Method and device for detecting seepage law of shale gas in microcracks

Abstract

The invention provides a method and a device for detecting a seepage rule of shale gas in microcracks, and relates to the technical field of detection. The method comprises the following steps: acquiring characteristic data of a shale gas reservoir in a rock stratum micro-fracture; calculating the feature data based on a preset shale gas reservoir recoverable reserve calculation model to obtain a reserve calculation result; wherein the preset shale gas reservoir recoverable reserve calculation model is obtained by training a plurality of support vector machine models or a plurality of neural network models according to sample data; and determining predicted values corresponding to different possibilities greater than actual final recoverable reserves according to the reserve calculation result. The device executes the method. According to the method and the device for detecting the seepage rule of the shale gas in the microfracture, the seepage rule of the shale gas in the microfracture can be truly and accurately detected by accurately determining the predicted value of the recoverable reserves of each shale gas reservoir.

Description

Technical Field

[0001] The present invention relates to the field of detection technology, and in particular to a method and device for detecting the seepage law of shale gas in micro-cracks. Background Art

[0002] Shale gas refers to the natural gas of biological origin, pyrolysis origin and mixed origin with certain commercial value stored and preserved in organic-rich, mature dark mud shale or high-carbon mud shale due to the adsorption of organic matter or the existence of cracks and matrix pores in the rock. Shale gas is an unconventional natural gas found in reservoir rock systems dominated by organic-rich shales. It is a continuously generated biochemical gas, thermogenic gas or a mixture of the two. It can exist in natural cracks and pores in a free state and in the adsorbed state on the surface of kerogen and clay particles. However, the seepage law of shale gas in microcracks can be obtained by calculating the recoverable reserves of shale gas reservoirs. The calculation process of recoverable reserves of shale gas reservoirs is affected by many factors, making it impossible for existing calculation methods to accurately calculate the recoverable reserves of shale gas reservoirs. Summary of the invention

[0003] In view of the problems in the prior art, an embodiment of the present invention provides a method and device for detecting the seepage law of shale gas in micro-fractures, which can at least partially solve the problems in the prior art.

[0004] On the one hand, the present invention provides a method for detecting the seepage law of shale gas in micro-fractures, comprising:

[0005] Obtain characteristic data of shale gas reservoirs in micro-fractures of rock formations;

[0006] Calculating the characteristic data based on a preset shale gas reservoir recoverable reserves calculation model to obtain a reserves calculation result;

[0007] Wherein, the preset shale gas reservoir recoverable reserves calculation model is obtained by training multiple support vector machine models or multiple neural network models based on sample data;

[0008] According to the reserve calculation results, predicted values ​​corresponding to different possibilities that are greater than the actual ultimate recoverable reserves are determined.

[0009] Wherein, the acquisition of characteristic data of shale gas reservoirs in micro-fractures of rock formations includes:

[0010] At least the porosity, permeability, completion method, drilling parameters, fracture length and conductivity of the shale gas reservoir in the micro-fractures of the rock formation are obtained.

[0011] Wherein, the acquisition of characteristic data of shale gas reservoirs in micro-fractures of rock formations includes:

[0012] According to the attribute reduction algorithm, attribute data related to the actual ultimate recoverable reserves of the shale gas reservoir in the micro-fractures of the rock formation are obtained from all attribute data of the shale gas reservoir in the micro-fractures of the rock formation as characteristic data.

[0013] Among them, training multiple support vector machine models or multiple neural network models according to sample data to obtain the preset shale gas reservoir recoverable reserves calculation model includes:

[0014] Grouping the sample data to obtain a training subsample set corresponding to each group;

[0015] If it is determined that the number of groups is less than or equal to the preset number of groups, multiple support vector machine models are trained based on the sample data in the training subsample set corresponding to each group to obtain the preset shale gas reservoir recoverable reserves calculation model.

[0016] Among them, training multiple support vector machine models or multiple neural network models according to sample data to obtain the preset shale gas reservoir recoverable reserves calculation model includes:

[0017] Grouping the sample data to obtain a training subsample set corresponding to each group;

[0018] If it is determined that the number of groups is greater than the preset number of groups, multiple neural network models are trained based on the sample data in the training subsample set corresponding to each group to obtain the preset shale gas reservoir recoverable reserves calculation model.

[0019] Wherein, the predicted values ​​corresponding to different possibilities of being greater than the actual ultimate recoverable reserves are determined according to the reserve calculation results, including:

[0020] Aggregating multiple reserve calculation results output by multiple support vector machine models or multiple neural network models to obtain a normal distribution diagram reflecting predicted values ​​of the multiple reserve calculation results;

[0021] A plurality of target prediction values ​​are obtained from the normal distribution diagram; wherein each target prediction value corresponds to a prediction value corresponding to a possibility greater than the actual ultimate recoverable reserves.

