoir characteristic parameters include a permeability heterogeneity index and a reservoir gas production, the gas injection parameters include a total gas injection volume and a reservoir gas flow rate, and the reservoir pressure parameters include a reservoir pressure difference; determining the sum of the products of the permeability heterogeneity index, the total gas injection volume, the reservoir gas flow rate, the reservoir pressure difference, and the daily gas production, respectively, and corresponding preset weight coefficients to obtain a crossflow risk value for the target reservoir; and determining the presence of a crossflow channel in the target reservoir when the crossflow risk value is greater than a preset crossflow risk threshold.

[0036] It is understood that reservoir characteristic parameters may include, but are not limited to, permeability heterogeneity index and reservoir gas production. Reservoir gas production can be set as the reservoir gas production over a preset time period (e.g., 24 hours). Gas injection parameters may include, but are not limited to, total gas injection volume and reservoir gas flow rate. The total gas injection volume is the total amount of a preset gas (e.g., carbon dioxide) injected, which is used to predict the fluid volume pressure load within the reservoir, and the reservoir gas flow rate reflects the flow rate of the preset gas (e.g., carbon dioxide) within the target reservoir. Reservoir pressure parameters include, but are not limited to, reservoir pressure difference. The reservoir pressure difference is the difference between the reservoir pressure value of the target reservoir at the current time step and the reference reservoir pressure value, which is used to comprehensively assess the pressure distribution state within the reservoir. The reference reservoir pressure value is the initial pressure value of the target reservoir in a natural equilibrium state without any preset gas injection or production operations. The preset weight coefficient is a preset weight coefficient. The crossflow risk value is an indicator for determining whether a crossflow channel exists in the target reservoir, and the preset crossflow risk threshold is a preset crossflow risk threshold. The preset weight coefficient is a preset weight coefficient corresponding to each parameter.

[0037] Specifically, the crossflow risk value can be determined by the following formula:

[0038] S=w1·V+w2·ΔP+w3·Q+w4·A+w5·T

[0039] Among them, S is the crossflow risk value, V is the reservoir gas flow rate, ΔP is the reservoir pressure difference, Q is the reservoir gas production, A is the permeability heterogeneity index, T is the total gas injection volume, w1 is the weight coefficient corresponding to the reservoir gas flow rate, w2 is the weight coefficient corresponding to the reservoir pressure difference, w3 is the weight coefficient corresponding to the reservoir gas production, w4 is the weight coefficient corresponding to the permeability heterogeneity index, and w5 is the weight coefficient corresponding to the total volume injection volume.

[0040] After determining the crossflow risk value corresponding to the current time step, the crossflow risk value is compared with the crossflow risk threshold. If the crossflow risk value is less than or equal to the preset crossflow risk threshold, it is determined that the severity of the crossflow phenomenon in the target reservoir is relatively small and no crossflow channel exists. If the crossflow risk value is greater than the preset crossflow risk threshold, the severity of the crossflow phenomenon is relatively large and a crossflow channel has formed.

[0041] After determining the crossflow risk value, the processor can also determine the crossflow risk trend based on the crossflow risk value, identify the difference between the current crossflow situation and historical data, and then determine whether stronger control measures need to be triggered based on the crossflow risk trend. The crossflow risk trend can be determined by the following formula:

[0042]

[0043] Among them, S mean and S std are the mean and standard deviation of historical crossflow risk values. norm is the normalized crossflow risk value. C is the preset adjustment factor.

[0044] When S norm When S is low, the reservoir gas velocity, reservoir pressure difference and reservoir gas production are all within the normal range, and a lower injection rate or appropriate adjustment of the injection point can be adopted to optimize the sealing effect. norm When the injection gas is medium, the concentration and flow rate of the injected gas increase. The crossflow channel determination model can recommend adjusting the injection point position or using the gas-water alternating injection method to ensure the sealing stability. norm When the value is higher than the critical value, the model automatically triggers strong control measures such as plugging agent injection to reduce the impact of crossflow on the reservoir and ensure the safety and stability of the injection gas (such as carbon dioxide) storage process.

