A gas storage reservoir parameter dynamic prediction method and system

Abstract

The application relates to the technical field of gas storage operation monitoring, and relates to a gas storage reservoir parameter dynamic prediction method and system, which comprises the following steps: detecting the permeability of a core sample to obtain an initial permeability, testing the stress sensitivity of the core sample to obtain a stress sensitivity coefficient, obtaining a standardized historical operation parameter set of the gas storage, constructing a reservoir pressure prediction model by using the standardized historical operation parameter set, obtaining a target operation parameter set, inputting the target operation parameter set into the reservoir pressure prediction model to obtain a target reservoir pressure sequence, correcting the initial permeability by using the target reservoir pressure sequence and the stress sensitivity coefficient to obtain a corrected permeability sequence, obtaining a reservoir seepage capacity sequence by using the target reservoir pressure sequence, a target flow pressure sequence and the corrected permeability sequence, and performing reservoir capacity evaluation based on the reservoir seepage capacity sequence to obtain a reservoir capacity evaluation result. The application can improve the accuracy of identifying the seepage capacity change trend of the reservoir.

Description

Technical Field

[0001] This invention relates to the field of gas storage operation monitoring technology, and in particular to a method and system for dynamic prediction of gas storage reservoir parameters. Background Technology

[0002] Underground gas storage facilities are crucial infrastructure for ensuring a stable supply of natural gas. They function as seasonal peak shaving and energy reserves by injecting and extracting natural gas from underground reservoirs. By obtaining the initial permeability and stress sensitivity coefficient of core samples and combining them with historical operating parameters of the gas storage facility, future reservoir pressure is predicted. The permeability is then dynamically adjusted based on pressure changes to further calculate the reservoir's seepage capacity and complete the reservoir's operational status assessment.

[0003] Currently, methods for obtaining reservoir parameters in gas storage facilities mainly include field pressure testing, well test analysis, and laboratory core testing. While field pressure testing can obtain pressure data under certain operational conditions, it is limited by testing cycles, costs, and well conditions, making continuous dynamic prediction difficult. Well test analysis methods typically rely on specific testing conditions and are ill-suited to the complex changes that occur during the long-term cyclic injection and production process in gas storage facilities. Therefore, optimizing dynamic prediction methods for gas storage reservoir parameters is crucial for improving the accuracy of identifying trends in reservoir permeability and enabling early assessment of reservoir operational status. Summary of the Invention

[0004] This invention provides a method for dynamic prediction of gas storage reservoir parameters and a computer-readable storage medium, the main purpose of which is to improve the accuracy of identifying the trend of changes in the seepage capacity of the reservoir.

[0005] To achieve the above objectives, the present invention provides a method for dynamic prediction of gas storage reservoir parameters, comprising: Receive dynamic prediction instructions and determine the dynamic prediction environment based on the dynamic prediction instructions. The dynamic prediction environment includes the gas storage facility and the prediction time window. The prediction time window includes the data acquisition window and the parameter prediction window. Based on core samples obtained from the gas storage facility, the permeability of the core samples was measured to obtain the initial permeability; Stress sensitivity tests were performed on the core samples to obtain the stress sensitivity coefficient; The historical operating parameter set of the gas storage facility is obtained based on the data acquisition window within the prediction time window. The historical operating parameter set includes the steam injection sequence, gas production sequence, flow pressure sequence, and historical reservoir pressure sequence. Preprocess the historical operating parameter set to obtain a standardized historical operating parameter set; A reservoir pressure prediction model is constructed using the standardized historical operating parameter set. The target operating parameter set is obtained based on the parameter prediction window, and the target operating parameter set is input into the reservoir pressure prediction model to obtain the target reservoir pressure sequence, wherein the target reservoir pressure sequence includes multiple target reservoir pressures; The initial permeability was corrected using the target reservoir pressure sequence and stress sensitivity coefficient to obtain the corrected permeability sequence; Extract the target flow pressure sequence based on the target operating parameter set; The reservoir permeability sequence is obtained by using the target reservoir pressure sequence, target flowing pressure sequence and modified permeability sequence. The reservoir capacity is then assessed based on the reservoir permeability sequence to obtain the reservoir capacity assessment results.

[0006] Optionally, the permeability test of the core sample to obtain the initial permeability includes: The core samples were standardized to obtain standard core samples. Porosity was determined by testing the porosity of standard core samples. The standard core sample was cut at equal intervals to obtain multiple core samples. Perform the following operation on each of the multiple core samples: Microstructure images of core samples were obtained using pre-confirmed electron microscopy. The core particle diameter, capillary tortuosity, maximum pore diameter, and minimum pore diameter are obtained using the microstructure images. The fractal dimension is calculated using the porosity, maximum pore diameter, and minimum pore diameter. By summarizing the maximum pore diameter, minimum pore diameter, capillary tortuosity, core particle diameter, and fractal dimension, multiple maximum pore diameters, multiple minimum pore diameters, multiple capillary tortuosities, multiple core particle diameters, and multiple fractal dimensions are obtained. The measured maximum pore diameter, measured capillary tortuosity, measured core particle diameter, and measured fractal dimension are obtained by using the multiple maximum pore diameters, multiple minimum pore diameters, multiple capillary tortuosities, multiple core particle diameters, and multiple fractal dimensions. The measured permeability is calculated using the porosity, measured fractal dimension, measured maximum pore diameter, measured capillary tortuosity, and measured core particle diameter. The theoretical permeability was calculated using porosity, measured capillary tortuosity, measured core particle diameter, and measured fractal dimension. The initial permeability is calculated using theoretical and measured permeability.

[0007] Optionally, obtaining the core particle diameter, capillary tortuosity, maximum pore diameter, and minimum pore diameter using the microstructure image includes: The microstructure image is converted to grayscale to obtain a grayscale image; The grayscale image is preprocessed and filtered to obtain a denoised grayscale image; The denoised grayscale image is subjected to binary segmentation to obtain a binarized image; Connectivity analysis was performed on the binarized image to obtain multiple pore connected regions and multiple core particle regions; Capillary tortuosity is obtained by utilizing multiple interconnected pore regions. For each of the multiple pore connectivity regions, perform the following operation: Obtain the pixel area of ​​the connected region of the aperture; The actual physical area is obtained based on the pre-confirmed scale and pixel area. Construct an equivalent circle using the actual physical area, and obtain the diameter of the equivalent circle. By summing up the equivalent circle diameters, multiple equivalent circle diameters are obtained; The maximum and minimum pore diameters were determined based on multiple equivalent circle diameters; Core particle diameters were obtained using multiple core particle regions.

[0008] Optionally, obtaining the capillary tortuosity using multiple interconnected pore regions includes: Multiple distance-transformed images are obtained using the multiple interconnected pore regions; Perform the following operation on each of the multiple distance-transformed images: The center pixel of the distance-transformed image is extracted to obtain multiple candidate centerline pixels; The target centerline is obtained by connecting and correcting multiple candidate pixels for the centerline. The target centerline is divided into multiple discrete curves by equal intervals. Obtain multiple arc lengths of multiple discrete curves, where each arc length corresponds one-to-one with a discrete curve; Multiple line segment lengths are obtained using multiple discrete curves, where each line segment length corresponds one-to-one with a discrete curve. Calculate multiple local curvature rates using multiple curve arc lengths and multiple line segment lengths; Calculate the local capillary tortuosity using multiple local tortuosities; By summarizing the aforementioned local capillary tortuosities, multiple local capillary tortuosities are obtained; The capillary tortuosity is calculated using multiple local capillary tortuosities.

[0009] Optionally, acquiring multiple distance-transformed images using the multiple interconnected aperture regions includes: For each of the multiple pore connectivity regions, perform the following operation: Constructing connected region images based on pore connected regions; Extracting pixels from multiple connected regions based on connected region images; Multiple boundary pixels were identified using the connected component image; Perform the following operation on each of the connected region pixels in a plurality of connected region pixels; Calculate multiple Euclidean distances using connected region pixels and multiple boundary pixels; Obtain distance change values ​​using multiple Euclidean distances; By summing the distance change values, multiple distance change values ​​are obtained; Construct a distance transformation matrix using multiple distance change values; The distance transformation matrix is ​​used to obtain the distance transformation image; By summing the distance-transformed images, multiple distance-transformed images are obtained.