[0022] On the one hand, the present invention provides a device for detecting the seepage law of shale gas in micro-fractures, comprising:

[0023] An acquisition unit, used for acquiring characteristic data of shale gas reservoirs in micro-fractures of rock formations;

[0024] A calculation unit, used to calculate the characteristic data based on a preset shale gas reservoir recoverable reserves calculation model to obtain a reserves calculation result;

[0025] Wherein, the preset shale gas reservoir recoverable reserves calculation model is obtained by training multiple support vector machine models or multiple neural network models based on sample data;

[0026] A determination unit is used to determine predicted values ​​corresponding to different possibilities that are greater than the actual ultimate recoverable reserves according to the reserve calculation results.

[0027] In another aspect, an embodiment of the present invention provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following method when executing the computer program:

[0028] Obtain characteristic data of shale gas reservoirs in micro-fractures of rock formations;

[0029] Calculating the characteristic data based on a preset shale gas reservoir recoverable reserves calculation model to obtain a reserves calculation result;

[0030] Wherein, the preset shale gas reservoir recoverable reserves calculation model is obtained by training multiple support vector machine models or multiple neural network models based on sample data;

[0031] According to the reserve calculation results, predicted values ​​corresponding to different possibilities that are greater than the actual ultimate recoverable reserves are determined.

[0032] An embodiment of the present invention provides a computer-readable storage medium, including:

[0033] The computer readable storage medium stores a computer program, and when the computer program is executed by a processor, the following method is implemented:

[0034] Obtain characteristic data of shale gas reservoirs in micro-fractures of rock formations;

[0035] Calculating the characteristic data based on a preset shale gas reservoir recoverable reserves calculation model to obtain a reserves calculation result;

[0036] Wherein, the preset shale gas reservoir recoverable reserves calculation model is obtained by training multiple support vector machine models or multiple neural network models based on sample data;

[0037] According to the reserve calculation results, predicted values ​​corresponding to different possibilities that are greater than the actual ultimate recoverable reserves are determined.

[0038] The embodiment of the present invention further provides a computer program product, the computer program product comprising a computer program, and when the computer program is executed by a processor, the following method is implemented:

[0039] Obtain characteristic data of shale gas reservoirs in micro-fractures of rock formations;

[0040] Calculating the characteristic data based on a preset shale gas reservoir recoverable reserves calculation model to obtain a reserves calculation result;

[0041] Wherein, the preset shale gas reservoir recoverable reserves calculation model is obtained by training multiple support vector machine models or multiple neural network models based on sample data;

[0042] According to the reserve calculation results, predicted values ​​corresponding to different possibilities that are greater than the actual ultimate recoverable reserves are determined.

[0043] The method and device for detecting the seepage law of shale gas in micro-cracks provided in the embodiments of the present invention obtain characteristic data of shale gas reservoirs in micro-cracks of rock formations; calculate the characteristic data based on a preset shale gas reservoir recoverable reserves calculation model to obtain a reserve calculation result; wherein the preset shale gas reservoir recoverable reserves calculation model is obtained by training multiple support vector machine models or multiple neural network models based on sample data; and determine the predicted values ​​corresponding to different possibilities that are greater than the actual final recoverable reserves based on the reserve calculation result, so that the seepage law of shale gas in micro-cracks can be truly and accurately detected by accurately determining the predicted values ​​of the recoverable reserves of each shale gas reservoir. BRIEF DESCRIPTION OF THE DRAWINGS

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

[0045] Figure 1 It is a schematic flow chart of a method for detecting the seepage law of shale gas in micro-fractures provided in one embodiment of the present invention.

[0046] Figure 2 It is a schematic structural diagram of a device for detecting the seepage law of shale gas in micro-fractures provided by one embodiment of the present invention.

[0047] Figure 3 A schematic diagram of the physical structure of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical scheme and advantages of the embodiments of the present invention more clear, the embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings. Here, the illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention. It should be noted that, in the absence of conflict, the embodiments in this application and the features in the embodiments can be combined with each other arbitrarily.

[0049] Figure 1 FIG. 1 is a flow chart of a method for detecting the seepage law of shale gas in micro-fractures provided by an embodiment of the present invention. Figure 1 As shown, the method for detecting the seepage law of shale gas in micro-fractures provided by the embodiment of the present invention includes:

[0050] Step S1: Acquire characteristic data of shale gas reservoirs in micro-fractures of rock formations.

[0051] Step S2: Calculate the characteristic data based on a preset shale gas reservoir recoverable reserves calculation model to obtain a reserves calculation result;

[0052] The preset shale gas reservoir recoverable reserves calculation model is obtained by training multiple support vector machine models or multiple neural network models based on sample data.