[0045] By obtaining the reservoir characteristic parameters, gas injection parameters, and reservoir pressure parameters within the target reservoir, the crossflow risk value of the crossflow channel within the target reservoir can be determined to quantify the severity of the crossflow phenomenon in the target reservoir and compare the crossflow risk value with the crossflow risk threshold. If the crossflow channel is confirmed to exist in the target reservoir, the target reservoir area covered by the crossflow channel can be immediately determined, so that timely adjustment strategies (such as adjusting the injection rate of the gas injection equipment or blocking the crossflow channel) can be made for prevention and control.

[0046] In one embodiment, based on the first reservoir gas flow rate, the first reservoir pressure value, the second reservoir gas flow rate and the second reservoir pressure value, determining the target reservoir grid area covered by the crossflow channel in multiple reservoir grid areas to obtain the location of the crossflow channel in the target reservoir can include: determining a first difference between the first reservoir gas flow rate and the second reservoir gas flow rate, and a second difference between the first reservoir pressure value and the first reservoir pressure value; when it is determined that the first difference is greater than a preset gas flow rate threshold and the second difference is greater than a preset reservoir pressure threshold, determining the target reservoir grid area covered by the crossflow channel in multiple reservoir grid areas to obtain the location of the crossflow channel in the target reservoir.

[0047] It can be understood that the preset gas flow rate threshold may be a preset gas flow rate threshold, and the preset reservoir pressure threshold may be a preset reservoir pressure threshold.

[0048] Specifically, the first difference can be determined by calculating the difference between the gas flow rate of the first reservoir and the gas flow rate of the second reservoir. At the same time, the second difference can be determined by calculating the difference between the first reservoir pressure value and the second reservoir pressure value. The first difference and the preset gas flow rate threshold, and the second difference and the preset reservoir pressure threshold are compared respectively. Under the conditions that the first difference is greater than the preset gas flow rate threshold, and the second difference is greater than the preset reservoir pressure threshold, it can be determined that there are abnormal changes in reservoir pressure and gas flow rate (for example, a significant decrease in reservoir pressure value or a sudden increase in gas flow rate) in some areas of multiple reservoir grid areas. In this way, it can be determined that the reservoir grid area where this situation exists is covered with a crossflow channel. Based on this, the position of the crossflow channel in the target reservoir can be accurately determined by comparing with real-time data.

[0049] In addition, the processor can also call historical data for crossflow pattern matching to determine whether there are similar crossflow patterns in the historical data between the gas flow rate of the first reservoir and the gas flow rate of the second reservoir, and the pressure value of the first reservoir and the pressure value of the second reservoir. It can further determine the spatial distribution of the crossflow channel in the target reservoir, and formulate crossflow prevention and control strategies based on classification and grading to provide guarantees for efficient oil and gas extraction and carbon storage.

[0050] In one embodiment, determining the target reservoir grid area covered by the crossflow channel in multiple reservoir grid areas based on the first reservoir gas flow rate, the first reservoir pressure value, the second reservoir gas flow rate and the second reservoir pressure value to obtain the position of the crossflow channel in the target reservoir may include: based on a pre-built crossflow channel determination model, determining the target reservoir grid area covered by the crossflow channel in multiple reservoir grid areas based on the first reservoir gas flow rate, the first reservoir pressure value, the second reservoir gas flow rate and the second reservoir pressure value to obtain the position of the crossflow channel in the target reservoir.

[0051] It is understandable that the crossflow channel determination model can be constructed in advance.

