Strike-slip fracture belt configuration prediction method, device and equipment and storage medium

Abstract

The embodiment of the application provides a prediction method, device and equipment of strike-slip fault fracture zone configuration and a storage medium, and relates to the oil and gas exploration technical field.The method comprises the following steps: obtaining a feature sample dictionary, wherein the feature sample dictionary comprises seismic waveforms of a plurality of strike-slip fault fracture zone samples and configurations of the plurality of strike-slip fault fracture zone samples; obtaining a target seismic waveform of a target strike-slip fault fracture zone; extracting the target seismic waveform to obtain seismic data of different waveforms; and performing matching analysis on the seismic data of different waveforms and the feature sample dictionary to determine a predicted configuration of the target strike-slip fault fracture zone. The technical scheme provided by the embodiment of the application can improve the prediction accuracy of the strike-slip fault fracture zone configuration.

Description

Technical Field

[0001] This application relates to the field of oil and gas exploration technology, and in particular to a method, apparatus, equipment and storage medium for predicting strike-slip fracture zone configurations. Background Technology

[0002] Long-term exploration results indicate that oil and natural gas resources are easily enriched in strike-slip fault fracture zones.

[0003] In related technologies, by sending probe waves underground and collecting the waveforms reflected by the strata, relevant technicians analyze and predict the seismic waveforms reflected by the strata based on experience, and determine whether the strata are strike-slip fault fracture zones and the configuration of strike-slip fault fracture zones.

[0004] Among the aforementioned related technologies, predicting the configuration of strike-slip fault fracture zones solely based on human experience, coupled with the high noise levels and low signal-to-noise ratio in the collected seismic waveforms, results in low accuracy in predicting the configuration of strike-slip fault fracture zones when the relevant technical personnel lack sufficient experience. Summary of the Invention

[0005] This application provides a method, apparatus, device, and storage medium for predicting strike-slip fracture zone configurations, which can improve the prediction accuracy of strike-slip fracture zone configurations. The technical solution is as follows:

[0006] According to one aspect of the embodiments of this application, a method for predicting the configuration of a strike-slip fracture zone is provided, the method comprising:

[0007] Obtain a feature sample dictionary, which includes the seismic waveforms of multiple strike-slip fault fracture zone samples and the configurations of the multiple strike-slip fault fracture zone samples;

[0008] Obtain the target seismic waveform of the target strike-slip fault fracture zone;

[0009] The target seismic waveform is extracted to obtain seismic data with different waveforms;

[0010] By matching and analyzing the seismic data with different waveforms and the feature sample dictionary, the predicted configuration of the target strike-slip fault fracture zone is determined.

[0011] Optionally, the target seismic waveform includes data corresponding to seismic waveforms of different frequencies and / or different amplitudes;

[0012] The extraction of the target seismic waveform to obtain seismic data with different waveforms includes at least one of the following:

[0013] The target seismic waveform is subjected to guided filtering to obtain a guided-filtered seismic waveform, and the signal-to-noise ratio of the guided-filtered seismic waveform is better than that of the target seismic waveform.

[0014] The target seismic waveform is subjected to high-frequency filtering to obtain the low-frequency seismic waveform of the target strike-slip fault fracture zone;

[0015] The target seismic waveform is subjected to low-frequency filtering to obtain the high-frequency seismic waveform of the target strike-slip fault fracture zone;

[0016] High-amplitude filtering is applied to the target seismic waveform to obtain the low-amplitude seismic waveform of the target strike-slip fault fracture zone;

[0017] The target seismic waveform is subjected to low-amplitude filtering to obtain the high-amplitude seismic waveform of the target strike-slip fault fracture zone.

[0018] Optionally, the step of matching and analyzing the seismic data of different waveforms with the feature sample dictionary to determine the predicted configuration of the target strike-slip fault fracture zone includes:

[0019] The low-frequency seismic waveform of the target strike-slip fault fracture zone is matched with the feature sample dictionary to obtain the predicted configuration of the target strike-slip fault fracture zone corresponding to the low-frequency seismic waveform.

[0020] The high-frequency seismic waveform of the target strike-slip fault fracture zone is matched with the feature sample dictionary to obtain the predicted configuration of the target strike-slip fault fracture zone corresponding to the high-frequency seismic waveform;

[0021] Based on the predicted configuration of the main fault zone of the target strike-slip fracture zone corresponding to the low-frequency seismic waveform, and the predicted configuration of the branch fault zones and associated fault zones of the target strike-slip fracture zone corresponding to the high-frequency seismic waveform, the predicted configuration of the target strike-slip fracture zone is obtained.