[0053] Step S3: Determine predicted values ​​corresponding to different possibilities that are greater than the actual ultimate recoverable reserves according to the reserve calculation results.

[0054] In the above step S1, the device obtains characteristic data of shale gas reservoirs in micro-fractures of rock formations. The device may be a computer device that executes the method. The acquisition, storage, use, and processing of data in the technical solution of this application are in compliance with relevant regulations. The acquisition of characteristic data of shale gas reservoirs in micro-fractures of rock formations includes:

[0055] At least the porosity, permeability, completion method, drilling parameters, fracture length and conductivity of the shale gas reservoir in the micro-fractures of the rock formation are obtained.

[0056] The drilling parameters include drilling pressure, drilling speed, drilling cycle, rotation speed, pore pressure, fracture pressure and collapse pressure.

[0057] The method of obtaining characteristic data of shale gas reservoirs in micro-fractures of rock formations includes:

[0058] According to the attribute reduction algorithm, attribute data related to the actual ultimate recoverable reserves of the shale gas reservoir in the micro-fractures of the rock formation are obtained from all attribute data of the shale gas reservoir in the micro-fractures of the rock formation as characteristic data.

[0059] The existing attribute reduction algorithms are mainly implemented through the following three ways:

[0060] 1. Heuristic reduction algorithm based on attribute importance;

[0061] 2. Use the Skowron discriminant matrix to solve the simplification; Skowron is an error control method.

[0062] 3. Apply theories in the field of biological intelligence to attribute simplification.

[0063] In the above step S2, the device calculates the characteristic data based on the preset shale gas reservoir recoverable reserves calculation model to obtain the reserve calculation result; all the above characteristic data can be input into the preset shale gas reservoir recoverable reserves calculation model, and the output result of the preset shale gas reservoir recoverable reserves calculation model is used as the reserve calculation result.

[0064] The preset shale gas reservoir recoverable reserves calculation model is obtained by training multiple support vector machine models or multiple neural network models based on sample data.

[0065] Training multiple support vector machine models or multiple neural network models according to sample data to obtain the preset shale gas reservoir recoverable reserves calculation model includes:

[0066] Grouping the sample data to obtain a training subsample set corresponding to each group;

[0067] If it is determined that the number of groups is less than or equal to the preset number of groups, multiple support vector machine models are trained based on the sample data in the training subsample set corresponding to each group to obtain the preset shale gas reservoir recoverable reserves calculation model. The preset number of groups can be set independently according to actual conditions.

[0068] Training multiple support vector machine models or multiple neural network models according to sample data to obtain the preset shale gas reservoir recoverable reserves calculation model includes:

[0069] Grouping the sample data to obtain a training subsample set corresponding to each group;

[0070] If it is determined that the number of groups is greater than the preset number of groups, multiple neural network models are trained based on the sample data in the training subsample set corresponding to each group to obtain the preset shale gas reservoir recoverable reserves calculation model. The preset number of groups can be set independently according to actual conditions. The model training is explained as follows:

[0071] Acquire characteristic data of shale gas reservoirs in multiple groups of rock formation micro-fractures and corresponding recoverable reserves as sample data in a training sample set;

[0072] arbitrarily selecting a plurality of specific groups of sample data from the training sample set, each specific group of sample data forming a training sub-sample set;

[0073] If the number of groups of sample data in the training sample set is not greater than the preset number of groups, the sample data in each training sub-sample set is input into the support vector machine model for training, and the sample data is mapped to a higher-dimensional space through a Gaussian kernel function to obtain multiple trained support vector machine models;

[0074] If the number of groups of sample data in the training sample set is greater than the preset number of groups, the sample data in each training sub-sample set is input into the neural network model for training, and the connection weights of the neurons in the neural network model are adjusted according to the training results of each group of sample data in the training sub-sample set until the error of the training result is less than the preset threshold, and a plurality of trained neural network models are obtained.

[0075] Furthermore, the neural network model is a BP neural network model:

[0076] The BP neural network model includes 9 hidden layers;

[0077] The neurons in the hidden layer adopt a sigmoid transfer function.

[0078] Furthermore, the characteristic data is input into the trained model to obtain the predicted value of the final recoverable reserves of the shale gas reservoir in the micro-fractures of the rock formation, specifically including:

[0079] The characteristic data is input into a plurality of trained support vector machine models or a plurality of neural network models, each model outputs a set of predicted values ​​of the final recoverable reserves of shale gas reservoirs in micro-fractures of rock formations, and a plurality of sets of the predicted values ​​are obtained.