[0052] Specifically, a pressure sensor or other reservoir pressure determination device is installed in the target reservoir. A gas flow rate sensor or other reservoir gas flow rate determination device may also be installed in the target reservoir. The processor obtains the first reservoir gas flow rate and first reservoir pressure value of the target reservoir at the current time step, as well as the second reservoir gas flow rate and second reservoir pressure value of the target reservoir at the previous time step, through the corresponding sensors within the target reservoir. The processor inputs these values into the crossflow channel determination model. After processing these values, the crossflow channel determination model determines the target reservoir grid area covered by the crossflow channel among the multiple reservoir grid areas and outputs the location of the crossflow channel in the target reservoir.

[0053] Through the crossflow channel determination model, real-time parameters within the target reservoir can be input to accurately determine the location of the crossflow channel, reducing dependence on technical personnel. Combined with real-time data, the accuracy of the judgment of the crossflow channel location can be improved.

[0054] In one embodiment, the method may further include: obtaining the sealed gas volume, oil and gas production, unsealed gas volume, water production and reservoir pressure difference corresponding to the current time step; determining a first pre-reward value, a second pre-reward value, a third pre-reward value, a fourth pre-reward value and a fifth pre-reward value, wherein the first pre-reward value is determined according to the sealed gas volume and the first pre-reward value is positively correlated with the sealed gas volume, the second pre-reward value is determined according to the oil and gas production and the second pre-reward value is positively correlated with the oil and gas production, the third pre-reward value is determined according to the unsealed gas volume and is positively correlated with the unsealed gas volume, the fourth pre-reward value is determined according to the water production and is positively correlated with the water production, and the fifth pre-reward value is determined according to the water production. Five pre-reward values are determined based on the reservoir pressure difference and are positively correlated with the reservoir pressure difference; a first product value of the first preset weight value and the first pre-reward value, a second product value of the second preset weight value and the second pre-reward value, a third product value of the third preset weight value and the third pre-reward value, a fourth product value of the fourth preset weight value and the fourth pre-reward value, and a fifth product value of the fifth preset weight value and the fifth pre-reward value are determined respectively; a target reward value corresponding to the current time step is determined based on the first product value, the second product value, the third product value, the fourth product value, and the fifth product value; and model parameters of the crossflow channel determination model are updated based on the target reward value to obtain an updated crossflow channel determination model.

[0055] It can be understood that the sealed gas volume is the preset gas volume that has been sealed (for example, the carbon dioxide volume). The oil and gas production is the sum of the crude oil production and the natural gas production inside the reservoir. The water production is the production of groundwater in the reservoir. The unsealed gas volume is the gas volume that causes the crossflow channel inside the reservoir. The reservoir pressure difference is the difference between the real-time reservoir pressure value and the reference reservoir pressure value. The first pre-reward value, the second pre-reward value, the third pre-reward value, the fourth pre-reward value and the fifth pre-reward value are respectively determined by the sealed gas volume, the oil and gas production, the unsealed gas volume, the water production and the reservoir pressure difference, and are positively correlated therewith. The first preset weight value, the second preset weight value, the third preset weight value, the fourth preset weight value and the fifth preset weight value can be pre-set, and the updated crossflow channel determination model can be the crossflow channel determination model after the parameters are updated.

[0056] By determining the target reward value, the real-time state changes of the target reservoir can be accurately reflected, and the injection strategy of the gas injection equipment controlled by the crossflow channel determination model can be optimized. The injection strategy includes the injection position and the injection gas flow rate. Specifically: each reward item in the target reward value is dynamically adjusted based on different variables inside the reservoir. The first pre-reward value can be determined by the sealed gas volume. The larger the sealed gas volume, the higher the first pre-reward value, so as to improve the efficiency of the sealed gas. Similarly, the second pre-reward value, the third pre-reward value, the fourth pre-reward value and the fifth pre-reward value are respectively determined by the oil and gas production, the unsealed gas volume, the water production and the reservoir pressure difference, and are positively correlated with the oil and gas production, the unsealed gas volume, the water production and the reservoir pressure difference, so as to ensure the stability of the reservoir pressure and improve the safety of operation.