[0010] Optionally, the calculation of theoretical permeability using porosity, measured capillary tortuosity, measured core particle diameter, and measured fractal dimension includes: The theoretical maximum pore diameter was calculated using porosity and measured core particle diameter. The theoretical minimum pore diameter is calculated using the measured fractal dimension and the theoretical maximum pore diameter. The theoretical permeability is calculated using the theoretical maximum pore diameter, the theoretical minimum pore diameter, the measured capillary tortuosity, and the measured fractal dimension. The formula for calculating the theoretical permeability is shown below:

[0011] in, Indicates theoretical penetration rate. Indicates porosity. Represents the measured fractal dimension. This represents the measured capillary tortuosity. Indicates the theoretical maximum pore diameter. This represents the theoretical minimum pore diameter.

[0012] Optionally, the formula for calculating the theoretical maximum pore diameter is as follows:

[0013] in, This indicates the measured diameter of the core particles. This represents the pre-confirmed value of pi.

[0014] Optionally, the stress sensitivity test of the core sample to obtain the stress sensitivity coefficient includes: Set multiple test confining pressure values; For each of the multiple test confining pressure values, perform the following operation: Based on the test confining pressure value and the core sample, pressure is applied to obtain a compressed core sample; The permeability of the compressed rock core sample was measured to obtain the test permeability. By summing up the aforementioned test penetration rates, multiple test penetration rates are obtained; A permeability variation curve was constructed using multiple permeability tests and multiple confining pressure values. The stress sensitivity coefficient is obtained using the permeability change curve.

[0015] Optionally, the step of correcting the initial permeability using the target reservoir pressure sequence and stress sensitivity coefficient to obtain a corrected permeability sequence includes: Initial reservoir pressure is extracted based on historical reservoir pressure sequences; For each target reservoir pressure in the target reservoir pressure sequence, the following operation is performed: Calculate the pressure change using the target reservoir pressure and the initial reservoir pressure; The permeability correction factor is calculated using the pressure change and stress sensitivity coefficient. Calculate the corrected permeability using the permeability correction factor and the initial permeability; By summing the corrected permeability rates, a corrected permeability rate sequence is obtained.

[0016] To achieve the above objectives, the present invention also provides a dynamic prediction system for gas storage reservoir parameters, comprising: The initial parameter calculation module is used to receive dynamic prediction instructions and determine the dynamic prediction environment based on the dynamic prediction instructions. The dynamic prediction environment includes the gas storage facility and the prediction time window, which includes the data acquisition window and the parameter prediction window. Based on core samples obtained from the gas storage facility, the permeability of the core samples was measured to obtain the initial permeability; Stress sensitivity tests were performed on the core samples to obtain the stress sensitivity coefficient; The operation parameter processing module is used to obtain the historical operation parameter set of the gas storage based on the data acquisition window in the prediction time window. The historical operation parameter set includes the steam injection sequence, gas production sequence, flow pressure sequence and historical reservoir pressure sequence. Preprocess the historical operating parameter set to obtain a standardized historical operating parameter set; The prediction model building module is used to build a reservoir pressure prediction model using the standardized historical operating parameter set. The reservoir capacity assessment module is used to obtain a target operating parameter set based on the parameter prediction window, input the target operating parameter set into the reservoir pressure prediction model, and obtain a target reservoir pressure sequence, wherein the target reservoir pressure sequence includes multiple target reservoir pressures. The initial permeability was corrected using the target reservoir pressure sequence and stress sensitivity coefficient to obtain the corrected permeability sequence; Extract the target flow pressure sequence based on the target operating parameter set; The reservoir permeability sequence is obtained by using the target reservoir pressure sequence, target flowing pressure sequence and modified permeability sequence. The reservoir capacity is then assessed based on the reservoir permeability sequence to obtain the reservoir capacity assessment results.

[0017] To address the above problems, the present invention also provides an electronic device, the electronic device comprising: A memory that stores at least one instruction; and a processor that executes the instructions stored in the memory to implement the above-described method for dynamic prediction of gas storage reservoir parameters.

[0018] To address the aforementioned problems, the present invention also provides a computer-readable storage medium storing at least one instruction, which is executed by a processor in an electronic device to implement the aforementioned method for dynamic prediction of gas storage reservoir parameters.

[0019] To address the problems described in the background art, this invention receives dynamic prediction commands and determines a dynamic prediction environment based on these commands. The dynamic prediction environment includes a gas storage facility and a prediction time window, which comprises a data acquisition window and a parameter prediction window. Core samples are acquired from the gas storage facility, and permeability is measured to obtain an initial permeability. Thus, this invention, by determining the prediction time window of the gas storage facility and acquiring the initial permeability of the core samples, accurately obtains the basic seepage characteristics of the reservoir, providing a basis for subsequent dynamic permeability correction based on pressure changes. Furthermore, this invention performs stress sensitivity testing on the core samples to obtain a stress sensitivity coefficient. This invention, by acquiring the permeability change characteristics of the core samples under different pressures, obtains a stress sensitivity coefficient characterizing the impact of reservoir pressure changes on permeability, providing a basis for subsequent dynamic permeability correction based on predicted reservoir pressure. Subsequently, this invention obtains the historical operating parameter set of the gas storage facility through a data acquisition window based on the prediction time window. The historical operating parameter set includes the steam injection rate sequence, gas production rate sequence, flow pressure sequence, and historical reservoir pressure sequence. The historical operating parameter set is preprocessed to obtain a standardized historical operating parameter set. It can be seen that the embodiments of this invention obtain a historical operating parameter set containing information on gas injection and production processes and reservoir pressure changes, and standardize different types of operating parameters to reduce the impact of parameter dimension differences on the subsequent model training process, thus providing a unified data foundation for establishing a reservoir pressure prediction model. Then, the present invention constructs a reservoir pressure prediction model using the standardized historical operating parameter set, obtains a target operating parameter set based on the parameter prediction window, and inputs the target operating parameter set into the reservoir pressure prediction model to obtain a target reservoir pressure sequence. The target reservoir pressure sequence includes multiple target reservoir pressures. It can be seen that the embodiments of the present invention establish a reservoir pressure prediction model based on historical operating parameters and dynamically predict the reservoir pressure using operating parameters within the future prediction time window to obtain target reservoir pressures corresponding to multiple time points. This enables the early acquisition of the future reservoir pressure change trend of the gas storage facility, providing data basis for subsequent permeability correction and reservoir seepage capacity assessment based on pressure changes. Furthermore, this invention corrects the initial permeability using the target reservoir pressure sequence and stress sensitivity coefficient to obtain a corrected permeability sequence. It then extracts the target flow pressure sequence based on the target operating parameter set. Finally, it obtains the reservoir flow capacity sequence using the target reservoir pressure sequence, target flow pressure sequence, and corrected permeability sequence. Based on this flow capacity sequence, it performs reservoir capacity assessment to obtain the reservoir capacity assessment result. It is evident that this embodiment of the invention dynamically corrects the permeability by combining the predicted reservoir pressure changes and stress sensitivity characteristics, avoiding deviations in reservoir state characterization caused by a fixed permeability. Furthermore, by comprehensively considering reservoir pressure, flow pressure, and corrected permeability to obtain the reservoir flow capacity sequence, it achieves an accurate assessment of the future reservoir flow capacity changes in a gas storage facility.Therefore, the present invention can improve the accuracy of identifying the trend of changes in reservoir permeability. Attached Figure Description

[0020] Figure 1 A flowchart illustrating a method for dynamic prediction of gas storage reservoir parameters according to an embodiment of the present invention; Figure 2 This is a functional block diagram of a dynamic prediction system for gas storage reservoir parameters provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of an electronic device for implementing the dynamic prediction method of gas storage reservoir parameters according to an embodiment of the present invention.

[0021] Explanation of reference numerals in the attached figures: 10. Electronic device; 11. Processor; 12. Memory; 13. Bus.

[0022] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0023] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0024] This application provides a method for dynamically predicting reservoir parameters in a gas storage facility. The execution entity of this method includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application: a server, a terminal, etc. In other words, the method for dynamically predicting reservoir parameters can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster.