[0080] In the above step S3, the device determines the predicted values ​​corresponding to different possibilities that are greater than the actual final recoverable reserves according to the reserve calculation result. The method of determining the predicted values ​​corresponding to different possibilities that are greater than the actual final recoverable reserves according to the reserve calculation result includes:

[0081] Aggregating multiple reserve calculation results output by multiple support vector machine models or multiple neural network models to obtain a normal distribution diagram reflecting predicted values ​​of the multiple reserve calculation results;

[0082] A plurality of target prediction values ​​are obtained from the normal distribution diagram; wherein each target prediction value corresponds to a prediction value corresponding to a possibility greater than the actual ultimate recoverable reserves.

[0083] The specific instructions are as follows:

[0084] Obtain three predicted values ​​of P10, P50 and P90 from the normal distribution graph;

[0085] Among them, P10 means that the predicted value has a 10% probability of being greater than the actual ultimate recoverable reserves; P50 means that the predicted value has a 50% probability of being greater than the actual ultimate recoverable reserves; P90 means that the predicted value has a 90% probability of being greater than the actual ultimate recoverable reserves. Among them, P10 corresponds to the aggressive prediction value calculation, P50 corresponds to the stable prediction value calculation, and P50 corresponds to the conservative prediction value calculation. You can choose one of the above methods to calculate the prediction value according to the actual situation.

[0086] It is also possible to detect cracks in shale layers, and the detection results can reflect the seepage law of shale gas in micro-cracks.

[0087] Shale gas can also be tested, and the results of shale gas testing can reflect the seepage law of shale gas in micro-cracks.

[0088] The seepage pressure of shale gas in micro-cracks can also be tested, and the seepage law of shale gas in micro-cracks can be reflected by the test results of seepage pressure.

[0089] It is also possible to classify shale gas enrichment reservoirs, and to use the classification results to reflect the seepage laws of shale gas in micro-fractures.

[0090] The above classification method is explained as follows:

[0091] (1) Analyze the shale gas enrichment and accumulation system in rock micro-fractures, and divide the system into three static subsystems: source rock, gas accumulation reservoir, and protective stratum, and four dynamic subsystems: tectonic evolution, sedimentary sequence, diagenetic evolution, and hydrocarbon generation history. By analyzing the interaction between the dynamic and static subsystems and extracting the main factors, a shale gas enrichment and accumulation model in rock micro-fractures with three major categories and six subcategories was established.

[0092] (2) According to the different degrees of control of tectonic evolution on shale gas source rocks, gas accumulation reservoirs and protective strata in micro-fractures of rock formations, the shale gas enrichment patterns in micro-fractures of rock formations are divided into shale gas enrichment patterns in micro-fractures of rock formations mainly controlled by structure for source rocks, shale gas enrichment patterns in micro-fractures of rock formations mainly controlled by structure for gas accumulation reservoirs and shale gas enrichment patterns in micro-fractures of rock formations mainly controlled by structure for protective strata;

[0093] (3) The shale gas enrichment patterns in the micro-cracks of the source rock type strata controlled by the structure include the following two subcategories; the shale gas enrichment patterns in the micro-cracks of the gas reservoir type strata controlled by the structure include the following two subcategories; the shale gas accumulation patterns in the micro-cracks of the protective strata type strata controlled by the structure include the following two subcategories.

[0094] Furthermore, the shale gas enrichment patterns in the micro-fractures of the source rock type strata of the structure mainly control the hydrocarbon generation include the following two subcategories:

[0095] In-situ continuous biogenic rock strata microcracks shale gas enrichment model: If the basin tectonic settlement is not large, the burial depth is shallow, the pore water in the mud shale has not been completely discharged, and at the same time, through the continuous injection of atmospheric fresh water at the edge of the basin, the organic-rich mud shale begins to generate shale gas in the microcracks of biogenic rock strata under anoxic, low-temperature and water environment, and accumulates in-situ, it is classified as the in-situ continuous biogenic rock strata microcracks shale gas enrichment model;

[0096] Shale gas accumulation mode in micro-cracks of in-situ continuous thermogenic rock formations: If the tectonic settlement of the basin increases, the burial depth increases, the formation temperature and pressure gradually increase, the primary water in the pores will either be gradually discharged due to compaction, or gradually evaporate due to the high temperature and high pressure environment, and eventually be consumed, and the kerogen and asphalt organic matter in the shale will begin to generate hydrocarbons in large quantities through thermal degradation or thermal cracking, then it is classified as a shale gas enrichment mode in micro-cracks of in-situ continuous thermogenic rock formations.

