Intelligent classification method, device and equipment for residual gas potential area of tight gas reservoir

Abstract

The invention relates to the technical field of exploration and development, in particular to an intelligent classification method, device and equipment for residual gas potential areas of tight gas reservoirs. Comprising the steps of obtaining characteristic factors of a tight gas reservoir, constructing a tight gas reservoir model, and inputting multiple pieces of characteristic data into the tight gas reservoir model to obtain main control factors; the adaptability of various clustering algorithms to the tight gas reservoir is analyzed according to the main control factors, and an optimal clustering algorithm suitable for the tight gas reservoir is selected; and finally, establishing a potential area analysis field of the tight gas reservoir, and dividing the potential area analysis field of the tight gas reservoir through an optimal clustering algorithm. Therefore, a method capable of accurately describing the distribution of the residual gas is established to determine the distribution condition of the residual gas in the gas reservoir, so that the utilization rate and the recovery rate of reserves are improved. And meanwhile, the distribution of the residual gas can be automatically and accurately described, and the distribution condition of the residual gas in the gas reservoir can be determined, so that the requirements of subsequent potential tapping work are met, and the utilization rate and recovery rate of reserves are improved.

Description

Technical Field

[0001] The present specification relates to the field of exploration and development technology, and in particular to a method, device and equipment for intelligently classifying remaining gas potential areas in tight gas reservoirs. Background Art

[0002] In recent years, with the rapid economic development, the demand for energy has increased day by day, and the supply of conventional oil and natural gas resources can no longer meet the demand, resulting in an increase in the external dependence of oil and gas year by year. Energy is becoming the main controlling factor restricting economic development. Therefore, major oil fields have begun to shift the focus of exploration and development to unconventional oil and gas. Unconventional oil and gas reservoirs mainly include: shale oil, shale gas, tight oil, tight gas, coalbed methane and natural gas hydrates. Among them, tight gas has huge resource potential and considerable reserves. In recent years, the proportion of tight gas in the total proven reserves of natural gas has continued to increase, but compared with the amount of tight gas resources, the proven rate is still low, and there is still great growth potential and space. The overall characteristics of tight gas reservoirs are large-area distribution in the plane, multi-layer folding in the vertical direction, and strong reservoir heterogeneity, which often causes uneven formation pressure drop in the middle and late stages of development, and local enrichment of residual gas. Many of the discovered large gas fields are also typical tight sandstone gas fields with low permeability, low porosity, low pressure and strong heterogeneity. The gas well has a limited discharge radius. How to implement the distribution and potential of the remaining gas in the gas reservoir is the basis and key to increasing production and improving the recovery rate in the middle and late stages of tight sandstone gas reservoir development. The accurate characterization of the remaining gas distribution is currently a difficult problem. The present invention provides a method for classifying the remaining gas potential areas in tight gas reservoirs based on machine learning, which has important practical significance for guiding the later evaluation of the preferred areas and well location control, and provides technical and theoretical support for improving the recovery rate in the middle and late stages of gas reservoir development.

[0003] The characteristics of tight gas reservoirs are that there is no clear existence of edge and bottom water, strong reservoir heterogeneity, and complex seepage mechanism. Therefore, the development of tight gas reservoirs requires development characteristics different from those of conventional gas reservoirs. In the later stage of the development process, the distribution of residual gas is affected by many factors, including reservoir physical properties, water saturation, well network layout, well type selection, development time and process measures. Accurately understanding the distribution of residual gas is very important for adjusting well deployment, carrying out potential tapping measures such as plugging holes and layer conversion. Therefore, it is necessary to establish a method that can accurately describe the distribution of residual gas to determine the distribution of residual gas in the gas reservoir to meet the needs of subsequent potential tapping work, thereby improving the utilization rate and recovery rate of reserves. At present, the research on the evaluation of the potential area of ​​residual gas in tight gas reservoirs mainly adopts methods such as geological analysis, dynamic monitoring, gas reservoir engineering and numerical simulation. However, the existing methods are limited by the large range of parameters used. The "production and storage coefficient distribution map" described cannot accurately describe the distribution of residual gas, and the operation process is complicated, and the final judgment criteria are vague.

[0004] Therefore, establishing a method that can accurately describe the distribution of residual gas in order to determine the distribution of residual gas in gas reservoirs is a technical problem that needs to be solved urgently. Summary of the invention

[0005] In order to solve the problems of complicated operation process and vague judgment criteria of tight gas reservoirs in the prior art, the embodiments of this specification provide a method, device and equipment for intelligent classification of remaining gas potential areas in tight gas reservoirs. In order to solve the problem that the conventional "quantitative description method of remaining gas in gas reservoirs" is limited to the large range of parameters used, and the described "production and storage coefficient distribution map" cannot accurately describe the distribution of remaining gas, a method for classifying remaining gas potential areas in tight gas reservoirs based on characteristic factors of tight gas reservoirs is proposed, and a method that can accurately describe the distribution of remaining gas is established, so as to accurately determine the distribution of remaining gas in the gas reservoir. This specification establishes a method for intelligent classification of remaining gas potential areas in tight gas reservoirs to determine the distribution of remaining gas in gas reservoirs to meet the needs of subsequent potential tapping work, thereby improving the utilization rate and recovery rate of reserves.