[0057] In each time step, the above-mentioned pre-reward values (first pre-reward value, second pre-reward value, third pre-reward value, fourth pre-reward value, and fifth pre-reward value) will be recalculated based on these real-time variables so that the target reward value can accurately reflect the reservoir state of the current target reservoir.

[0058] In one embodiment, determining a target reward value corresponding to a current time step based on the first product value, the second product value, the third product value, the fourth product value, and the fifth product value may include: determining the sum of the first product value and the second product value to obtain a first reward value; determining the third product value, the fourth product value, and the fifth product value to obtain a second reward value; and determining a difference between the first reward value and the second reward value to obtain the target reward value corresponding to the current time step.

[0059] Specifically, the target reward value can be determined by the following formula:

[0060] R=k1·r1+k2·r2-k3·r3-k4·r4-k5·r5

[0061] Among them, R is the target reward value, k1 is the first preset weight value, k2 is the second preset weight value, k3 is the third preset weight value, k4 is the fourth preset weight value, k5 is the fifth preset weight value, r1 is the first pre-reward value, r2 is the second pre-reward value, r3 is the third pre-reward value, r4 is the fourth pre-reward value and r5 is the fifth pre-reward value.

[0062] In one embodiment, the crossflow channel determination model may be a reinforcement learning model.

[0063] It can be understood that reinforcement learning, also known as reinforcement learning, evaluation learning or enhanced learning, is an important branch of the field of machine learning. The reinforcement learning model is a model that uses the reinforcement learning algorithm.

[0064] Specifically, a reinforcement learning model, through data preprocessing and experience replay techniques, makes the identification process more automated and intelligent, enabling rapid identification and advanced analysis. By automatically extracting past interaction samples for current training, the model not only effectively breaks time series correlations and avoids local optimal solutions, but also continuously improves recognition accuracy and speed. As the model is applied more frequently, its recognition performance gradually improves, enabling faster and more accurate identification of gas channeling pathways, fully meeting the needs of identifying CO2 channeling pathways in complex reservoir conditions.

[0065] In another embodiment, the processor may determine multiple parameters, such as porosity, permeability, initial saturation, total amount of injected gas, reservoir gas density, production channel volume, cross-sectional area of gas channel pores, formation crude oil density, gas production rate, injected gas volume, reservoir gas production, reservoir oil production, reservoir water production, gas injection rate, and reservoir pressure difference, as input parameters for the channel determination model. Porosity, permeability, initial saturation, and total amount of injected gas are used to describe the physical properties of the target reservoir and the initial distribution of a predetermined gas (carbon dioxide) in the target reservoir. Reservoir gas production, reservoir oil production, reservoir water production, gas injection rate, and reservoir pressure difference are used to reflect the real-time status of various fluids during the reservoir production process and gas injection process. The above parameters can be obtained through various monitoring equipment. Porosity and permeability can be measured by geological logging equipment, initial saturation can be determined through core analysis, the total amount of injected gas can be recorded by gas injection equipment, reservoir gas production, reservoir oil production, and reservoir water production can be measured by wellhead flowmeters, and the gas injection rate and reservoir pressure differential can be monitored in real time by gas injection equipment (such as injection pumps) and pressure sensors, respectively. To further improve the accuracy of the data and the applicability of the model, data from previous literature can be combined as initial estimates, and then optimized and corrected using field monitoring data to ensure that the crossflow channel identification model accurately reflects the reservoir state and optimizes identification and treatment strategies.

[0066] To ensure data accuracy and consistency, the processor can also perform data preprocessing on the raw data (data obtained from real-time monitoring). Data preprocessing can include steps such as data cleaning, normalization, and time series organization. The data cleaning process aims to remove noise and outliers to ensure data accuracy. Normalization is to scale the data to a uniform scale, usually using a normalization formula.

[0067] The normalization formula can be:

[0068]

[0069] Among them, x new is the normalized data, xold is the original data, x min and x max are the minimum and maximum values of the original data, respectively.