[0025] Reference Figure 1 The diagram shown is a flowchart illustrating a dynamic prediction method for gas storage reservoir parameters according to an embodiment of the present invention. In this embodiment, the dynamic prediction method for gas storage reservoir parameters includes: S1. Receive dynamic prediction instructions and determine the dynamic prediction environment based on the dynamic prediction instructions. The dynamic prediction environment includes the gas storage facility and the prediction time window. The prediction time window includes the data acquisition window and the parameter prediction window.

[0026] It should be explained that a dynamic prediction command is an instruction issued by personnel who wish to predict the reservoir parameters of a gas storage facility. A dynamic prediction environment is the necessary environment for predicting reservoir parameters. A gas storage facility refers to the gas storage facility for which reservoir parameter prediction is required. The prediction time window is the complete time range covered by this reservoir parameter prediction, which includes a data acquisition window and a parameter prediction window. The data acquisition window is the time range from which historical operating parameter sets are extracted from the historical production database, and it is located before the current time. The historical production database is a dataset used to store real-time monitoring data of the gas storage facility throughout its entire historical production time. This real-time monitoring data includes steam injection volume, gas production volume, bottom hole flowing pressure, casing pressure, and fluid temperature recorded in chronological order from earliest to latest. The current time is the moment the dynamic prediction command is received. The parameter prediction window is the time range covered by the predicted target reservoir pressure sequence, and it is located after the current time.

[0027] S2. Obtain core samples from the gas storage facility, perform permeability testing on the core samples, and obtain the initial permeability.

[0028] It should be explained that obtaining core samples from a gas storage facility refers to the process of collecting rock samples from the reservoir section of the gas storage facility. Core samples are rock samples collected from the target reservoir section of the gas storage facility; for example, cylindrical cores with a diameter of 50 mm and a length of 100 mm are used to reflect the porosity of the reservoir.

[0029] Furthermore, the permeability testing of the core sample to obtain the initial permeability includes: The core samples were standardized to obtain standard core samples. Porosity was determined by testing the porosity of standard core samples. The standard core sample was cut at equal intervals to obtain multiple core samples. Perform the following operation on each of the multiple core samples: Microstructure images of core samples were obtained using pre-confirmed electron microscopy. The core particle diameter, capillary tortuosity, maximum pore diameter, and minimum pore diameter are obtained using the microstructure images. The fractal dimension is calculated using the porosity, maximum pore diameter, and minimum pore diameter. By summarizing the maximum pore diameter, minimum pore diameter, capillary tortuosity, core particle diameter, and fractal dimension, multiple maximum pore diameters, multiple minimum pore diameters, multiple capillary tortuosities, multiple core particle diameters, and multiple fractal dimensions are obtained. The measured maximum pore diameter, measured capillary tortuosity, measured core particle diameter, and measured fractal dimension are obtained by using the multiple maximum pore diameters, multiple minimum pore diameters, multiple capillary tortuosities, multiple core particle diameters, and multiple fractal dimensions. The measured permeability is calculated using the porosity, measured fractal dimension, measured maximum pore diameter, measured capillary tortuosity, and measured core particle diameter. The theoretical permeability was calculated using porosity, measured capillary tortuosity, measured core particle diameter, and measured fractal dimension. The initial permeability is calculated using theoretical and measured permeability.

[0030] Further, standardization involves washing and drying the core sample to remove residual oil, gas, and moisture from the pores. A standard core sample is a core sample that has undergone standardization. Porosity testing is the process of determining the percentage of pore volume in a standard core sample relative to its total volume. Optionally, an oil immersion saturation method can be used for porosity testing. Porosity is the percentage of pore volume in a standard core sample relative to its total volume, obtained through porosity testing. Equal-interval cutting is the process of cutting the standard core sample along its axial direction at predetermined fixed intervals (e.g., 10 mm) to obtain multiple core samples. The axial direction refers to the direction of the geometric center axis of the standard core sample, i.e., the direction extending along the length of the core sample. The core sample is a slice of the core sample obtained through equal-interval cutting, resembling a thin sheet.

[0031] Understandably, a microstructure image is an image of the surface of a core sample obtained using an electron microscope. Fractal dimension is a parameter used to quantify the complexity of the pore structure of a reservoir core sample; the formula for calculating fractal dimension is as follows:

[0032] in, Denotes the fractal dimension. Indicates porosity. Indicates the minimum pore diameter. This indicates the maximum pore diameter.

[0033] Furthermore, the measured maximum pore diameter is the average of multiple maximum pore diameters. The measured capillary tortuosity is the average of multiple capillary tortuosities. The measured core particle diameter is the average of multiple core particle diameters. The measured fractal dimension is the average of multiple fractal dimensions. The initial permeability is a parameter used to characterize the seepage capacity of the core sample, obtained by permeability testing of the core sample, wherein the initial permeability is the square root of the product of the theoretical permeability and the measured permeability.

[0034] It should be explained that obtaining the core particle diameter, capillary tortuosity, maximum pore diameter, and minimum pore diameter using the microstructure image includes: The microstructure image is converted to grayscale to obtain a grayscale image; The grayscale image is preprocessed and filtered to obtain a denoised grayscale image; The denoised grayscale image is subjected to binary segmentation to obtain a binarized image; Connectivity analysis was performed on the binarized image to obtain multiple pore connected regions and multiple core particle regions; Capillary tortuosity is obtained by utilizing multiple interconnected pore regions. Core particle diameter was obtained using multiple core particle regions; For each of the multiple pore connectivity regions, perform the following operation: Obtain the pixel area of ​​the connected region of the aperture; The actual physical area is obtained based on the pre-confirmed scale and pixel area. Construct an equivalent circle using the actual physical area, and obtain the diameter of the equivalent circle. By summing up the equivalent circle diameters, multiple equivalent circle diameters are obtained; The maximum and minimum pore diameters were determined based on multiple equivalent circle diameters.

[0035] Furthermore, grayscale conversion is the process of converting a microstructure image into a grayscale image. The grayscale image is the microstructure image after grayscale conversion. Preprocessing filtering is the process of denoising the grayscale image. Optionally, median filtering is used as the preprocessing filtering method. The denoised grayscale image is the grayscale image after preprocessing filtering. Binary segmentation uses a segmentation threshold to divide the pixels in the denoised grayscale image into two categories: one category is labeled as pore region pixels, and the other category is labeled as rock skeleton region pixels. Pixels greater than or equal to the segmentation threshold are classified as pore region pixels, and pixels less than the segmentation threshold are classified as rock skeleton region pixels. In the binarized image, the grayscale value of pore region pixels is assigned 255 (white), and the grayscale value of rock skeleton region pixels is assigned 0 (black), creating a black-and-white contrast between the pore region and the rock skeleton region in the binarized image. The segmentation threshold is a threshold value used to divide pixels in a denoised grayscale image into pixels representing pore regions and pixels representing rock skeleton regions. This segmentation threshold is adaptively determined using the Otsu algorithm, which will not be elaborated further here. The binarized image is the image obtained after binary segmentation, where pore regions are represented by white pixels and rock skeleton regions by black pixels. Pore region pixels represent the pore spaces (i.e., the voids that store natural gas) in the core sample. Rock skeleton region pixels represent the solid rock particles (i.e., the mineral components that make up the rock matrix) in the core sample.

[0036] Understandably, connected component analysis is the process of dividing adjacent pixels with the same gray value in a binarized image into a region. A pore connected region is a region in a binarized image composed of multiple adjacent pore region pixels. A core particle region is a region in a binarized image composed of multiple adjacent rock skeleton region pixels. Obtaining the core particle diameter using multiple core particle regions refers to obtaining multiple equivalent particle diameters from multiple core particle regions, and taking the average of these equivalent diameters as the core particle diameter. The method for obtaining multiple equivalent particle diameters using multiple core particle regions is the same as the method for obtaining multiple equivalent circle diameters using multiple pore connected regions, and will not be repeated here. The particle equivalent diameter is the diameter of the equivalent circle corresponding to the core particle region. The core particle diameter is the average of multiple particle equivalent diameters.

[0037] Furthermore, the pixel area is the number of pixels in the pore region contained within the pore-connected region. Obtaining the actual physical area based on a pre-confirmed scale and pixel area refers to the process of converting the pixel area of ​​the pore-connected region into the physical area in real space according to the scale. The physical area is the product of the square of the scale and the pixel area. The scale is the ratio between the pixel length in the binarized image and the actual physical length, used to convert image size to actual size. For example, 1 pixel equals 0.1 micrometers. The scale is obtained through calibration data from an electron microscope, which will not be elaborated further here. The actual physical area is the area after converting the pixel area using the scale, used to represent the area occupied by the pore region.