[0097] Furthermore, the shale gas enrichment mode in the micro-fractures of the structural main gas accumulation reservoir type rock formation includes the following two subcategories:

[0098] Shale gas enrichment mode in micro-fractures of positive structural reservoir type rock formations: During the formation of the foreland basin, or after the formation of the source rock, when the source rock begins to generate and expel hydrocarbons in large quantities, the area where the gas-accumulating reservoir is located suffers from strong structural compression, causing the gas-accumulating reservoir originally located on the monocline structure in the slope of the basin or in the negative structure in the center of the basin to undergo large-scale folding and deformation. This is classified as the shale gas enrichment mode in micro-fractures of positive structural reservoir type rock formations;

[0099] Shale gas enrichment pattern in micro-cracks of reservoir-type rock formations in fracture zones: If during the formation of the foreland basin, or after its formation, source rocks begin to generate and expel hydrocarbons in large quantities, or the generation and expulsion process has ended, and at the same time, multiple phases of tectonic uplift and downlift movements occur in the area where the gas-accumulating reservoir is located, the burial depth of the gas-accumulating reservoir will cause sharp fluctuations in formation temperature and pressure due to the oscillatory changes, and the gas adsorption and desorption processes and the free gas contraction and expansion processes will be repeated, which will promote the opening and activation of various diagenetic fractures in the gas-accumulating reservoir. The interactive changes in stress concentration formed by the tectonic uplift and downlift movements will also induce more tectonic fractures. This is classified as a shale gas enrichment pattern in micro-cracks of reservoir-type rock formations in fracture zones.

[0100] Furthermore, the shale gas accumulation mode in the micro-fractures of the structure-dominated protective formation type includes the following two subcategories:

[0101] Fracture-destructive shale gas accumulation mode in micro-cracks of rock formations: After multiple periods of tectonic movement compression or tension, various compression or tension faults and their induced fractures begin to occur in the core area of ​​shale gas reservoirs in micro-cracks of rock formations, and the original gas accumulation reservoirs and their top and bottom protective strata begin to be cut into blocks by numerous faults. The shale gas enriched in the micro-cracks of rock formations near the faults gradually escapes and releases pressure along the faults and their induced fractures, causing the cutting and destruction of the original shale gas reservoirs in the micro-cracks of rock formations. The shale itself is dense and has a certain sealing ability. In addition, the existence of its top and bottom protective layers means that the shale gas in the micro-cracks of rock formations that is locally accumulated is still retained in the fault blocks far away from the faults and their induced fractures. This is classified as a fracture-destructive shale gas accumulation mode in micro-cracks of rock formations.

[0102] Shale gas accumulation mode in micro-cracks of erosion residual rock formations: if after experiencing multiple stages of tectonic uplift, the core area of ​​shale gas reservoirs in micro-cracks of rock formations suffers from continuous uplift, the formation dip angle increases, resulting in the upturned ends of the gas accumulation reservoir and its top and bottom protective formations being exposed to the surface and subjected to the leaching of surface atmospheric water, the shale gas enriched in the micro-cracks of rock formations desorbs due to pressure reduction, and a large amount of shale gas adsorbed in the micro-cracks of rock formations becomes free gas. On the other hand, since N2 and CO2 from the air have stronger adsorption properties and enter the shale reservoirs, they replace a large amount of shale gas in the micro-cracks of rock formations, resulting in more and more free shale gas in the micro-cracks of rock formations gradually escaping to the surface, while the atmospheric fresh water on the surface is simultaneously injected into the gas accumulation reservoir in the reverse direction. When the gas escape and the atmospheric fresh water injection reach a balance, the gas re-accumulates into a reservoir in the gas accumulation reservoir of the shale gas reservoir in the micro-cracks of rock formations, which is classified as the shale gas accumulation mode in micro-cracks of erosion residual rock formations.

[0103] The method for detecting the seepage law of shale gas in micro-fractures provided by the embodiment of the present invention has the following advantages and positive effects:

[0104] First, in view of the technical problems existing in the above-mentioned prior art and the difficulty of solving the problems, the technical solutions to be protected by the present invention and the results and data during the research and development process are closely combined to analyze in detail and deeply how the technical solutions of the present invention solve the technical problems, and some creative technical effects brought about after solving the problems. The specific description is as follows:

[0105] The present invention fully absorbs the characteristics of shale gas reservoirs in micro-fractures of rock formations with different enrichment characteristics, carefully analyzes the factor composition of the shale gas enrichment system in micro-fractures of rock formations and the interaction relationship of each factor, extracts the key main factors affecting the enrichment and accumulation of shale gas in micro-fractures of rock formations, breaks the existing continuous enrichment and accumulation theory of shale gas in micro-fractures of rock formations and its characteristic pattern, and establishes a new enrichment and accumulation model of shale gas in micro-fractures of rock formations with three major categories and six subcategories. This model classifies the enrichment and accumulation of shale gas in micro-fractures of rock formations more finely. At the same time, the calculation of the final recoverable reserves of shale gas reservoirs in micro-fractures of rock formations is combined with machine learning through a reserve calculation module, and known historical data is fully utilized to establish a machine learning model without making any assumptions. The predicted value obtained by the machine learning model conforms to the actual law of shale gas reservoirs in micro-fractures of rock formations, so that the evaluation result of the final recoverable reserves can be true and reliable with high accuracy.