[0070] The channel determination model is based on the reward value R obtained after executing the action t and the next state S t+1 Update the Q value, and the update formula is:

[0071]

[0072] Among them, α is the learning rate, which controls the update step size; γ is the discount factor, which determines the current value of the future reward; Q value Q(S t ,a t ) represents the current state S of the target reservoir t Next, select Action A t The cumulative expected reward obtained, the target Q value is determined by the immediate reward R t and the next state S t+1 The maximum Q value in Through continuous training, the crossflow channel determination model can gradually approach the optimal strategy, allowing it to autonomously learn and optimize the migration path and storage strategy of carbon dioxide in complex geological environments.

[0073] When the crossflow channel determines the model in state S t Perform a specific action a t Then get the reward value R t , and enter the next state S t+1 When the model calculates the difference between the current Q value and the target Q value. The target Q value is determined by the immediate reward R t and the next state S t+1 The maximum Q value in The reservoir state S of the target reservoir t These parameters include, but are not limited to, porosity, permeability, initial saturation, total injected gas volume, reservoir gas density, production channel volume, cross-sectional area of gas channel pores, formation crude oil density, gas production rate, injected gas volume, reservoir gas production, reservoir oil production, reservoir water production, gas injection rate, and reservoir pressure differential. These parameters describe the reservoir's physical properties and production dynamics, ensuring that the model comprehensively considers actual changes in reservoir and production conditions when updating the Q value. During each update, the difference in value adjusts the Q value using a learning rate α, gradually optimizing the cross-channel determination model's decision-making ability in reservoir management. This ensures that the model parameters better reflect reservoir conditions and enables precise optimization of CO2 migration pathways and storage strategies.

[0074] In a specific embodiment, the crossflow channel determination model can also predict the occurrence time of gas crossflow in the target reservoir, so that effective preventive measures can be taken before the gas crossflow occurs, such as adjusting the injection rate or increasing the density of the wellbore pressure fluid, thereby reducing the impact of gas crossflow on the reservoir sealing stability and ensuring the safety and effectiveness of the carbon dioxide storage process.

[0075] The core formula for predicting the occurrence time of gas channeling is as follows:

[0076]

[0077] Where Q(t) represents the gas velocity or flow rate at time t, k is the reservoir permeability, which represents the reservoir's resistance to fluid penetration, A is the cross-sectional area of the seepage channel in square meters, Δp is the pressure difference between the injection point and the production point in the reservoir, μ is the viscosity of the fluid in Pascal seconds (Pa·s), L is the length of the path of gas flow in the reservoir, t is the time at which the gas channeling phenomenon needs to be predicted, t0 is the initial moment, which usually represents the time when the injection operation begins, and σ is the standard deviation of the gas flow rate time series, which is used to describe the fluctuation characteristics of the time variation of the gas flow process, especially the fluctuation amplitude at different flow rates.

[0078] In a specific embodiment, the total cost of the remediation process can be determined by the crossflow channel determination model, thereby judging the economic and effectiveness of the remediation strategy of the crossflow channel determination model, thereby reducing resource waste in the remediation process while maintaining high storage efficiency. The total cost can be determined by the following formula:

[0079]

[0080] Among them, Cost total Represents the total cost accumulated during the entire governance process. injection (t) represents the cost of the injection operation at time t. pressure (t) represents the cost of adjusting the reservoir pressure at time t. relocation (t) represents the cost of adjusting the injection point position at time t.

[0081] Taking the CO2 storage process as an example, after the process is complete, the effectiveness of the management strategy is comprehensively evaluated through analysis of monitoring data. Combined with the adjustments to the crossflow channel determination model during the management process, the following key conclusions can be drawn: First, the CO2 storage capacity index (CSI) assesses the effectiveness of the management strategy. This index measures the ratio of successfully stored CO2 to the total injected volume. A CSI of 90% or higher is generally required to be considered effective. Second, the effectiveness of crossflow control is assessed using the crossflow control index. This index is measured by the crossflow reduction rate, and a CSI of 30% or higher is generally required to be considered effective. Finally, the CO2 utilization efficiency index assesses resource efficiency. This index measures the ratio of successfully stored CO2 to the total CO2 consumed during the management process. A CSI of 80% or higher is generally required to ensure economical resource utilization and avoid waste. These quantitative indicators can scientifically assess the effectiveness of the management strategy and provide a basis for further optimization, ensuring the stability and long-term effectiveness of the CO2 storage process.