[0038] Furthermore, the equivalent circle is a circle with the same actual physical area as the pore-connected region. The diameter of the equivalent circle is the diameter of the pore itself, and the formula for calculating the diameter of the equivalent circle is as follows:

[0039] in, Indicates the diameter of the equivalent circle. Represents the actual physical area. This represents the pre-confirmed value of pi.

[0040] Understandably, the maximum pore diameter is the largest of the multiple equivalent circle diameters. The minimum pore diameter is the smallest of the multiple equivalent circle diameters.

[0041] It should be explained that the method of obtaining capillary tortuosity by utilizing multiple interconnected pore regions includes: Multiple distance-transformed images are obtained using the multiple interconnected pore regions; Perform the following operation on each of the multiple distance-transformed images: The center pixel of the distance-transformed image is extracted to obtain multiple candidate centerline pixels; The target centerline is obtained by connecting and correcting multiple candidate pixels for the centerline. The target centerline is divided into multiple discrete curves by equal intervals. Obtain multiple arc lengths of multiple discrete curves, where each arc length corresponds one-to-one with a discrete curve; Multiple line segment lengths are obtained using multiple discrete curves, where each line segment length corresponds one-to-one with a discrete curve. Calculate multiple local curvature rates using multiple curve arc lengths and multiple line segment lengths; Calculate the local capillary tortuosity using multiple local tortuosities; By summarizing the aforementioned local capillary tortuosities, multiple local capillary tortuosities are obtained; The capillary tortuosity is calculated using multiple local capillary tortuosities.

[0042] Furthermore, the step of acquiring multiple distance-transformed images using the multiple interconnected pore regions includes: For each of the multiple pore connectivity regions, perform the following operation: Constructing connected region images based on pore connected regions; Extracting pixels from multiple connected regions based on connected region images; Multiple boundary pixels were identified using the connected component image; Perform the following operation on each of the connected region pixels in a plurality of connected region pixels; Calculate multiple Euclidean distances using connected region pixels and multiple boundary pixels; Obtain distance change values ​​using multiple Euclidean distances; By summing the distance change values, multiple distance change values ​​are obtained; Construct a distance transformation matrix using multiple distance change values; The distance transformation matrix is ​​used to obtain the distance transformation image; By summing the distance-transformed images, multiple distance-transformed images are obtained.

[0043] Understandably, a connected region image is a binary image corresponding to a porous connected region. Pixels belonging to the same porous connected region have a grayscale value of 0, while pixels not belonging to the same region have a grayscale value of 255. A connected region pixel is a pixel in the connected region image that belongs to the porous connected region corresponding to that region. These pixels represent the spatial location within the porous connected region, and each pixel has corresponding pixel coordinates, which are the coordinates of the pixel in an image coordinate system constructed based on the connected region image. Boundary pixels are pixels located at the edges of the porous connected region. Euclidean distance is a distance parameter representing the spatial distance between two pixels. The calculation method for Euclidean distance is existing technology and will not be elaborated here. The distance change value is the smallest Euclidean distance among multiple distances, representing the distance of a connected region pixel from the porous boundary. A larger distance change value indicates that the connected region pixel is farther from the boundary of the porous connected region and closer to the center of the region. The distance transformation matrix is ​​a matrix formed by arranging the distance change values ​​corresponding to pixels in multiple connected regions according to their pixel positions in the connected region image. Each element in the distance transformation matrix corresponds to a pixel position and stores the distance change value corresponding to that position. The distance transformation image is an image generated based on the distance transformation matrix to represent the distance distribution of the pore connected regions. The pixel grayscale values ​​in the distance transformation image are related to the distance change values ​​at corresponding positions, and are used to intuitively characterize the distances between different positions within the pore connected regions and the pore boundaries.

[0044] Furthermore, center pixel extraction is a process of identifying the central pixel within the aperture connectivity region based on the distance change value in the distance-transformed image. Specifically, for each pixel in the distance-transformed image, the distance change value corresponding to that pixel is obtained, and the distance change values ​​corresponding to multiple adjacent pixels within a preset pixel neighborhood are also obtained. The distance change value corresponding to the pixel is compared with the distance change values ​​corresponding to the multiple adjacent pixels. When the distance change value corresponding to the pixel is greater than or equal to the distance change values ​​corresponding to its adjacent pixels, the pixel is determined as a candidate pixel for the center line. These candidate pixels are then aggregated to obtain multiple candidate pixels for the center line. The pixel neighborhood is a 3×3 area centered on a pixel in the distance-transformed image, where the pixel at the center is the pixel to be detected, and the remaining pixels are adjacent pixels. Centerline candidate pixels are pixels extracted from center pixels. A larger distance variation value for a centerline candidate pixel indicates that the pixel is far from the pore boundary and located in the central region of the pore cross-section, reflecting the main connectivity direction inside the capillary. Connection correction is a process of optimizing and adjusting the connection relationship between multiple centerline candidate pixels. Specifically, broken or isolated centerline candidate pixels are connected or deleted to form a continuous path. The target centerline is the path composed of multiple centerline candidate pixels after connection correction. Equidistant splitting is the process of splitting the target centerline according to a preset splitting interval. Specifically, along the target centerline, the continuous target centerline is divided into multiple independent curve segments according to the splitting interval, which can be set to 2 pixels. Discrete curves are local curve segments of the target centerline obtained after equidistant splitting. Curve arc length is the length of the discrete curve, representing the sum of the path lengths between adjacent pixels along the discrete curve direction. Optionally, Euclidean distance is used as the path length. The calculation method for Euclidean distance is existing technology and will not be elaborated here.

[0045] Understandably, a continuous line segment is the line segment obtained by connecting the first and last pixels of a discrete curve. The segment length is the length of the continuous line segment, calculated using the Euclidean distance between the coordinates of the first and last pixels of the discrete curve. Local curvature is a parameter used to characterize the degree of curvature of the discrete curve, where the local curvature is the value obtained by dividing the arc length of the corresponding curve by the corresponding line segment length. Local capillary curvature is the average of multiple local curvatures, used to characterize the degree of curvature of the capillaries within the pore connectivity region. Capillary curvature is the average of multiple local capillary curvatures, used to characterize the overall capillary curvature of the core sample.

[0046] It should be explained that the calculation of theoretical permeability using porosity, measured capillary tortuosity, measured core particle diameter, and measured fractal dimension includes: The theoretical maximum pore diameter was calculated using porosity and measured core particle diameter. The theoretical minimum pore diameter is calculated using the measured fractal dimension and the theoretical maximum pore diameter. The theoretical permeability is calculated using the theoretical maximum pore diameter, the theoretical minimum pore diameter, the measured capillary tortuosity, and the measured fractal dimension. The formula for calculating the theoretical permeability is shown below:

[0047] in, Indicates theoretical penetration rate. Indicates porosity. Represents the measured fractal dimension. This represents the measured capillary tortuosity. Indicates the theoretical maximum pore diameter. This represents the theoretical minimum pore diameter.

[0048] Furthermore, the theoretical maximum pore diameter is the diameter of the equivalent circle used to characterize the largest pore inside the core sample, calculated based on porosity and measured core grain diameter. The theoretical minimum pore diameter is the diameter of the equivalent circle used to characterize the smallest pore inside the core sample, calculated based on measured fractal dimension and the theoretical maximum pore diameter. The formula for calculating the theoretical minimum pore diameter is as follows:

[0049] Understandably, theoretical permeability is calculated based on porosity, theoretical maximum pore diameter, theoretical minimum pore diameter, measured capillary tortuosity, and measured fractal dimension to characterize the permeability of a core sample when it is not affected by external pressure.

[0050] It should be explained that the formula for calculating the theoretical maximum pore diameter is as follows:

[0051] in, This indicates the measured diameter of the core particles. This represents the pre-confirmed value of pi.

[0052] S3. Perform stress sensitivity testing on the core sample to obtain the stress sensitivity coefficient.