[0106] The method for detecting the seepage law of shale gas in micro-fractures provided in an embodiment of the present invention obtains characteristic data of shale gas reservoirs in micro-fractures of rock formations; calculates the characteristic data based on a preset shale gas reservoir recoverable reserves calculation model to obtain a reserve calculation result; wherein the preset shale gas reservoir recoverable reserves calculation model is obtained by training multiple support vector machine models or multiple neural network models based on sample data; and determines the predicted values ​​corresponding to different possibilities that are greater than the actual final recoverable reserves based on the reserve calculation result, and can accurately determine the predicted values ​​of the recoverable reserves of each shale gas reservoir, so as to truly and accurately detect the seepage law of shale gas in micro-fractures.

[0107] Furthermore, the step of obtaining characteristic data of shale gas reservoirs in micro-fractures of rock formations includes:

[0108] At least the porosity, permeability, completion method, drilling parameters, fracture length and conductivity of the shale gas reservoir in the micro-fractures of the rock formation are obtained. The above-mentioned embodiments can be referred to for explanation and will not be described in detail.

[0109] Furthermore, the step of obtaining characteristic data of shale gas reservoirs in micro-fractures of rock formations includes:

[0110] According to the attribute reduction algorithm, attribute data related to the actual final recoverable reserves of the shale gas reservoir in the micro-fractures of the rock formation are obtained from all attribute data of the shale gas reservoir in the micro-fractures of the rock formation as feature data.

[0111] Furthermore, multiple support vector machine models or multiple neural network models are trained according to the sample data to obtain the preset shale gas reservoir recoverable reserves calculation model, including:

[0112] The sample data are grouped to obtain a training sub-sample set corresponding to each group; this may be described with reference to the above embodiment and will not be described in detail.

[0113] If it is determined that the number of groups is less than or equal to the preset number of groups, multiple support vector machine models are trained based on the sample data in the training subsample set corresponding to each group to obtain the preset shale gas reservoir recoverable reserves calculation model.

[0114] Furthermore, multiple support vector machine models or multiple neural network models are trained according to the sample data to obtain the preset shale gas reservoir recoverable reserves calculation model, including:

[0115] The sample data are grouped to obtain a training sub-sample set corresponding to each group; this may be described with reference to the above embodiment and will not be described in detail.

[0116] If it is determined that the number of groups is greater than the preset number of groups, multiple neural network models are trained based on the sample data in the training subsample set corresponding to each group to obtain the preset shale gas reservoir recoverable reserves calculation model.

[0117] Furthermore, the determination of predicted values ​​corresponding to different possibilities that are greater than the actual ultimate recoverable reserves according to the reserve calculation results includes:

[0118] A plurality of reserve calculation results output by a plurality of support vector machine models or a plurality of neural network models are aggregated to obtain a normal distribution diagram reflecting the predicted values ​​of the plurality of reserve calculation results; this may be described with reference to the above embodiment and will not be described in detail.

[0119] A plurality of target prediction values ​​are obtained from the normal distribution diagram, wherein each target prediction value corresponds to a prediction value corresponding to a possibility greater than the actual final recoverable reserves. The above-mentioned embodiments can be referred to for explanation and will not be described in detail.

[0120] Figure 2 FIG. 1 is a schematic diagram of a device for detecting the seepage law of shale gas in micro-fractures according to an embodiment of the present invention. Figure 2 As shown, the device for detecting the seepage law of shale gas in micro-fractures provided by the embodiment of the present invention includes an acquisition unit 201, a calculation unit 202 and a determination unit 203, wherein:

[0121] The acquisition unit 201 is used to acquire characteristic data of shale gas reservoirs in micro-fractures of rock formations; the determination unit 202 is used to calculate the characteristic data based on a preset shale gas reservoir recoverable reserves calculation model to obtain a reserve calculation result; wherein the preset shale gas reservoir recoverable reserves calculation model is obtained by training multiple support vector machine models or multiple neural network models based on sample data; the determination unit 203 is used to determine the predicted values ​​corresponding to different possibilities that are greater than the actual final recoverable reserves based on the reserve calculation result.

[0122] Specifically, the acquisition unit 201 in the device is used to acquire characteristic data of shale gas reservoirs in micro-fractures of rock formations; the determination unit 202 is used to calculate the characteristic data based on a preset shale gas reservoir recoverable reserves calculation model to obtain a reserve calculation result; wherein the preset shale gas reservoir recoverable reserves calculation model is obtained by training multiple support vector machine models or multiple neural network models based on sample data; the determination unit 203 is used to determine the predicted values ​​corresponding to different possibilities that are greater than the actual final recoverable reserves based on the reserve calculation result.