[0082] In order to further quantify the governance effect, this application can introduce a comprehensive benefit function to calculate the governance benefits under different combinations of governance parameters:

[0083]

[0084] Among them, E total represents the overall benefit of the remediation process, S(t) represents the storage efficiency, G(t) represents the amount of unstored gas, and R(t) represents the resource cost. w1, w2, and w3 represent the weights of the storage efficiency, unstored gas, and resource cost, respectively. The core of the optimization process is to adjust these weights to achieve the optimal remediation effect: First, by increasing the weight of w1, the CO2 storage efficiency is maximized, achieving the desired storage effect. Second, by adjusting the weight of w2, the frequency and scale of gas leakage are reduced, effectively minimizing the impact of gas leakage on the storage process and ensuring the stability and safety of the gas in the reservoir. Finally, by optimizing the weight of w3, resource utilization is optimized while meeting the requirements of storage and gas cross-flow control, avoiding unnecessary waste. Through this optimized adjustment of weights, a balance is achieved between storage efficiency, gas cross-flow control, and resource cost, ensuring that the remediation process achieves maximum benefits at the lowest resource cost, guaranteeing economic efficiency and long-term stability.

[0085] A second aspect of an embodiment of the present application also provides a device for determining the position of a crossflow channel, which may include: a memory configured to store instructions; and a processor configured to call instructions from the memory and implement the above-mentioned method for determining the position of a crossflow channel in a reservoir when executing the instructions.

[0086] A third aspect of the embodiments of the present application further provides a device for determining the position of a crossflow channel, which may include: the device for determining the position of a crossflow channel in a reservoir according to the above-mentioned device.

[0087] A fourth aspect of the embodiments of the present application further provides a machine-readable storage medium having stored thereon instructions for causing a machine to execute the above-mentioned method for determining the location of reservoir crossflow channels.

[0088] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0089] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0090] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0091] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps for the function specified in one or more boxes.

[0092] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0093] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0094] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules, 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 technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory media such as modulated data signals and carrier waves.

[0095] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0096] The above are merely embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A method for determining the location of a reservoir crossflow channel, characterized in that: The method comprises: During the process of injecting a preset gas into a target reservoir, determining that a crossflow channel exists in the target reservoir; Dividing the area where the target reservoir is located into grids to obtain a plurality of reservoir grid areas; Obtaining a first reservoir gas flow rate and a first reservoir pressure value corresponding to each of the reservoir grid areas at a current time step, and a second reservoir gas flow rate and a second reservoir pressure value corresponding to each of the reservoir grid areas at a previous time step; Determining a target reservoir grid area covered by the crossflow channel among the plurality of reservoir grid areas based on the first reservoir gas flow rate, the first reservoir pressure value, the second reservoir gas flow rate, and the second reservoir pressure value, so as to obtain a position of the crossflow channel in the target reservoir; Wherein, determining the existence of a crossflow channel in the target reservoir includes: obtaining reservoir characteristic parameters, gas injection parameters and reservoir pressure parameters of the target reservoir, wherein the reservoir characteristic parameters include a permeability heterogeneity index and a reservoir gas production, the gas injection parameters include a total gas injection volume and a reservoir gas flow rate, and the reservoir pressure parameters include a reservoir pressure difference; determining the sum of the products of the permeability heterogeneity index, the total gas injection volume, the reservoir gas flow rate, the reservoir pressure difference and the reservoir gas production, respectively, and corresponding preset weight coefficients to obtain a crossflow risk value of the target reservoir; and determining the existence of a crossflow channel in the target reservoir when the crossflow risk value is greater than a preset crossflow risk threshold.