[0006] The specific technical solutions of the embodiments of this specification are as follows:

[0007] On the one hand, the embodiments of this specification provide a method for intelligently classifying remaining gas potential areas in tight gas reservoirs, the method comprising:

[0008] Acquiring characteristic factors of a tight gas reservoir, wherein the characteristic factors include a plurality of characteristic data;

[0009] Constructing a tight gas reservoir model, and inputting the plurality of characteristic data into the tight gas reservoir model to obtain the main controlling factors of the tight gas reservoir;

[0010] Analyzing the adaptability of multiple clustering algorithms to the tight gas reservoir according to the main controlling factors, and selecting a preferred clustering algorithm suitable for the tight gas reservoir;

[0011] A potential area analysis field of the tight gas reservoir is established based on the main controlling factors, and the potential area analysis field is divided by the preferred clustering algorithm.

[0012] Furthermore, the plurality of characteristic data at least include: reservoir physical property characteristic parameters, production dynamic characteristic parameters, and fracturing operation characteristic parameters.

[0013] Furthermore, the reservoir physical property characteristic parameters at least include porosity, absolute permeability, effective thickness, initial gas saturation, and initial pressure;

[0014] The production dynamic characteristic parameters at least include initial gas saturation, cumulative gas production, open flow, current gas saturation, effective permeability, and formation pressure;

[0015] The characteristic parameters of the fracturing construction include at least Poisson's ratio and brittleness index.

[0016] Furthermore, the plurality of clustering algorithms include K-Means mean clustering, affinity propagation, mean shift, spectral clustering, Ward hierarchical clustering, hierarchical clustering, DBSCAN density clustering, OPTICS clustering, Gaussian mixture clustering and Birch hierarchical clustering.

[0017] Furthermore, analyzing the adaptability of multiple clustering algorithms to the tight gas reservoir based on the main controlling factors further includes:

[0018] Determining the adaptability of each clustering algorithm according to the type, number and data volume of the main controlling factors of the tight gas reservoir;

[0019] If the number of the main controlling factors exceeds 5, it is determined to be high-dimensional data to determine the data volume scale of the main controlling factors;

[0020] If the data volume is larger than the preset threshold, K-Means mean clustering, Ward hierarchical clustering or hierarchical clustering algorithm is used;

[0021] If the data volume is smaller than a preset threshold, a mean shift, mean shift or spectral clustering algorithm is used;

[0022] If the number of the main controlling factors is less than 5, it is judged as low-dimensional data and the Birch hierarchical clustering algorithm is used.

[0023] Furthermore, analyzing the adaptability of multiple clustering algorithms to the tight gas reservoir based on the main controlling factors further includes:

[0024] Extracting part of the data from the main control factors and calculating them using a clustering algorithm with adaptability greater than a preset threshold;

[0025] A clustering result calculated by the clustering algorithm is obtained, and the preferred clustering algorithm is selected according to the clustering result.

[0026] Furthermore, establishing the potential area analysis field of the tight gas reservoir based on the main controlling factors further includes:

[0027] The potential area analysis field includes production potential field, remaining gas reserve field and seepage field;

[0028] Establishing production potential field and remaining gas reserve field based on reservoir physical property characteristic parameters in the main controlling factors;

[0029] A seepage field is established according to the production dynamic characteristic parameters.

[0030] Furthermore, dividing the potential area analysis field by the preferred clustering algorithm further includes:

[0031] Inputting the established production potential field, remaining gas reserve field and seepage field into the preferred clustering algorithm respectively;

[0032] Verifying the data sets in the production potential field, the remaining gas reserve field, and the seepage field, and randomly selecting initial points in the data sets;

[0033] Calculating average values ​​of the production potential field, the remaining gas reserve field, and the seepage field according to the initial point and the preferred clustering algorithm;

[0034] The potential area analysis field is divided according to the average values ​​of the production potential field, the remaining gas reserve field and the seepage field.

[0035] On the other hand, the embodiment of this specification also provides an intelligent classification device for remaining gas potential areas in tight gas reservoirs, the device comprising:

[0036] A feature extraction module is used to obtain feature factors of tight gas reservoirs, wherein the feature factors include a plurality of feature data;

[0037] A model building module, used for building a tight gas reservoir model, inputting the plurality of characteristic data into the tight gas reservoir model to obtain the main controlling factors of the tight gas reservoir;

[0038] An adaptability calculation module, used to analyze the adaptability of multiple clustering algorithms to the tight gas reservoir according to the main control factors, and select a preferred clustering algorithm suitable for the tight gas reservoir;

[0039] The potential area division module is used to establish the potential area analysis field of the tight gas reservoir based on the main controlling factors, and divide the potential area analysis field by using the preferred clustering algorithm.

[0040] On the other hand, an embodiment of the present specification further provides a computer device, including a memory, a processor, and a computer program stored in the memory, and the processor implements the above method when executing the computer program.

[0041] On the other hand, an embodiment of the present specification further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program implements the above method when executed by a processor.

[0042] Finally, the embodiments of this specification also provide a computer program product, wherein the computer program product includes a computer program, and the computer program implements the above method when executed by a processor.