[0053] It should be explained that the stress sensitivity test of the core sample to obtain the stress sensitivity coefficient includes: Set multiple test confining pressure values; For each of the multiple test confining pressure values, perform the following operation: Based on the test confining pressure value and the core sample, pressure is applied to obtain a compressed core sample; The permeability of the compressed core sample was measured to obtain the test permeability. By summing up the aforementioned test penetration rates, multiple test penetration rates are obtained; A permeability variation curve was constructed using multiple permeability tests and multiple confining pressure values. The stress sensitivity coefficient is obtained using the permeability change curve.

[0054] Furthermore, the test confining pressure value is used to simulate the external stress exerted on the rock in the gas storage reservoir. The test confining pressure value can be set according to the actual operating pressure range of the gas storage reservoir, for example, 5 MPa, 10 MPa, 15 MPa, and 20 MPa. Applying pressure is the process of applying external pressure to the core sample based on the test confining pressure value. Specifically, a pressure loading device is used to apply the pressure corresponding to the test confining pressure value to the core sample, placing the core sample under the corresponding pressure conditions. Optionally, a loading test machine is used as the pressure loading device. The pressure-loaded core sample is the core sample after pressure loading has been completed under the test confining pressure value. The test permeability is a seepage capacity parameter obtained by permeability testing of the pressure-loaded core sample under the corresponding test confining pressure value. The test permeability corresponds one-to-one with the test confining pressure value and is used to characterize the permeability change of the core sample under different pressure conditions. The permeability variation curve is a curve constructed based on multiple test confining pressure values ​​and multiple test permeabilities to describe the influence of confining pressure changes on the permeability of the core sample. The horizontal axis of the permeability variation curve represents the test confining pressure value, and the vertical axis represents the test permeability at the corresponding test confining pressure value. The stress sensitivity coefficient is a parameter calculated from the permeability variation curve to characterize the change in permeability of the core sample with the test confining pressure value. Optionally, the nonlinear least squares method is used as the method for obtaining the stress sensitivity coefficient.

[0055] S4. Obtain the historical operating parameter set of the gas storage facility based on the data acquisition window within the prediction time window. The historical operating parameter set includes the steam injection sequence, gas production sequence, flow pressure sequence, and historical reservoir pressure sequence.

[0056] It should be explained that the historical operating parameter set is a collection including steam injection volume sequence, gas production volume sequence, flow pressure sequence, and historical reservoir pressure sequence. This historical operating parameter set can be obtained from the historical production records of the gas storage facility, and will not be elaborated further here. The steam injection volume sequence is a sequence formed by arranging the steam injection volumes corresponding to multiple sampling time points in chronological order, where each steam injection volume corresponds to one sampling time point. The steam injection volume is the volume of natural gas injected into the reservoir by the gas storage facility per unit time during the injection process. This steam injection volume can be obtained using a flow meter installed on the injection pipeline. The sampling time point is the time at which various operating parameters (steam injection volume, gas production volume, flow pressure, and fluid temperature) are recorded. The gas production volume sequence is a sequence formed by arranging the gas production volumes corresponding to multiple sampling time points in chronological order, where each gas production volume corresponds to one sampling time point. The gas production volume is the volume of natural gas extracted from the reservoir by the gas storage facility per unit time during the gas production process. This gas production volume can be obtained using a flow meter installed on the gas production pipeline. The flowing pressure sequence is a sequence formed by arranging the flowing pressures corresponding to multiple sampling time points in chronological order, where each flowing pressure corresponds to one sampling time point. The flowing pressure is the pressure value at the bottom of the gas well under the flow state during the gas production and injection process of the gas storage facility, used to characterize the pressure changes of the gas well under gas flow conditions. The flowing pressure can be obtained by pressure sensors installed downhole in the gas storage well. The historical reservoir pressure sequence is a sequence formed by arranging the historical reservoir pressures corresponding to multiple sampling time points in chronological order, where each historical reservoir pressure corresponds to one sampling time point. The historical reservoir pressure is the pressure value of natural gas within the pore space of the gas storage reservoir.

[0057] S5. Preprocess the historical operating parameter set to obtain a standardized historical operating parameter set, and use the standardized historical operating parameter set to construct a reservoir pressure prediction model.

[0058] It should be explained that the preprocessing of the historical operating parameter set refers to normalizing the steam injection volume sequence, gas production volume sequence, and flow pressure sequence in the historical operating parameter set, transforming different types of operating parameters into the [0, 1] interval to eliminate the impact of dimensional differences between different parameters on the subsequent reservoir pressure prediction model training process. Optionally, Min-Max normalization can be used as the normalization method. The standardized historical operating parameter set is the preprocessed historical operating parameter set, which includes the normalized steam injection volume sequence, normalized gas production volume sequence, normalized flow pressure sequence, and historical reservoir pressure sequence. The normalized steam injection volume sequence is the normalized steam injection volume sequence. The normalized gas production volume sequence is the normalized gas production volume sequence. The normalized flow pressure sequence is the normalized flow pressure sequence.

[0059] Understandably, constructing a reservoir pressure prediction model using the standardized historical operating parameter set refers to using the normalized steam injection rate sequence, normalized gas production rate sequence, and normalized flow pressure sequence from the standardized historical operating parameter set as model input, and the historical reservoir pressure sequence corresponding to the standardized historical operating parameter set as model output. This allows the prediction model to learn the mapping relationship between steam injection rate, gas production rate, and flow pressure and historical reservoir pressure. Specifically, the normalized steam injection rate sequence, normalized gas production rate sequence, and normalized flow pressure sequence are combined according to the same corresponding sampling time point to form multiple operating state feature vectors. These multiple operating state feature vectors are then mapped to the historical reservoir pressure at the corresponding sampling time point and input into a pre-constructed time-series prediction model for training. This process continues until the input operating state feature vector composed of steam injection rate, gas production rate, and flow pressure can output the corresponding reservoir pressure, thus obtaining the reservoir pressure prediction model. Optionally, time-series prediction can be used as the training method for the time-series prediction model. The reservoir pressure prediction model is a time-series prediction model that takes the operating state feature vector as input and reservoir pressure as output. The operating state feature vector is a vector obtained by combining the normalized steam injection rate, gas production rate, and flowing pressure at the same moment, for example, [steam injection rate, gas production rate, flowing pressure].

[0060] S6. Obtain the target operating parameter set based on the parameter prediction window, input the target operating parameter set into the reservoir pressure prediction model, and obtain the target reservoir pressure sequence, wherein the target reservoir pressure sequence includes multiple target reservoir pressures.

[0061] It should be explained that the target operating parameter set is a collection of operating parameters obtained based on the parameter prediction window for predicting reservoir pressure changes. This target operating parameter set includes target steam injection rate sequences, target gas production rate sequences, and target flow pressure sequences corresponding to multiple sampling time points within the parameter prediction window. The target steam injection rate sequence, target gas production rate sequence, and target flow pressure sequence are respectively the steam injection rate sequence, gas production rate sequence, and flow pressure sequence within the parameter prediction. The target reservoir pressure sequence is a sequence of reservoir pressures predicted by the reservoir pressure prediction model based on the target operating parameter set, corresponding one-to-one with multiple sampling time points within the parameter prediction window. The target reservoir pressure sequence includes multiple target reservoir pressures.

[0062] S7. Correct the initial permeability using the target reservoir pressure sequence and stress sensitivity coefficient to obtain the corrected permeability sequence. Extract the target flowing pressure sequence based on the target operating parameter set. Obtain the reservoir seepage capacity sequence using the target reservoir pressure sequence, target flowing pressure sequence and corrected permeability sequence. Evaluate the reservoir capacity based on the reservoir seepage capacity sequence to obtain the reservoir capacity evaluation result.

[0063] It should be explained that the step of correcting the initial permeability using the target reservoir pressure sequence and stress sensitivity coefficient to obtain the corrected permeability sequence includes: Initial reservoir pressure is extracted based on historical reservoir pressure sequences; For each target reservoir pressure in the target reservoir pressure sequence, the following operation is performed: Calculate the pressure change using the target reservoir pressure and the initial reservoir pressure; The permeability correction factor is calculated using the pressure change and stress sensitivity coefficient. Calculate the corrected permeability using the permeability correction factor and the initial permeability; By summing the corrected permeability rates, a corrected permeability rate sequence is obtained.