2. The method according to claim 1, characterized in that The step of determining a target reservoir grid area covered by the crossflow channel among the plurality of reservoir grid areas based on the first reservoir gas flow rate, the first reservoir pressure value, the second reservoir gas flow rate, and the second reservoir pressure value, so as to obtain a position of the crossflow channel in the target reservoir, includes: determining a first difference between the first reservoir gas flow rate and the second reservoir gas flow rate, and a second difference between the first reservoir pressure value and the second reservoir pressure value; When it is determined that the first difference is greater than a preset gas flow rate threshold and the second difference is greater than a preset reservoir pressure threshold, the target reservoir grid area covered by the crossflow channel in the multiple reservoir grid areas is determined to obtain the position of the crossflow channel in the target reservoir.

3. The method according to claim 1, characterized in that The step of determining a target reservoir grid area covered by the crossflow channel among the plurality of reservoir grid areas based on the first reservoir gas flow rate, the first reservoir pressure value, the second reservoir gas flow rate, and the second reservoir pressure value, so as to obtain a position of the crossflow channel in the target reservoir, includes: Based on a pre-constructed crossflow channel determination model, the target reservoir grid area covered by the crossflow channel in the multiple reservoir grid areas is determined according to the first reservoir gas flow rate, the first reservoir pressure value, the second reservoir gas flow rate and the second reservoir pressure value to obtain the position of the crossflow channel in the target reservoir.

4. The method according to claim 3, characterized in that The method further comprises: Obtain the stored gas volume, oil and gas production, unstored gas volume, water production, and reservoir pressure difference corresponding to the current time step; determining a first pre-reward value, a second pre-reward value, a third pre-reward value, a fourth pre-reward value, and a fifth pre-reward value, wherein the first pre-reward value is determined based on the sealed gas volume and is positively correlated with the sealed gas volume, the second pre-reward value is determined based on the oil and gas production and is positively correlated with the oil and gas production, the third pre-reward value is determined based on the unsealed gas volume and is positively correlated with the unsealed gas volume, the fourth pre-reward value is determined based on the water production and is positively correlated with the water production, and the fifth pre-reward value is determined based on the reservoir pressure difference and is positively correlated with the reservoir pressure difference; respectively determining a first product value of a first preset weight value and the first pre-reward value, a second product value of a second preset weight value and the second pre-reward value, a third product value of a third preset weight value and the third pre-reward value, a fourth product value of a fourth preset weight value and the fourth pre-reward value, and a fifth product value of a fifth preset weight value and the fifth pre-reward value; determining a target reward value corresponding to a current time step according to the first product value, the second product value, the third product value, the fourth product value, and the fifth product value; Based on the target reward value, the model parameters of the crossflow channel determination model are updated to obtain an updated crossflow channel determination model.

5. The method according to claim 4, characterized in that Determining a target reward value corresponding to a current time step according to the first product value, the second product value, the third product value, the fourth product value, and the fifth product value includes: determining a sum of the first product value and the second product value to obtain a first reward value; determining the third product value, the fourth product value, and the fifth product value to obtain a second reward value; Determine a difference between the first reward value and the second reward value to obtain the target reward value corresponding to the current time step.

6. The method according to claim 3, characterized in that The crossflow channel determination model is a reinforcement learning model.

7. A device for determining the position of a crossflow channel, characterized in that: include: a memory configured to store instructions; as well as A processor is configured to call the instructions from the memory and implement the method for determining the location of a reservoir crossflow channel according to any one of claims 1 to 6 when executing the instructions.

8. A device for determining the position of a crossflow channel, characterized in that: include: The device for determining the location of reservoir crossflow channels according to claim 7.

9. A machine-readable storage medium, characterized in that The machine-readable storage medium stores instructions for causing a machine to execute the method for determining the location of a reservoir crossflow channel according to any one of claims 1 to 6.

Images