[0022] Optionally, the step of matching and analyzing the seismic data of different waveforms with the feature sample dictionary to determine the predicted configuration of the target strike-slip fault fracture zone includes:

[0023] The low-amplitude seismic waveform of the target strike-slip fault fracture zone is matched with the feature sample dictionary to obtain the predicted configuration of the target strike-slip fault fracture zone corresponding to the low-amplitude seismic waveform.

[0024] The high-amplitude seismic waveform of the target strike-slip fault fracture zone is matched with the feature sample dictionary to obtain the predicted configuration of the target strike-slip fault fracture zone corresponding to the high-amplitude seismic waveform;

[0025] Based on the predicted configuration of the main fault zone of the target strike-slip fracture zone corresponding to the low-amplitude seismic waveform, and the predicted configuration of the branch fault zones and associated fault zones of the target strike-slip fracture zone corresponding to the high-amplitude seismic waveform, the predicted configuration of the target strike-slip fracture zone is obtained.

[0026] Optionally, obtaining the feature sample dictionary includes:

[0027] Obtain the interpretation configuration corresponding to the strike-slip fracture zone sample;

[0028] And / or,

[0029] The configuration of the strike-slip fault fracture zone sample is determined by forward modeling based on the seismic waveform of the sample.

[0030] Optionally, the step of matching and analyzing the seismic data of different waveforms with the feature sample dictionary to determine the predicted configuration of the target strike-slip fault fracture zone includes:

[0031] A convolutional neural network (CNN) is used to match and analyze the filtered seismic waveform with the feature sample dictionary to generate a probabilistic data volume of the target strike-slip fault fracture zone.

[0032] Based on the probabilistic data of the target strike-slip fracture zone, the predicted configuration of the target strike-slip fracture zone is determined.

[0033] According to one aspect of the embodiments of this application, a device for predicting strike-slip fracture zone configuration is provided, the device comprising:

[0034] The dictionary acquisition module is used to acquire a feature sample dictionary, which includes the seismic waveforms of multiple strike-slip fault fracture zone samples and the configurations of the multiple strike-slip fault fracture zone samples.

[0035] The waveform acquisition module is used to acquire the target seismic waveform of the target strike-slip fault fracture zone;

[0036] The waveform extraction module is used to extract the target seismic waveform to obtain seismic data with different waveforms;

[0037] The configuration determination module is used to match and analyze the filtered seismic waveform with the feature sample dictionary to determine the predicted configuration of the target strike-slip fault fracture zone.

[0038] Optionally, the target seismic waveform includes data corresponding to seismic waveforms of different frequencies and / or different amplitudes; the waveform acquisition module is used for:

[0039] The target seismic waveform is subjected to guided filtering to obtain a guided-filtered seismic waveform, and the signal-to-noise ratio of the guided-filtered seismic waveform is better than that of the target seismic waveform.

[0040] The target seismic waveform is subjected to high-frequency filtering to obtain the low-frequency seismic waveform of the target strike-slip fault fracture zone;

[0041] The target seismic waveform is subjected to low-frequency filtering to obtain the high-frequency seismic waveform of the target strike-slip fault fracture zone;

[0042] High-amplitude filtering is applied to the target seismic waveform to obtain the low-amplitude seismic waveform of the target strike-slip fault fracture zone;

[0043] The target seismic waveform is subjected to low-amplitude filtering to obtain the high-amplitude seismic waveform of the target strike-slip fault fracture zone.

[0044] Optionally, the configuration determination module is used to:

[0045] The low-frequency seismic waveform of the target strike-slip fault fracture zone is matched with the feature sample dictionary to obtain the predicted configuration of the target strike-slip fault fracture zone corresponding to the low-frequency seismic waveform.

[0046] The high-frequency seismic waveform of the target strike-slip fault fracture zone is matched with the feature sample dictionary to obtain the predicted configuration of the target strike-slip fault fracture zone corresponding to the high-frequency seismic waveform;

[0047] Based on the predicted configuration of the main fault zone of the target strike-slip fracture zone corresponding to the low-frequency seismic waveform, and the predicted configuration of the branch fault zones and associated fault zones of the target strike-slip fracture zone corresponding to the high-frequency seismic waveform, the predicted configuration of the target strike-slip fracture zone is obtained.