[0043] Using the embodiments of this specification, firstly, for the whole area of ​​the tight gas reservoir, the parameters of each grid point are collected to obtain the characteristic factors of the tight gas reservoir, wherein each characteristic factor contains multiple characteristic data; then, a tight gas reservoir model is constructed, and multiple characteristic data are input into the tight gas reservoir model to obtain the main controlling factors of the tight gas reservoir; according to the main controlling factors, the adaptability of multiple clustering algorithms to the tight gas reservoir is analyzed and calculated, and a clustering algorithm suitable for the actual gas reservoir is selected, and the clustering algorithm is used to perform clustering calculations on the actual data, and the potential area analysis field of the tight gas reservoir is established with geological, dynamic, and construction parameters as characteristic factors, and fields of different time and space dimensions are established with gas reservoir production capacity and energy storage as target factors, and the potential area analysis field is divided by the preferred clustering algorithm. Thus, a method that can accurately describe the distribution of residual gas is established to determine the distribution of residual gas in the gas reservoir to meet the needs of subsequent potential tapping work, thereby improving the utilization rate and recovery rate of reserves. At the same time, this scheme can automatically and accurately describe the distribution of remaining gas and determine the distribution of remaining gas in the gas reservoir to meet the needs of subsequent potential tapping work, thereby improving the utilization rate and recovery rate of reserves. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the embodiments of this specification or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the embodiments of this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0045] Figure 1 It is a schematic diagram of an implementation system of an intelligent classification method for remaining gas potential areas in tight gas reservoirs in an embodiment of this specification;

[0046] Figure 2 It is a schematic diagram of a process of an intelligent classification method for remaining gas potential areas in tight gas reservoirs according to an embodiment of this specification;

[0047] Figure 3 It is a schematic diagram of a flow chart of analyzing the adaptability of various clustering algorithms to the tight gas reservoir according to the main control factors in the embodiment of this specification;

[0048] Figure 4 It is a schematic diagram of the process of establishing the potential area analysis field of the tight gas reservoir based on the main controlling factors in the embodiment of this specification;

[0049] Figure 5 It is a schematic diagram of the process of dividing the potential area analysis field by the preferred clustering algorithm in the embodiment of this specification;

[0050] Figure 6The figure shows a preferred schematic diagram of a specific clustering algorithm in the embodiment of this specification;

[0051] Figure 7 It is a schematic diagram of the structure of an intelligent classification device for remaining gas potential areas in tight gas reservoirs in an embodiment of this specification;

[0052] Figure 8 The figure is a schematic diagram of the structure of a computer device in an embodiment of the present specification.

[0053]

Description of reference numerals

[0054] 101. Terminal;

[0055] 102. Server;

[0056] 701, feature extraction module;

[0057] 702, model building module;

[0058] 703, adaptive calculation module;

[0059] 704. Potential area division module;

[0060] 802. Computer equipment;

[0061] 804. Processing equipment;

[0062] 806. Storage resources;

[0063] 808, drive system;

[0064] 810, input / output module;

[0065] 812. Input device;

[0066] 814. Output device;

[0067] 816. Presentation equipment;

[0068] 818. Graphical user interface;

[0069] 820, network interface;

[0070] 822, communication link;

[0071] 824. Communication bus. DETAILED DESCRIPTION

[0072] The following will be combined with the drawings in the embodiments of this specification to clearly and completely describe the technical solutions in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of them. Based on the embodiments in the embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the embodiments of this specification.

[0073] It should be noted that the terms "first", "second", etc. in the description and claims of the embodiments of this specification and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the embodiments of this specification described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, device, product or equipment that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or equipment.

[0074] It should be noted that the acquisition, storage, use, and processing of data in the technical solutions of the embodiments of this specification comply with the relevant provisions of national laws and regulations.

[0075] It should be noted that in the embodiments of this specification, certain software, components, models and other existing solutions in the industry may be mentioned, and they should be regarded as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of this application, but it does not mean that the applicant has or will necessarily use the solution.

[0076] like Figure 1 The diagram shows a schematic diagram of an implementation system of an intelligent classification method for remaining gas potential areas in tight gas reservoirs in an embodiment of the specification, including a terminal 101 and a server 102. The terminal 101 and the server 102 can communicate with each other through a network, and the network can include a local area network (Local Area Network, referred to as LAN), a wide area network (Wide Area Network, referred to as WAN), the Internet or a combination thereof, and is connected to a website, a user device (such as a computing device) and a back-end system.

[0077] The data collector can input the parameters of each grid point in the whole area of ​​the tight gas reservoir to the server 102 through the terminal 101. The server 102 builds a tight gas reservoir model, extracts the main controlling factors from multiple characteristic data, and selects the preferred clustering algorithm suitable for the tight gas reservoir, and then divides the potential area analysis field of the tight gas reservoir based on the preferred clustering algorithm, and displays the division results through the terminal 101. Optionally, the server 102 can be a node of a cloud computing system (not shown in the figure), or each server can be a separate cloud computing system, including multiple computers interconnected by a network and working as a distributed processing system.

[0078] In addition, it should be noted that Figure 1 What is shown is only one application environment provided by the embodiment of this specification. In actual application, other application environments may also be included, and this specification does not limit it.

[0079] In view of the problems existing in the prior art, the embodiment of this specification provides an intelligent classification method for the potential area of ​​remaining gas in a tight gas reservoir, which selects the main controlling factors and the optimal clustering algorithm by obtaining the characteristic factors of the tight gas reservoir, and then establishes the potential area analysis field of the tight gas reservoir based on the main controlling factors, and divides the potential area analysis field by the optimal clustering algorithm, so as to accurately describe the distribution of the remaining gas and determine the distribution of the remaining gas in the gas reservoir. Figure 2 The figure shows a flow chart of the intelligent classification method of the remaining gas potential area of ​​the tight gas reservoir in the embodiment of this specification. The process of intelligent classification of the remaining gas potential area of ​​the tight gas reservoir is described in this figure. The order of steps listed in the embodiment is only one way of executing the order of many steps, and does not represent the only execution order. When the system or device product is executed in practice, it can be executed in the order of the method shown in the embodiment or the accompanying drawings or in parallel.