[0064] Furthermore, the initial reservoir pressure is the last historical reservoir pressure in the historical reservoir pressure sequence, used as a benchmark for comparing reservoir pressure changes within subsequent prediction time windows. The pressure change is the difference between the target reservoir pressure and the initial reservoir pressure. The permeability correction coefficient is a parameter calculated based on the pressure change and the stress sensitivity coefficient, used to characterize the impact of reservoir pressure changes on permeability. The formula for calculating the permeability correction coefficient is as follows:

[0065] in, This represents the permeability correction factor. Represents a power function. Represents the stress sensitivity coefficient. This indicates the change in pressure.

[0066] Understandably, the corrected permeability is the reservoir permeability corresponding to the target reservoir pressure, obtained by dynamically adjusting the initial permeability using a permeability correction coefficient. The corrected permeability is the product of the permeability correction coefficient and the initial permeability. The corrected permeability sequence is obtained by arranging multiple corrected permeabilities according to the order of multiple target reservoir pressures in the corresponding target reservoir pressure sequence.

[0067] Furthermore, obtaining the reservoir permeability sequence using the target reservoir pressure sequence, target flowing pressure sequence, and corrected permeability sequence refers to calculating the reservoir pressure differential sequence using the target reservoir pressure sequence and target flowing pressure sequence, and calculating the reservoir permeability sequence using the reservoir pressure differential sequence and corrected permeability sequence. The reservoir pressure differential sequence is a sequence composed of the difference between the target reservoir pressure and the target flowing pressure at the corresponding sampling time in the target reservoir pressure sequence and target flowing pressure sequence. The reservoir permeability sequence is a sequence containing multiple reservoir permeability parameters. These parameters are calculated based on the reservoir pressure differential and corrected permeability at the predicted time point and are used to characterize the reservoir's permeability. A higher reservoir permeability indicates a stronger natural gas flow capacity under the current pressure conditions (the product of the reservoir pressure differential and the corrected permeability).

[0068] It should be explained that the reservoir capacity assessment based on the reservoir permeability sequence to obtain the reservoir capacity assessment result refers to extracting the average reservoir permeability from the reservoir permeability sequence and comparing the average reservoir permeability with a preset permeability evaluation threshold: if the average reservoir permeability is greater than or equal to the permeability evaluation threshold, then the preset permeability is qualified as the reservoir capacity assessment result; if the average reservoir permeability is less than the permeability evaluation threshold, then the preset permeability is insufficient as the reservoir capacity assessment result.

[0069] Furthermore, the average reservoir permeability is the average of the permeability of multiple reservoirs in the reservoir permeability sequence. The permeability evaluation threshold is a critical value used to determine whether the reservoir permeability within the prediction time window meets the requirements for stable operation. This threshold can be determined based on the reservoir permeability corresponding to historical stable operation phases of the gas storage facility. For example, the reservoir permeability corresponding to multiple time points during the historical stable operation phase of the gas storage facility can be obtained, the historical average reservoir permeability can be calculated, and a preset proportion (e.g., 80%) of the historical average reservoir permeability can be used as the permeability evaluation threshold. A satisfactory permeability is an assessment result indicating that the permeability level formed under the combined effect of reservoir pressure driving force and reservoir permeability within the prediction time window meets the operational requirements of the gas storage facility. Insufficient permeability is an assessment result indicating that a decrease in reservoir pressure driving force, a decrease in permeability, or a combination of both within the prediction time window results in the overall reservoir permeability being lower than the operational requirements.

[0070] To address the problems described in the background art, this invention receives dynamic prediction commands and determines a dynamic prediction environment based on these commands. The dynamic prediction environment includes a gas storage facility and a prediction time window, which comprises a data acquisition window and a parameter prediction window. Core samples are acquired from the gas storage facility, and permeability is measured to obtain an initial permeability. Thus, this invention, by determining the prediction time window of the gas storage facility and acquiring the initial permeability of the core samples, accurately obtains the basic seepage characteristics of the reservoir, providing a basis for subsequent dynamic permeability correction based on pressure changes. Furthermore, this invention performs stress sensitivity testing on the core samples to obtain a stress sensitivity coefficient. This invention, by acquiring the permeability change characteristics of the core samples under different pressures, obtains a stress sensitivity coefficient characterizing the impact of reservoir pressure changes on permeability, providing a basis for subsequent dynamic permeability correction based on predicted reservoir pressure. Subsequently, this invention obtains the historical operating parameter set of the gas storage facility through a data acquisition window based on the prediction time window. The historical operating parameter set includes the steam injection rate sequence, gas production rate sequence, flow pressure sequence, and historical reservoir pressure sequence. The historical operating parameter set is preprocessed to obtain a standardized historical operating parameter set. It can be seen that the embodiments of this invention obtain a historical operating parameter set containing information on gas injection and production processes and reservoir pressure changes, and standardize different types of operating parameters to reduce the impact of parameter dimension differences on the subsequent model training process, thus providing a unified data foundation for establishing a reservoir pressure prediction model. Then, the present invention constructs a reservoir pressure prediction model using the standardized historical operating parameter set, obtains a target operating parameter set based on the parameter prediction window, and inputs the target operating parameter set into the reservoir pressure prediction model to obtain a target reservoir pressure sequence. The target reservoir pressure sequence includes multiple target reservoir pressures. It can be seen that the embodiments of the present invention establish a reservoir pressure prediction model based on historical operating parameters and dynamically predict the reservoir pressure using operating parameters within the future prediction time window to obtain target reservoir pressures corresponding to multiple time points. This enables the early acquisition of the future reservoir pressure change trend of the gas storage facility, providing data basis for subsequent permeability correction and reservoir seepage capacity assessment based on pressure changes. Furthermore, this invention corrects the initial permeability using the target reservoir pressure sequence and stress sensitivity coefficient to obtain a corrected permeability sequence. It then extracts the target flow pressure sequence based on the target operating parameter set. Finally, it obtains the reservoir flow capacity sequence using the target reservoir pressure sequence, target flow pressure sequence, and corrected permeability sequence. Based on this flow capacity sequence, it performs reservoir capacity assessment to obtain the reservoir capacity assessment result. It is evident that this embodiment of the invention dynamically corrects the permeability by combining the predicted reservoir pressure changes and stress sensitivity characteristics, avoiding deviations in reservoir state characterization caused by a fixed permeability. Furthermore, by comprehensively considering reservoir pressure, flow pressure, and corrected permeability to obtain the reservoir flow capacity sequence, it achieves an accurate assessment of the future reservoir flow capacity changes in a gas storage facility.Therefore, the present invention can improve the accuracy of identifying the trend of changes in reservoir permeability.

[0071] like Figure 2 The diagram shown is a functional block diagram of a dynamic prediction system for gas storage reservoir parameters provided in an embodiment of the present invention.

[0072] The dynamic prediction system 100 for gas storage reservoir parameters of this invention can be installed in an electronic device. Depending on the functions implemented, the dynamic prediction system 100 may include an initial parameter calculation module 101, an operating parameter processing module 102, a prediction model construction module 103, and a reservoir capacity assessment module 104. The module described in this invention can also be called a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, and which are stored in the memory of the electronic device.

[0073] The initial parameter calculation module 101 is used to receive dynamic prediction instructions and determine the dynamic prediction environment according to the dynamic prediction instructions. The dynamic prediction environment includes a gas storage facility and a prediction time window. The prediction time window includes a data acquisition window and a parameter prediction window. Based on core samples obtained from the gas storage facility, the permeability of the core samples was measured to obtain the initial permeability; Stress sensitivity tests were performed on the core samples to obtain the stress sensitivity coefficient; The operating parameter processing module 102 is used to obtain the historical operating parameter set of the gas storage based on the data acquisition window in the prediction time window. The historical operating parameter set includes the steam injection sequence, gas production sequence, flow pressure sequence and historical reservoir pressure sequence. Preprocess the historical operating parameter set to obtain a standardized historical operating parameter set; The prediction model construction module 103 is used to construct a reservoir pressure prediction model using the standardized historical operating parameter set. The reservoir capacity assessment module 104 is used to obtain a target operating parameter set based on the parameter prediction window, input the target operating parameter set into the reservoir pressure prediction model, and obtain a target reservoir pressure sequence, wherein the target reservoir pressure sequence includes multiple target reservoir pressures. The initial permeability was corrected using the target reservoir pressure sequence and stress sensitivity coefficient to obtain the corrected permeability sequence; Extract the target flow pressure sequence based on the target operating parameter set; The reservoir permeability sequence is obtained by using the target reservoir pressure sequence, target flowing pressure sequence and modified permeability sequence. The reservoir capacity is then assessed based on the reservoir permeability sequence to obtain the reservoir capacity assessment results.