[0048] Optionally, the configuration determination module is used to:

[0049] The low-amplitude seismic waveform of the target strike-slip fault fracture zone is matched with the feature sample dictionary to obtain the predicted configuration of the target strike-slip fault fracture zone corresponding to the low-amplitude seismic waveform.

[0050] The high-amplitude seismic waveform of the target strike-slip fault fracture zone is matched with the feature sample dictionary to obtain the predicted configuration of the target strike-slip fault fracture zone corresponding to the high-amplitude seismic waveform;

[0051] Based on the predicted configuration of the main fault zone of the target strike-slip fracture zone corresponding to the low-amplitude seismic waveform, and the predicted configuration of the branch fault zones and associated fault zones of the target strike-slip fracture zone corresponding to the high-amplitude seismic waveform, the predicted configuration of the target strike-slip fracture zone is obtained.

[0052] Optionally, the dictionary acquisition module is used for:

[0053] Obtain the interpretation configuration corresponding to the strike-slip fracture zone sample;

[0054] And / or,

[0055] The configuration of the strike-slip fault fracture zone sample is determined by forward modeling based on the seismic waveform of the sample.

[0056] Optionally, the configuration determination module is used to:

[0057] A convolutional neural network is used to match and analyze the filtered seismic waveform with the feature sample dictionary to generate a probabilistic data volume of the target strike-slip fault fracture zone.

[0058] Based on the probabilistic data of the target strike-slip fracture zone, the predicted configuration of the target strike-slip fracture zone is determined.

[0059] According to one aspect of the embodiments of this application, a computer device is provided, the computer device including a processor and a memory, the memory storing a computer program, the computer program being loaded and executed by the processor to implement the above-described method for predicting strike-slip fracture zone configurations.

[0060] According to one aspect of the present application, a computer-readable storage medium is provided, wherein a computer program is stored in the computer-readable storage medium, the computer program being loaded and executed by a processor to implement the above-described method for predicting strike-slip fracture zone configurations.

[0061] According to one aspect of the embodiments of this application, a computer program product is provided, which is loaded and executed by a processor to implement the above-described method for predicting strike-slip fracture zone configurations.

[0062] The technical solutions provided in this application embodiment may have the following beneficial effects:

[0063] A feature sample dictionary is established by using the configurations of multiple strike-slip fault fracture zone samples and their corresponding seismic waveforms. This feature sample dictionary becomes a knowledge base of the relationship between the configurations of strike-slip fault fracture zones and their corresponding seismic waves. Compared with the configurations of strike-slip fault fracture zones predicted based on human experience, matching and analyzing seismic waveforms with the feature sample dictionary yields more accurate predictions of the configurations of strike-slip fault fracture zones, thereby improving the prediction accuracy of strike-slip fault fracture zone configurations.

[0064] In addition, the technical solution provided in this application does not rely on the experience of relevant technical personnel. By matching and analyzing the target seismic waveform with the feature sample dictionary, a high-precision predicted configuration of the strike-slip fault fracture zone can be automatically generated, thereby improving the stability of the prediction accuracy of the strike-slip fault fracture zone configuration.

[0065] In addition, since the target seismic waves were filtered before predicting the configuration of the target strike-slip fault fracture zone, the signal-to-noise ratio of the target seismic waves was improved, which further improved the prediction accuracy of the strike-slip fault fracture zone configuration.

[0066] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0067] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0068] Figure 1 This is a flowchart of a method for predicting the configuration of a strike-slip fracture zone according to an embodiment of this application;

[0069] Figure 2 This is a schematic seismic profile of a strike-slip fault fracture zone provided in one embodiment of this application;

[0070] Figure 3 This is a schematic diagram of the forward modeling of a strike-slip fault fracture zone provided in one embodiment of this application;

[0071] Figure 4 This is a schematic diagram of a strike-slip fracture zone provided in one embodiment of this application;

[0072] Figure 5 This is a schematic diagram of the predicted configuration of a strike-slip fracture zone provided in one embodiment of this application;

[0073] Figure 6This is a block diagram of a device for predicting strike-slip fracture zone configuration according to an embodiment of this application;

[0074] Figure 7 This is a block diagram of a computer device provided in one embodiment of this application. Detailed Implementation

[0075] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of methods consistent with some aspects of this application as detailed in the appended claims.