[0123] The device for detecting the seepage law of shale gas in micro-fractures provided in an embodiment of the present invention obtains characteristic data of shale gas reservoirs in micro-fractures of rock formations; calculates the characteristic data based on a preset shale gas reservoir recoverable reserves calculation model to obtain a reserve calculation result; wherein the preset shale gas reservoir recoverable reserves calculation model is obtained by training multiple support vector machine models or multiple neural network models based on sample data; and determines the predicted values ​​corresponding to different possibilities that are greater than the actual final recoverable reserves based on the reserve calculation result, and can accurately determine the predicted values ​​of the recoverable reserves of each shale gas reservoir, so as to truly and accurately detect the seepage law of shale gas in micro-fractures.

[0124] Furthermore, the acquisition unit 201 is specifically used for:

[0125] At least the porosity, permeability, completion method, drilling parameters, fracture length and conductivity of the shale gas reservoir in the micro-fractures of the rock formation are obtained.

[0126] Furthermore, the acquisition unit 201 is specifically used for:

[0127] According to the attribute reduction algorithm, attribute data related to the actual ultimate recoverable reserves of the shale gas reservoir in the micro-fractures of the rock formation are obtained from all attribute data of the shale gas reservoir in the micro-fractures of the rock formation as characteristic data.

[0128] Furthermore, the device for detecting the seepage law of shale gas in micro-fractures is also used for:

[0129] Grouping the sample data to obtain a training subsample set corresponding to each group;

[0130] If it is determined that the number of groups is less than or equal to the preset number of groups, multiple support vector machine models are trained based on the sample data in the training subsample set corresponding to each group to obtain the preset shale gas reservoir recoverable reserves calculation model.

[0131] Furthermore, the device for detecting the seepage law of shale gas in micro-fractures is also used for:

[0132] Grouping the sample data to obtain a training subsample set corresponding to each group;

[0133] If it is determined that the number of groups is greater than the preset number of groups, multiple neural network models are trained based on the sample data in the training subsample set corresponding to each group to obtain the preset shale gas reservoir recoverable reserves calculation model.

[0134] Furthermore, the determining unit 203 is specifically configured to:

[0135] Aggregating multiple reserve calculation results output by multiple support vector machine models or multiple neural network models to obtain a normal distribution diagram reflecting predicted values ​​of the multiple reserve calculation results;

[0136] A plurality of target prediction values ​​are obtained from the normal distribution diagram; wherein each target prediction value corresponds to a prediction value corresponding to a possibility greater than the actual ultimate recoverable reserves.

[0137] The embodiment of the present invention provides an embodiment of a shale gas seepage law detection device in micro-fractures, which can be specifically used to execute the processing flow of the above-mentioned method embodiments. Its functions are not repeated here, and reference can be made to the detailed description of the above-mentioned method embodiments.

[0138] Figure 3 A schematic diagram of the physical structure of a computer device provided in an embodiment of the present invention is shown in FIG. Figure 3 As shown, the computer device includes: a memory 301, a processor 302, and a computer program stored in the memory 301 and executable on the processor 302. When the processor 302 executes the computer program, the following method is implemented:

[0139] Obtain characteristic data of shale gas reservoirs in micro-fractures of rock formations;

[0140] Calculating the characteristic data based on a preset shale gas reservoir recoverable reserves calculation model to obtain a reserves calculation result;

[0141] Wherein, the preset shale gas reservoir recoverable reserves calculation model is obtained by training multiple support vector machine models or multiple neural network models based on sample data;

[0142] According to the reserve calculation results, predicted values ​​corresponding to different possibilities that are greater than the actual ultimate recoverable reserves are determined.

[0143] This embodiment discloses a computer program product, the computer program product including a computer program, and when the computer program is executed by a processor, the following method is implemented:

[0144] Obtain characteristic data of shale gas reservoirs in micro-fractures of rock formations;

[0145] Calculating the characteristic data based on a preset shale gas reservoir recoverable reserves calculation model to obtain a reserves calculation result;

[0146] Wherein, the preset shale gas reservoir recoverable reserves calculation model is obtained by training multiple support vector machine models or multiple neural network models based on sample data;

[0147] According to the reserve calculation results, predicted values ​​corresponding to different possibilities that are greater than the actual ultimate recoverable reserves are determined.

[0148] This embodiment provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following method is implemented:

[0149] Obtain characteristic data of shale gas reservoirs in micro-fractures of rock formations;

[0150] Calculating the characteristic data based on a preset shale gas reservoir recoverable reserves calculation model to obtain a reserves calculation result;

[0151] Wherein, the preset shale gas reservoir recoverable reserves calculation model is obtained by training multiple support vector machine models or multiple neural network models based on sample data;

[0152] According to the reserve calculation results, predicted values ​​corresponding to different possibilities that are greater than the actual ultimate recoverable reserves are determined.