[0074] In detail, the modules in the dynamic prediction system 100 for gas storage reservoir parameters described in this embodiment of the invention employ the same methods as described above. Figure 1 The method used here is the same as the dynamic prediction method for gas storage reservoir parameters described above, and it can produce the same technical effect, so it will not be elaborated here.

[0075] like Figure 3 The diagram shown is a schematic diagram of an electronic device for implementing a dynamic prediction method for gas storage reservoir parameters according to an embodiment of the present invention.

[0076] The electronic device 1 may include a processor 10, a memory 11 and a bus 12, and may also include a computer program stored in the memory 11 and capable of running on the processor 10, such as a dynamic prediction method program for gas storage reservoir parameters.

[0077] The memory 11 includes at least one type of readable storage medium, such as flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of the electronic device 1, such as the portable hard drive of the electronic device 1. In other embodiments, the memory 11 can be an external storage device of the electronic device 1, such as a plug-in portable hard drive, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the electronic device 1. Furthermore, the memory 11 includes both internal storage units and external storage devices of the electronic device 1. The memory 11 can be used not only to store application software and various types of data installed on the electronic device 1, such as the code of a dynamic prediction method program for gas storage reservoir parameters, but also to temporarily store data that has been output or will be output.

[0078] In some embodiments, the processor 10 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control unit of the electronic device, connecting various components of the entire electronic device through various interfaces and lines. It executes programs or modules stored in the memory 11 (such as a dynamic prediction method program for gas storage reservoir parameters) and calls data stored in the memory 11 to perform various functions of the electronic device 1 and process data.

[0079] The bus 12 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus 12 can be divided into an address bus, a data bus, a control bus, etc. The bus 12 is configured to realize the connection and communication between the memory 11 and at least one processor 10, etc.

[0080] Figure 3 Only electronic devices with components are shown; it will be understood by those skilled in the art that... Figure 3 The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0081] For example, although not shown, the electronic device 1 may also include a power supply (such as a battery) to power the various components. Preferably, the power supply can be logically connected to the at least one processor 10 through a power management device, thereby enabling functions such as charging management, discharging management, and power consumption management. The power supply may also include one or more DC or AC power supplies, recharging devices, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device 1 may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0082] Furthermore, the electronic device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a Wi-Fi interface, a Bluetooth interface, etc.), which is typically used to establish communication connections between the electronic device 1 and other electronic devices.

[0083] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), and optionally, a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen, etc. The display may also be appropriately referred to as a screen or display unit, used to display information processed in the electronic device 1 and to display a visual user interface.

[0084] The dynamic prediction method program for gas storage reservoir parameters stored in the memory 11 of the electronic device 1 is a combination of multiple instructions. When run in the processor 10, it can achieve the following: Receive dynamic prediction instructions and determine the dynamic prediction environment based on the dynamic prediction instructions. The dynamic prediction environment includes the gas storage facility and the prediction time window. The prediction time window includes the data acquisition window and the parameter prediction window. Based on core samples obtained from the gas storage facility, the permeability of the core samples was measured to obtain the initial permeability; Stress sensitivity tests were performed on the core samples to obtain the stress sensitivity coefficient; The historical operating parameter set of the gas storage facility is obtained based on the data acquisition window within the prediction time window. The historical operating parameter set includes the steam injection sequence, gas production sequence, flow pressure sequence, and historical reservoir pressure sequence. Preprocess the historical operating parameter set to obtain a standardized historical operating parameter set; A reservoir pressure prediction model is constructed using the standardized historical operating parameter set. The target operating parameter set is obtained based on the parameter prediction window, and the target operating parameter set is input into the reservoir pressure prediction model to obtain the target reservoir pressure sequence, wherein the target reservoir pressure sequence includes multiple target reservoir pressures; The initial permeability was corrected using the target reservoir pressure sequence and stress sensitivity coefficient to obtain the corrected permeability sequence; Extract the target flow pressure sequence based on the target operating parameter set; The reservoir permeability sequence is obtained by using the target reservoir pressure sequence, target flowing pressure sequence and modified permeability sequence. The reservoir capacity is then assessed based on the reservoir permeability sequence to obtain the reservoir capacity assessment results.

[0085] Specifically, the processor 10's implementation method for the above instructions can be found in [reference needed]. Figures 1 to 3 The descriptions of the relevant steps in the corresponding embodiments are not repeated here.

[0086] Furthermore, if the modules / units integrated in the electronic device 1 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).

[0087] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor of an electronic device, can perform the following: Receive dynamic prediction instructions and determine the dynamic prediction environment based on the dynamic prediction instructions. The dynamic prediction environment includes the gas storage facility and the prediction time window. The prediction time window includes the data acquisition window and the parameter prediction window. Based on core samples obtained from the gas storage facility, the permeability of the core samples was measured to obtain the initial permeability; Stress sensitivity tests were performed on the core samples to obtain the stress sensitivity coefficient; The historical operating parameter set of the gas storage facility is obtained based on the data acquisition window within the prediction time window. The historical operating parameter set includes the steam injection sequence, gas production sequence, flow pressure sequence, and historical reservoir pressure sequence. Preprocess the historical operating parameter set to obtain a standardized historical operating parameter set; A reservoir pressure prediction model is constructed using the standardized historical operating parameter set. The target operating parameter set is obtained based on the parameter prediction window, and the target operating parameter set is input into the reservoir pressure prediction model to obtain the target reservoir pressure sequence, wherein the target reservoir pressure sequence includes multiple target reservoir pressures; The initial permeability was corrected using the target reservoir pressure sequence and stress sensitivity coefficient to obtain the corrected permeability sequence; Extract the target flow pressure sequence based on the target operating parameter set; The reservoir permeability sequence is obtained by using the target reservoir pressure sequence, target flowing pressure sequence and modified permeability sequence. The reservoir capacity is then assessed based on the reservoir permeability sequence to obtain the reservoir capacity assessment results.

[0088] In the embodiments provided by this invention, it should be understood that the disclosed devices, systems, and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative, and actual implementations may have other classification methods.

[0089] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0090] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0091] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0092] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for dynamic prediction of reservoir parameters in a gas storage facility, characterized in that, The method includes: Receive dynamic prediction instructions and determine the dynamic prediction environment based on the dynamic prediction instructions. The dynamic prediction environment includes the gas storage facility and the prediction time window. The prediction time window includes the data acquisition window and the parameter prediction window. Based on core samples obtained from the gas storage facility, the permeability of the core samples was measured to obtain the initial permeability; Stress sensitivity tests were performed on the core samples to obtain the stress sensitivity coefficient; The historical operating parameter set of the gas storage facility is obtained based on the data acquisition window within the prediction time window. The historical operating parameter set includes the steam injection sequence, gas production sequence, flow pressure sequence, and historical reservoir pressure sequence. The historical operating parameter set is preprocessed to obtain a standardized historical operating parameter set; A reservoir pressure prediction model is constructed using the standardized historical operating parameter set. The target operating parameter set is obtained based on the parameter prediction window, and the target operating parameter set is input into the reservoir pressure prediction model to obtain the target reservoir pressure sequence, wherein the target reservoir pressure sequence includes multiple target reservoir pressures; The initial permeability was corrected using the target reservoir pressure sequence and stress sensitivity coefficient to obtain the corrected permeability sequence; Extract the target flow pressure sequence based on the target operating parameter set; The reservoir permeability sequence is obtained by using the target reservoir pressure sequence, target flowing pressure sequence and modified permeability sequence. The reservoir capacity is then assessed based on the reservoir permeability sequence to obtain the reservoir capacity assessment results.