[0080] Specific as Figure 2 As shown, the method may include:

[0081] Step 201: Acquire characteristic factors of a tight gas reservoir, wherein the characteristic factors include a plurality of characteristic data;

[0082] Step 202: construct a tight gas reservoir model, and input the plurality of characteristic data into the tight gas reservoir model to obtain the main controlling factors of the tight gas reservoir;

[0083] Step 203: analyzing the adaptability of multiple clustering algorithms to the tight gas reservoir according to the main controlling factors, and selecting a preferred clustering algorithm suitable for the tight gas reservoir;

[0084] Step 204: establishing a potential area analysis field of the tight gas reservoir based on the main controlling factors, and dividing the potential area analysis field by using the preferred clustering algorithm.

[0085] Using the embodiments of this specification, firstly, for the whole area of ​​the tight gas reservoir, the parameters of each grid point are collected to obtain the characteristic factors of the tight gas reservoir, wherein each characteristic factor contains multiple characteristic data; then, a tight gas reservoir model is constructed, and multiple characteristic data are input into the tight gas reservoir model to obtain the main controlling factors of the tight gas reservoir; according to the main controlling factors, the adaptability of multiple clustering algorithms to the tight gas reservoir is analyzed and calculated, and a clustering algorithm suitable for the actual gas reservoir is selected, and the clustering algorithm is used to perform clustering calculations on the actual data, and the potential area analysis field of the tight gas reservoir is established with geological, dynamic, and construction parameters as characteristic factors, and fields of different time and space dimensions are established with gas reservoir production capacity and energy storage as target factors, and the potential area analysis field is divided by the preferred clustering algorithm. Thus, a method that can accurately describe the distribution of residual gas is established to determine the distribution of residual gas in the gas reservoir to meet the needs of subsequent potential tapping work, thereby improving the utilization rate and recovery rate of reserves. At the same time, this scheme can automatically and accurately describe the distribution of remaining gas and determine the distribution of remaining gas in the gas reservoir to meet the needs of subsequent potential tapping work, thereby improving the utilization rate and recovery rate of reserves.

[0086] The characteristics of tight gas reservoirs are that there is no clear existence of edge and bottom water, strong reservoir heterogeneity, and complex seepage mechanism. Therefore, the development of tight gas reservoirs requires development characteristics different from conventional gas reservoirs. In the later stage of the development process, the distribution of residual gas is affected by many factors, including reservoir properties, water saturation, well network layout, well type selection, development time and process measures. Therefore, the embodiment of this specification collects parameters of each grid point for the entire area of ​​tight gas reservoirs, including reservoir properties, production dynamics, fracturing construction parameters, etc., and then through a variety of main control factor evaluation methods, the selected parameters are processed and the main influencing parameters are selected. Then, with gas reservoir production capacity and energy storage as target factors, multiple potential area analysis fields of different time and space dimensions are established, and a clustering algorithm suitable for the actual gas reservoir situation is selected. The clustering algorithm is used to perform clustering calculations on the actual data of multiple potential area analysis fields, and each "cluster" and clustering result are calculated according to each clustering algorithm, and finally the clustering results are mutually verified with actual cognition to obtain the division results of the potential area analysis field.

[0087] In the embodiments of the present specification, the plurality of characteristic data at least include: reservoir physical property characteristic parameters, production dynamic characteristic parameters, and fracturing operation characteristic parameters.

[0088] The reservoir physical property characteristic parameters include at least porosity, absolute permeability, effective thickness, initial gas saturation, and initial pressure;

[0089] The production dynamic characteristic parameters at least include initial gas saturation, cumulative gas production, open flow, current gas saturation, effective permeability, and formation pressure;

[0090] The characteristic parameters of the fracturing construction include at least Poisson's ratio and brittleness index.

[0091] Specifically, in step 202, a tight gas reservoir model of the basic geology of the gas reservoir is established using modeling software, and characteristic factors of gas reservoir development are collected, including reservoir physical parameters, production dynamic parameters, and fracturing construction parameters. The reservoir physical parameters include porosity, absolute permeability, effective thickness, initial gas saturation, initial pressure, etc., the fracturing construction parameters include Poisson's ratio, brittleness index, etc., and the production dynamic parameters include initial current gas saturation, cumulative gas production in the first three months, open flow, current gas saturation, effective permeability, formation pressure, etc. In order to avoid the error of the final result caused by parameters with little correlation in the big data algorithm process, it is necessary to optimize the selected parameters. The optimization methods include the production capacity main control factor evaluation method based on the entropy method, the production capacity main control factor evaluation method based on the gray correlation method, the production capacity main control factor evaluation method based on the hierarchical analysis method, the production capacity main control factor evaluation method based on the comprehensive weight, etc., and the main control factor analysis is performed using programming tools such as python, and finally the main control factors that have a major impact on the tight gas reservoir are selected from multiple characteristic data.