[0153] Compared with the technical solutions in the prior art, the method for detecting the seepage law of shale gas in micro-fractures provided in the embodiment of the present invention obtains characteristic data of shale gas reservoirs in micro-fractures of rock formations; the characteristic data are calculated based on a preset shale gas reservoir recoverable reserves calculation model to obtain a reserve calculation result; wherein the preset shale gas reservoir recoverable reserves calculation model is obtained by training multiple support vector machine models or multiple neural network models based on sample data; and the predicted values ​​corresponding to different possibilities greater than the actual final recoverable reserves are determined according to the reserve calculation result, so that the seepage law of shale gas in micro-fractures can be truly and accurately detected by accurately determining the predicted value of the recoverable reserves of each shale gas reservoir.

[0154] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0155] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0156] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0157] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0158] In the description of this specification, the description with reference to the terms "one embodiment", "a specific embodiment", "some embodiments", "for example", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0159] The specific embodiments described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for detecting the seepage law of shale gas in micro-fractures, characterized in that: include: Obtain characteristic data of shale gas reservoirs in micro-fractures of rock formations; Calculating the characteristic data based on a preset shale gas reservoir recoverable reserves calculation model to obtain a reserves calculation result; Wherein, the preset shale gas reservoir recoverable reserves calculation model is obtained by training multiple support vector machine models or multiple neural network models based on sample data; According to the reserve calculation results, predicted values ​​corresponding to different possibilities that are greater than the actual ultimate recoverable reserves are determined.

2. The method for detecting the seepage law of shale gas in micro-fractures according to claim 1, characterized in that: The method of obtaining characteristic data of shale gas reservoirs in micro-fractures of rock formations includes: At least the porosity, permeability, completion method, drilling parameters, fracture length and conductivity of the shale gas reservoir in the micro-fractures of the rock formation are obtained.

3. The method for detecting the seepage law of shale gas in micro-fractures according to claim 1, characterized in that: The method of obtaining characteristic data of shale gas reservoirs in micro-fractures of rock formations includes: According to the attribute reduction algorithm, attribute data related to the actual ultimate recoverable reserves of the shale gas reservoir in the micro-fractures of the rock formation are obtained from all attribute data of the shale gas reservoir in the micro-fractures of the rock formation as characteristic data.

4. The method for detecting the seepage law of shale gas in micro-fractures according to claim 1, characterized in that: Training multiple support vector machine models or multiple neural network models according to sample data to obtain the preset shale gas reservoir recoverable reserves calculation model includes: Grouping the sample data to obtain a training subsample set corresponding to each group; If it is determined that the number of groups is less than or equal to the preset number of groups, multiple support vector machine models are trained based on the sample data in the training subsample set corresponding to each group to obtain the preset shale gas reservoir recoverable reserves calculation model.

5. The method for detecting the seepage law of shale gas in micro-fractures according to claim 1, characterized in that: Training multiple support vector machine models or multiple neural network models according to sample data to obtain the preset shale gas reservoir recoverable reserves calculation model includes: Grouping the sample data to obtain a training subsample set corresponding to each group; If it is determined that the number of groups is greater than the preset number of groups, multiple neural network models are trained based on the sample data in the training subsample set corresponding to each group to obtain the preset shale gas reservoir recoverable reserves calculation model.

6. The method for detecting the seepage law of shale gas in micro-fractures according to any one of claims 1 to 5, characterized in that: Determining predicted values ​​corresponding to different possibilities of reserves greater than the actual ultimate recoverable reserves according to the reserve calculation results includes: Aggregating multiple reserve calculation results output by multiple support vector machine models or multiple neural network models to obtain a normal distribution diagram reflecting predicted values ​​of the multiple reserve calculation results; A plurality of target prediction values ​​are obtained from the normal distribution diagram, wherein each target prediction value corresponds to a prediction value corresponding to a possibility greater than the actual ultimate recoverable reserves.

7. A device for detecting the seepage law of shale gas in micro-fractures, characterized in that: include: An acquisition unit, used for acquiring characteristic data of shale gas reservoirs in micro-fractures of rock formations; A calculation unit, used to calculate the characteristic data based on a preset shale gas reservoir recoverable reserves calculation model to obtain a reserves calculation result; Wherein, the preset shale gas reservoir recoverable reserves calculation model is obtained by training multiple support vector machine models or multiple neural network models based on sample data; A determination unit is used to determine predicted values ​​corresponding to different possibilities that are greater than the actual ultimate recoverable reserves according to the reserve calculation results.

8. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 6 is implemented.

9. 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 6 is implemented.

10. 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 6 is implemented.

Images