2. The method for dynamic prediction of gas storage reservoir parameters as described in claim 1, characterized in that, The process of permeability testing of the core sample to obtain the initial permeability includes: The core samples were standardized to obtain standard core samples. Porosity was determined by testing the porosity of standard core samples. The standard core sample was cut at equal intervals to obtain multiple core samples. Perform the following operation on each of the multiple core samples: Microstructure images of core samples were obtained using pre-confirmed electron microscopy. The core particle diameter, capillary tortuosity, maximum pore diameter, and minimum pore diameter are obtained using the microstructure images. The fractal dimension is calculated using the porosity, maximum pore diameter, and minimum pore diameter. By summarizing the maximum pore diameter, minimum pore diameter, capillary tortuosity, core particle diameter, and fractal dimension, multiple maximum pore diameters, multiple minimum pore diameters, multiple capillary tortuosities, multiple core particle diameters, and multiple fractal dimensions are obtained. The measured maximum pore diameter, measured capillary tortuosity, measured core particle diameter, and measured fractal dimension are obtained by using the multiple maximum pore diameters, multiple minimum pore diameters, multiple capillary tortuosities, multiple core particle diameters, and multiple fractal dimensions. The measured permeability is calculated using the porosity, measured fractal dimension, measured maximum pore diameter, measured capillary tortuosity, and measured core particle diameter. The theoretical permeability was calculated using porosity, measured capillary tortuosity, measured core particle diameter, and measured fractal dimension. The initial permeability is calculated using theoretical and measured permeability.

3. The method for dynamic prediction of gas storage reservoir parameters as described in claim 2, characterized in that, The process of obtaining core particle diameter, capillary tortuosity, maximum pore diameter, and minimum pore diameter using the microstructure image includes: The microstructure image is converted to grayscale to obtain a grayscale image; The grayscale image is preprocessed and filtered to obtain a denoised grayscale image; The denoised grayscale image is subjected to binary segmentation to obtain a binarized image; Connectivity analysis was performed on the binarized image to obtain multiple pore connected regions and multiple core particle regions; Capillary tortuosity is obtained by utilizing multiple interconnected pore regions. For each of the multiple pore connectivity regions, perform the following operation: Obtain the pixel area of ​​the connected region of the aperture; The actual physical area is obtained based on the pre-confirmed scale and pixel area. Construct an equivalent circle using the actual physical area, and obtain the diameter of the equivalent circle. By summing up the equivalent circle diameters, multiple equivalent circle diameters are obtained; The maximum and minimum pore diameters were determined based on multiple equivalent circle diameters; Core particle diameters were obtained using multiple core particle regions.

4. The method for dynamic prediction of gas storage reservoir parameters as described in claim 3, characterized in that, The method of obtaining capillary tortuosity using multiple interconnected pore regions includes: Multiple distance-transformed images are obtained using the multiple interconnected pore regions; Perform the following operation on each of the multiple distance-transformed images: The center pixel of the distance-transformed image is extracted to obtain multiple candidate centerline pixels; The target centerline is obtained by connecting and correcting multiple candidate pixels for the centerline. The target centerline is divided into multiple discrete curves by equal intervals. Obtain multiple arc lengths of multiple discrete curves, where each arc length corresponds one-to-one with a discrete curve; Multiple line segment lengths are obtained using multiple discrete curves, where each line segment length corresponds one-to-one with a discrete curve. Calculate multiple local curvature rates using multiple curve arc lengths and multiple line segment lengths; Calculate the local capillary tortuosity using multiple local tortuosities; By summarizing the aforementioned local capillary tortuosities, multiple local capillary tortuosities are obtained; The capillary tortuosity is calculated using multiple local capillary tortuosities.

5. The method for dynamic prediction of gas storage reservoir parameters as described in claim 4, characterized in that, The method of acquiring multiple distance-transformed images using the multiple interconnected regions of pores includes: For each of the multiple pore connectivity regions, perform the following operation: Constructing connected region images based on pore connected regions; Extracting pixels from multiple connected regions based on connected region images; Multiple boundary pixels were identified using the connected component image; Perform the following operation on each of the connected region pixels in a plurality of connected region pixels; Calculate multiple Euclidean distances using connected region pixels and multiple boundary pixels; Obtain distance change values ​​using multiple Euclidean distances; By summing the distance change values, multiple distance change values ​​are obtained; Construct a distance transformation matrix using multiple distance change values; The distance transformation matrix is ​​used to obtain the distance transformation image; By summing the distance-transformed images, multiple distance-transformed images are obtained.

6. The method for dynamic prediction of gas storage reservoir parameters as described in claim 5, characterized in that, The calculation of theoretical permeability using porosity, measured capillary tortuosity, measured core particle diameter, and measured fractal dimension includes: The theoretical maximum pore diameter was calculated using porosity and measured core particle diameter. The theoretical minimum pore diameter is calculated using the measured fractal dimension and the theoretical maximum pore diameter. The theoretical permeability is calculated using the theoretical maximum pore diameter, the theoretical minimum pore diameter, the measured capillary tortuosity, and the measured fractal dimension. The formula for calculating the theoretical permeability is shown below: ； in, Indicates theoretical penetration rate. Indicates porosity. Represents the measured fractal dimension. This represents the measured capillary tortuosity. Indicates the theoretical maximum pore diameter. This represents the theoretical minimum pore diameter.

7. The method for dynamic prediction of gas storage reservoir parameters as described in claim 6, characterized in that, The formula for calculating the theoretical maximum pore diameter is as follows: ； in, This indicates the measured diameter of the core particles. This represents the pre-confirmed value of pi.

8. The method for dynamic prediction of gas storage reservoir parameters as described in claim 7, characterized in that, The stress sensitivity test of the core sample to obtain the stress sensitivity coefficient includes: Set multiple test confining pressure values; For each of the multiple test confining pressure values, perform the following operation: Based on the test confining pressure value and the core sample, pressure is applied to obtain a compressed core sample; The permeability of the compressed rock core sample was measured to obtain the test permeability. By summing up the aforementioned test penetration rates, multiple test penetration rates are obtained; A permeability variation curve was constructed using multiple permeability tests and multiple confining pressure values. The stress sensitivity coefficient is obtained using the permeability change curve.

9. The method for dynamic prediction of gas storage reservoir parameters as described in claim 8, characterized in that, The process of correcting the initial permeability using the target reservoir pressure sequence and stress sensitivity coefficient to obtain a corrected permeability sequence includes: Initial reservoir pressure is extracted based on historical reservoir pressure sequences; For each target reservoir pressure in the target reservoir pressure sequence, the following operation is performed: Calculate the pressure change using the target reservoir pressure and the initial reservoir pressure; The permeability correction factor is calculated using the pressure change and stress sensitivity coefficient. Calculate the corrected permeability using the permeability correction factor and the initial permeability; By summing the corrected permeability rates, a corrected permeability rate sequence is obtained.

10. A dynamic prediction system for gas storage reservoir parameters, characterized in that, The system includes: The initial parameter calculation module is used to receive dynamic prediction instructions and determine the dynamic prediction environment based on the dynamic prediction instructions. The dynamic prediction environment includes the gas storage facility and the prediction time window, which includes the data acquisition window and the parameter prediction window. Based on core samples obtained from the gas storage facility, the permeability of the core samples was measured to obtain the initial permeability; Stress sensitivity tests were performed on the core samples to obtain the stress sensitivity coefficient; The operation parameter processing module is used to obtain the historical operation parameter set of the gas storage based on the data acquisition window in the prediction time window. The historical operation parameter set includes the steam injection sequence, gas production sequence, flow pressure sequence and historical reservoir pressure sequence. The historical operating parameter set is preprocessed to obtain a standardized historical operating parameter set; The prediction model building module is used to build a reservoir pressure prediction model using the standardized historical operating parameter set. The reservoir capacity assessment module is used to obtain a target operating parameter set based on the parameter prediction window, input the target operating parameter set into the reservoir pressure prediction model, and obtain a target reservoir pressure sequence, wherein the target reservoir pressure sequence includes multiple target reservoir pressures. The initial permeability was corrected using the target reservoir pressure sequence and stress sensitivity coefficient to obtain the corrected permeability sequence; Extract the target flow pressure sequence based on the target operating parameter set; The reservoir permeability sequence is obtained by using the target reservoir pressure sequence, target flowing pressure sequence and modified permeability sequence. The reservoir capacity is then assessed based on the reservoir permeability sequence to obtain the reservoir capacity assessment results.

Images