[0092] In the embodiments of the present specification, in order to minimize the corresponding clustering result obtained by the selected clustering algorithm, different clustering algorithms need to be considered according to the actual conditions of different oil fields, and the clustering algorithms are matched according to the actual conditions of different oil fields. The multiple clustering algorithms include K-Means mean clustering, affinity propagation, mean shift, spectral clustering, Ward hierarchical clustering, hierarchical clustering, DBSCAN density clustering, OPTICS clustering, Gaussian mixture clustering and Birch hierarchical clustering.

[0093] The other algorithms are not very similar, but they can also be used. Different models correspond to different adaptability options, and adaptability selection needs to be made for each gas reservoir.

[0094] In the embodiment of this specification, in order to find a clustering algorithm suitable for the actual situation of the oil field, the adaptability of multiple clustering algorithms to the tight gas reservoir is analyzed according to the main control factors, further including:

[0095] Determining the adaptability of each clustering algorithm according to the type, number and data volume of the main controlling factors of the tight gas reservoir;

[0096] If the number of the main controlling factors exceeds 5, it is determined to be high-dimensional data to determine the data volume scale of the main controlling factors;

[0097] If the data volume is larger than the preset threshold, K-Means mean clustering, Ward hierarchical clustering or hierarchical clustering algorithm is used;

[0098] If the data volume is smaller than a preset threshold, a mean shift, mean shift or spectral clustering algorithm is used;

[0099] If the number of the main controlling factors is less than 5, it is judged as low-dimensional data and the Birch hierarchical clustering algorithm is used.

[0100] Specifically, by comparing the advantages and disadvantages of the above clustering algorithms and combining them with the gas reservoir situation, it can be found that K-Means mean clustering algorithm, Ward hierarchical clustering algorithm, etc. are more suitable for situations with large data volumes, while mean shift, affinity propagation, etc. are suitable for situations with small data volumes. In the actual situation of the oil field, if the final classification into several types is determined, that is, the K value is determined, K-Means mean clustering is mostly applicable on site. If there are too many actual parameters considered in the end, spectral clustering or OPTICS clustering is applicable on site. Different clustering algorithms need to be considered according to the actual situation of different oil fields. Exemplarily, the clustering algorithm is matched to the actual situation of the oil field. If the number of grids does not exceed 500,000, it is judged as small-scale data, and if it exceeds 500,000, it is judged as relatively large-scale data. If the number of parameters considered exceeds 5 (excluding 5), it is judged as high-dimensional data. If the number of parameters considered does not exceed two, it is judged as low-dimensional data.

[0101] In the embodiments of this specification, in order to reduce the loss function corresponding to the clustering result, such as Figure 3 As shown, the adaptability of multiple clustering algorithms to the tight gas reservoir according to the main controlling factors is further analyzed,

[0102] Step 301: extracting part of the data of the main control factors and calculating them by a clustering algorithm whose adaptability is greater than a preset threshold;

[0103] Step 302: Obtain a clustering result calculated by the clustering algorithm, and select the preferred clustering algorithm according to the clustering result.

[0104] Specifically, the adaptability of the clustering algorithm is mainly determined by iteratively finding a partitioning scheme for K clusters (Cluster) so that the loss function corresponding to the clustering result is minimized. Then, the preferred clustering algorithm is selected according to the loss function corresponding to the clustering result. Among them, the loss function can be defined as the sum of square errors of each sample from the center point of the cluster to which it belongs. The artificial intelligence machine learning clustering algorithm is used to compare the adaptability of different clustering algorithms, and the research on the identification method of residual gas potential areas is carried out.

[0105] In the embodiments of this specification, Figure 4 As shown, in order to establish the potential area analysis field of the tight gas reservoir based on the main controlling factors, it further includes:

[0106] The potential area analysis field includes production potential field, remaining gas reserve field and seepage field;

[0107] Step 401: establishing a production potential field and a remaining gas reserve field based on reservoir physical property characteristic parameters in the main controlling factors;

[0108] Step 402: Establishing a seepage field according to the production dynamic characteristic parameters.

[0109] Specifically, based on the selected data and clustering algorithm, different fields are recommended according to different parameters. First, the three parameters of permeability, porosity, and effective thickness are used to establish the production potential field of different time and space dimensions using tNavigator, and then the reserve abundance is used to establish the remaining gas reserve field. Finally, the seepage field is established by considering the gas saturation and the pressure field at different times. Then, the level of the remaining gas enrichment area is preliminarily divided through the clustering algorithm determined by the preferred method.

[0110] In the embodiments of this specification, Figure 5 As shown, in order to divide the potential area analysis field by the preferred clustering algorithm, it further includes:

[0111] Step 501: inputting the established production potential field, remaining gas reserve field and seepage field into the preferred clustering algorithm respectively;

[0112] Step 502: verifying the data sets in the production potential field, the remaining gas reserve field, and the seepage field, and randomly selecting an initial point in the data sets;

[0113] Step 503: calculating the average values ​​of the production potential field, the remaining gas reserve field and the seepage field according to the initial point and the preferred clustering algorithm;

[0114] Step 504: Divide the potential area analysis field according to the average values ​​of the production potential field, the remaining gas reserve field and the seepage field.

[0115] Exemplarily, when the preferred clustering algorithm is the K-means algorithm, the established production potential field, remaining gas reserve field, and seepage field are input into Malatlab and processed using the K-means algorithm. First, the K-means algorithm processes the input data to exclude and optimize obviously erroneous data. And randomly select three initial points (centroids) in the data set (select as many initial points as there are categories); H0 = (x0, y0, z0, d0, h0).

[0116] The data points can be regarded as an n-dimensional vector. For example, if there are five indicators, each data point is a five-dimensional vector H i =(x i ,y i ,zi ,d i ,h i ); then calculate the distance between each data point and the three initial points. The distance:

[0117]

[0118] And divide it into a cluster with the closest initial point; then calculate the average value of the data points in each cluster, and update the average value as the new centroid; finally repeat the above steps until the centroid does not change. In this way, the K-means algorithm is calculated. After the calculation, the algorithm can automatically identify and classify the data points. Since the data used is located in the established production potential field, remaining gas reserve field, and seepage field, each parameter of the cluster center has a classification index.

[0119] In the prior art, the research on the evaluation of the remaining gas potential area in tight gas reservoirs mainly adopts methods such as geological analysis, dynamic monitoring, gas reservoir engineering and numerical simulation. The evaluation of the remaining gas potential is mainly based on parameters such as formation pressure, reserve abundance and gas saturation, and lacks quantitative and precise evaluation methods. In addition, most of the current research on the evaluation of the remaining gas potential does not consider the impact of economic conditions on the development of the remaining gas, making it difficult for the results of the remaining gas evaluation to directly guide subsequent development adjustments.

[0120] Through a method for quantitatively describing the remaining gas in a gas reservoir, "production capacity-storage coefficient", the production and storage coefficient distribution map of the tight gas reservoir can be generated according to the physical property parameters of the acquired tight gas reservoir and the target production and storage coefficient definition formula. The production and storage coefficient definition formula is:

[0121]

[0122] Where, ζ is the production and storage coefficient of the tight gas reservoir, P r is the average pressure of the tight gas reservoir, k is the reservoir permeability of the tight gas reservoir, h is the reservoir thickness of the tight gas reservoir, is the reservoir porosity of the tight gas reservoir, S g is the gas saturation of the tight gas reservoir.

[0123] According to the physical parameters of the gas reservoir, based on the "production capacity-storage coefficient", the "production capacity-storage coefficient distribution map" is generated through the tNavigator software. According to the "production capacity-storage coefficient distribution map", the potential regional level of the gas reservoir can be judged. However, this method is limited by the large range of parameters used. The "production and storage coefficient distribution map" described cannot accurately describe the distribution of the remaining gas, and the operation process is complicated, and the final judgment standard is vague.

[0124] Exemplarily, according to an embodiment of the present specification, after the data is collected, the selected parameters are processed for correlation, and the known parameters are analyzed using the grey correlation method. Driven by the multi-characteristic factor data, the main characteristic factors in this embodiment are determined: porosity, absolute permeability, effective thickness, initial gas saturation, initial pressure, Poisson's ratio, brittleness index, current gas saturation, unimpeded flow, current gas saturation, effective permeability, formation pressure, etc., and then the data format is adjusted to a recognizable format. Then, due to the different unit dimensions of each data, each dimension is processed, that is, a tight gas reservoir model is constructed, and the characteristic data is input into the model to solve the correlation and sort the correlation to obtain the main controlling factors. Then, based on the main controlling factors, the production potential field, the remaining gas reserve field, and the seepage field are established. According to the mathematical model built in the early stage, based on the TNavigator numerical simulation software, its basic reservoir physical properties, the absolute permeability, porosity, and effective thickness in different time and space dimensions can build the production potential field in different time and space dimensions, and the production and storage coefficients in different time and space dimensions can build the remaining gas reserve field, and according to the numerical simulation results of the gas reservoir, its gas saturation field and pressure field can build the final seepage field. At this point, clustering can begin.

[0125] The optimal diagram of clustering algorithm is as follows Figure 6 As shown in the figure, before the optimization, it is necessary to collect and organize various clustering algorithms. Widely used and common clustering algorithms, such as K-Means mean clustering, Ward hierarchical clustering, DBSCAN density clustering, Birch hierarchical clustering, etc., have different application conditions and adaptability. All major algorithms are imported into the data for calculation. The optimal clustering algorithm suitable for the tight gas reservoir is K-Means mean clustering, which has the fastest calculation speed and is very practical for processing big data. This time, the optimal use of K-Means mean clustering is used as an example to demonstrate the subsequent classification algorithm. Using K-Means for clustering, first input the data, and the K-means algorithm automatically optimizes the data. Then select three centroids and determine the centroid dimension, calculate the distance from each data to the initial point, and which category is closest to the centroid. It is divided into three "clusters", and the average value within the cluster is calculated as the new centroid. Repeat the iteration until the centroid no longer changes, and the final three-category regional standard can be obtained.

[0126] If the preferred clustering algorithm is the Birch hierarchical clustering algorithm, a new "CF" tree will be constructed first, and all sample points will be read: all sample points to be clustered are read from the data set. Insert sample points into the CF tree: For each sample point, calculate its CF value (ie, n, LS, SS) and insert it into the CF tree. During the insertion process, it may be necessary to update the CF values ​​of all nodes on the path from the root node to the leaf node. Merge similar CF nodes: Based on the distance between CF nodes (such as Euclidean distance or cosine similarity), select the two CF nodes with the highest similarity to merge.

[0127] When merging, update the CF value (n, LS, SS) of the merged node. Repeat the merging step: Repeat the merging step until certain termination conditions are met. The termination conditions may include that the number of clusters reaches a set threshold, or the diameter of the merged CF node exceeds a preset threshold. Then build a CF tree: use the merged CF nodes as nodes of the CF tree to build a complete CF tree. Then for each CF node, calculate the coordinates of its representative point. The representative point can be the center of gravity or center of mass of the sample point in the CF node. Determine the clustering clusters: According to the distance of the cluster representative points (such as Euclidean distance or cosine similarity), the CF nodes with the closest representative points are classified into the same cluster. Finally, output the clustering results: output the sample points in each cluster as the final clustering results. Finally, verify the results. The first type of area is a relatively high area of ​​physical properties, reserves, etc. according to conventional knowledge. That is, the first type of area in the classification result is the area with the best expected distribution of remaining gas potential.

[0128] The method provided in this specification takes into account the potential areas of tight gas reservoirs with multiple factors such as dynamics, geology, and construction, and establishes a method that can automatically and accurately describe the distribution of remaining gas, thereby improving the utilization rate and recovery rate of reserves. For the entire area of ​​tight gas reservoirs, the parameters of each grid point are collected, including reservoir properties, production dynamics, fracturing construction parameters, etc., and then the selected parameters are processed through the grey correlation method to select the main influencing parameters. At the same time, each clustering algorithm is optimized and calculated, and a clustering algorithm suitable for the actual gas reservoir situation is optimized, and the clustering algorithm is used to perform clustering calculations on the actual data, and each "cluster" and clustering result are calculated according to each clustering code. Finally, the clustering results are mutually verified with the actual cognition.

[0129] Based on the same inventive concept, the embodiment of this specification also provides an intelligent classification device for remaining gas potential areas in tight gas reservoirs, such as Figure 7 As shown, the device comprises:

[0130] A feature extraction module 701 is used to obtain feature factors of tight gas reservoirs, wherein the feature factors include a plurality of feature data;

[0131] A model building module 702 is used to build a tight gas reservoir model, and input the plurality of characteristic data into the tight gas reservoir model to obtain the main controlling factors of the tight gas reservoir;

[0132] An adaptability calculation module 703 is used to analyze the adaptability of multiple clustering algorithms to the tight gas reservoir according to the main control factors, and select a preferred clustering algorithm suitable for the tight gas reservoir;

[0133] The potential area division module 704 is used to establish a potential area analysis field of the tight gas reservoir based on the main controlling factors, and divide the potential area analysis field by using the preferred clustering algorithm.

[0134] like Figure 8 The diagram is a schematic diagram of the structure of a computer device according to an embodiment of the present specification. The method according to the embodiment of the present specification can be applied to the computer device according to the embodiment.

[0135] Specifically, Figure 8 As shown, the computer device 802 may include one or more processing devices 804, such as one or more central processing units (CPUs), each of which may implement one or more hardware threads. The computer device 802 may also include any storage resources 806 for storing any type of information such as code, settings, data, etc. Without limitation, for example, the storage resource 806 may include any one or more combinations of the following: any type of RAM, any type of ROM, a flash memory device, a hard disk, an optical disk, etc. More generally, any storage resource may use any technology to store information.

[0136] Further, any storage resource may provide volatile or non-volatile retention of information.

[0137] Further, any storage resource may represent a fixed or removable component of the computer device 802. In one case, when the processing device 804 executes the associated instructions stored in any storage resource or combination of storage resources, the computer device 802 may perform any operation of the associated instructions. The computer device 802 also includes one or more drive systems 808 for interacting with any storage resource, such as a hard disk drive system, an optical disk drive system, etc.

[0138] The computer device 802 may also include an input / output module 810 (I / O) for receiving various inputs (via input devices 812) and for providing various outputs (via output devices 814). A specific output mechanism may include a presentation device 816 and an associated graphical user interface (GUI) 818. In other embodiments, the input / output module 810 (I / O), the input device 812, and the output device 814 may not be included, and the computer device 802 may be used as a computer device in a network. The computer device 802 may also include one or more network interfaces 820 for exchanging data with other devices via one or more communication links 822. One or more communication buses 824 couple the components described above together.

[0139] The communication link 822 may be implemented in any manner, for example, through a local area network, a wide area network (e.g., the Internet), a point-to-point connection, etc., or any combination thereof. The communication link 822 may include any combination of hardwired links, wireless links, routers, gateway functions, name servers, etc. governed by any protocol or combination of protocols.

[0140] The embodiments of the present specification also provide a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program implements the above method when executed by a processor.

[0141] The embodiments of the present specification also provide a computer-readable instruction, wherein when a processor executes the instruction, the program therein causes the processor to execute the above method.

[0142] It should be understood that in the various embodiments of the present specification, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present specification.

[0143] It should also be understood that in the embodiments of this specification, the term "and / or" is only a description of the association relationship of the associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in the embodiments of this specification generally indicates that the associated objects before and after are in an "or" relationship.

[0144] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the embodiments of this specification can be implemented with electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the embodiments of this specification.

[0145] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0146] In the several embodiments provided in the embodiments of this specification, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, or it can be an electrical, mechanical or other form of connection.

[0147] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of this specification.

[0148] In addition, each functional unit in each embodiment of the present specification 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 above integrated unit can be implemented in the form of hardware or in the form of software functional units.

[0149] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of this specification is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the embodiment of this specification. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program code.

[0150] The embodiments of this specification use specific embodiments to illustrate the principles and implementation methods of the embodiments of this specification. The description of the above embodiments is only used to help understand the methods and core ideas of the embodiments of this specification. At the same time, for those skilled in the art, according to the ideas of the embodiments of this specification, there will be changes in the specific implementation methods and application scopes. In summary, the content of this specification should not be understood as a limitation on the embodiments of this specification.

Claims

1. An intelligent classification method for remaining gas potential areas in tight gas reservoirs, characterized in that: The method comprises: Acquiring characteristic factors of a tight gas reservoir, wherein the characteristic factors include a plurality of characteristic data; Constructing a tight gas reservoir model, and inputting the plurality of characteristic data into the tight gas reservoir model to obtain the main controlling factors of the tight gas reservoir; Analyzing the adaptability of multiple clustering algorithms to the tight gas reservoir according to the main controlling factors, and selecting a preferred clustering algorithm suitable for the tight gas reservoir; A potential area analysis field of the tight gas reservoir is established based on the main controlling factors, and the potential area analysis field is divided by the preferred clustering algorithm.

2. The intelligent classification method for remaining gas potential areas in tight gas reservoirs according to claim 1 is characterized in that: The plurality of characteristic data at least include: reservoir physical property characteristic parameters, production dynamic characteristic parameters, and fracturing operation characteristic parameters.

3. The intelligent classification method for remaining gas potential areas in tight gas reservoirs according to claim 2 is characterized in that: The reservoir physical property characteristic parameters at least include porosity, absolute permeability, effective thickness, initial gas saturation, and initial pressure; The production dynamic characteristic parameters at least include initial gas saturation, cumulative gas production, open flow, current gas saturation, effective permeability, and formation pressure; The characteristic parameters of the fracturing construction include at least Poisson's ratio and brittleness index.

4. The intelligent classification method for remaining gas potential areas in tight gas reservoirs according to claim 2 is characterized in that: The multiple clustering algorithms include K-Means mean clustering, affinity propagation, mean shift, spectral clustering, Ward hierarchical clustering, hierarchical clustering, DBSCAN density clustering, OPTICS clustering, Gaussian mixture clustering and Birch hierarchical clustering.

5. The intelligent classification method for remaining gas potential areas in tight gas reservoirs according to claim 4 is characterized in that: The adaptability of various clustering algorithms to the tight gas reservoir according to the main controlling factors is further analyzed, Determining the adaptability of each clustering algorithm according to the type, number and data volume of the main controlling factors of the tight gas reservoir; If the number of the main controlling factors exceeds 5, it is determined to be high-dimensional data to determine the data volume scale of the main controlling factors; If the data volume is larger than the preset threshold, K-Means mean clustering, Ward hierarchical clustering or hierarchical clustering algorithm is used; If the data volume is smaller than a preset threshold, a mean shift, mean shift or spectral clustering algorithm is used; If the number of the main controlling factors is less than 5, it is judged as low-dimensional data and the Birch hierarchical clustering algorithm is used.

6. The intelligent classification method for remaining gas potential areas in tight gas reservoirs according to claim 5 is characterized in that: The adaptability of various clustering algorithms to the tight gas reservoir according to the main controlling factors is further analyzed, Extracting part of the data from the main control factors and calculating them using a clustering algorithm with adaptability greater than a preset threshold; A clustering result calculated by the clustering algorithm is obtained, and the preferred clustering algorithm is selected according to the clustering result.

7. The intelligent classification method for remaining gas potential areas in tight gas reservoirs according to claim 3 is characterized in that: The potential area analysis field of the tight gas reservoir is established based on the main controlling factors and further includes: The potential area analysis field includes production potential field, remaining gas reserve field and seepage field; Establishing production potential field and remaining gas reserve field based on reservoir physical property characteristic parameters in the main controlling factors; A seepage field is established according to the production dynamic characteristic parameters.

8. The intelligent classification method for remaining gas potential areas in tight gas reservoirs according to claim 6 is characterized in that: Dividing the potential area analysis field by the preferred clustering algorithm further includes: Inputting the established production potential field, remaining gas reserve field and seepage field into the preferred clustering algorithm respectively; Verifying the data sets in the production potential field, the remaining gas reserve field, and the seepage field, and randomly selecting initial points in the data sets; Calculating average values ​​of the production potential field, the remaining gas reserve field, and the seepage field according to the initial point and the preferred clustering algorithm; The potential area analysis field is divided according to the average values ​​of the production potential field, the remaining gas reserve field and the seepage field.

9. An intelligent classification device for remaining gas potential areas in tight gas reservoirs, characterized in that: The device comprises: A feature extraction module, used to obtain feature factors of tight gas reservoirs, wherein the feature factors include a plurality of feature data; A model building module, used for building a tight gas reservoir model, inputting the plurality of characteristic data into the tight gas reservoir model to obtain the main controlling factors of the tight gas reservoir; An adaptability calculation module, used to analyze the adaptability of multiple clustering algorithms to the tight gas reservoir according to the main control factors, and select a preferred clustering algorithm suitable for the tight gas reservoir; The potential area division module is used to establish the potential area analysis field of the tight gas reservoir based on the main controlling factors, and divide the potential area analysis field by using the preferred clustering algorithm.

10. A computer device comprising a memory, a processor, and a computer program stored in the memory, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 8 is implemented.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

12. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images