[0076] The method provided in this application can be executed by a computer device, which refers to an electronic device with data computing, processing, and storage capabilities. This computer device can be a terminal such as a PC (Personal Computer), tablet computer, smartphone, wearable device, or intelligent robot; or it can be a server. The server can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0077] The technical solution of this application will be described and illustrated below through several embodiments.

[0078] Please refer to Figure 1 This document illustrates a flowchart of a method for predicting strike-slip fracture zone configuration according to an embodiment of this application. In this embodiment, the method is primarily illustrated by its application to the computer device described above. The method may include the following steps (101-104):

[0079] Step 101: Obtain the feature sample dictionary, which includes the seismic waveforms of multiple strike-slip fault fracture zone samples and the configurations of multiple strike-slip fault fracture zone samples.

[0080] In some embodiments, a feature sample dictionary is constructed based on multiple existing strike-slip fault fracture zone samples with high-precision predicted configurations and their corresponding seismic waveforms. The seismic waveforms of the strike-slip fault fracture zone samples may include: unfiltered seismic waveforms and / or filtered seismic waveforms.

[0081] Optionally, the strike-slip fracture zone sample has a three-dimensional configuration.

[0082] In some embodiments, the interpretation configuration corresponding to the strike-slip fault fracture zone sample is obtained. Based on the original seismic data (i.e., seismic waveforms), a detailed interpretation can be performed on different morphologies of the strike-slip fault fracture zone, revealing the geometric configuration, positive and negative flower-like features, and characteristics of the main fault and associated secondary faults within the target stratum. Figure 2 As shown, fracture 11 is the main fracture, and fracture 12 is the associated fracture.

[0083] In some embodiments, the configuration of a strike-slip fault fracture zone sample is determined based on the seismic waveform of the sample through forward modeling of a seismic model.

[0084] In some embodiments, forward modeling of a seismic model can refer to: after obtaining the actual seismic waveform of a strike-slip fault fracture zone sample, relevant technicians construct a simulated configuration of the strike-slip fault fracture zone, and simulate the seismic waveform corresponding to the simulated configuration of the strike-slip fault fracture zone using relevant applications; comparing the simulated seismic waveform with the actual seismic waveform, and adjusting the simulated configuration of the strike-slip fault fracture zone sample based on the waveform comparison results; until the final simulated seismic waveform is the same as or similar to the actual seismic waveform, the strike-slip fault fracture zone configuration corresponding to the final simulated seismic waveform can be determined as the configuration of the strike-slip fault fracture zone sample. Figure 3 As shown, by continuously adjusting the forward model (i.e., the simulated configuration of the strike-slip fault fracture zone) 13, the forward modeling seismic data (i.e., seismic waveforms) 14 corresponding to the forward model 13 are made as close as possible to the actual seismic waveforms, thereby obtaining the configuration of the strike-slip fault fracture zone sample through forward modeling of the seismic model.

[0085] The similarity threshold between the simulated earthquake waveform and the actual earthquake waveform can be set by relevant technical personnel according to the actual situation, and this application embodiment does not make specific limitations on this.

[0086] In some embodiments, the feature sample dictionary contains as many geometric features as possible of the strike-slip fracture zone.

[0087] Step 102: Obtain the target seismic waveform of the target strike-slip fault fracture zone.

[0088] In some embodiments, a probe wave is sent to the target strike-slip fault fracture zone and the seismic waveforms reflected (or returned) by the strata are collected to obtain the target seismic waveform.

[0089] In some embodiments, probe waves of multiple frequencies and / or multiple amplitudes are emitted toward the target strike-slip fault fracture zone strata, and seismic waveforms corresponding to probe waves of different frequencies and / or different amplitudes are collected respectively. Therefore, the target seismic waveforms may include multiple sets of seismic waveforms.

[0090] Step 103: Extract the target seismic waveform to obtain seismic data with different waveforms.

[0091] In some embodiments, the target seismic waveform is extracted by filtering. Optionally, the target seismic waveform is filtered based on the resulting seismic data to obtain filtered seismic waveforms and seismic data with different waveforms. For example, filtering is performed based on different frequency bands to obtain multiple sets of seismic waveforms reflecting faults at different scales.

[0092] In some embodiments, to enable more accurate and precise automatic identification of strike-slip fault fracture zone configurations, a high signal-to-noise ratio (SNR) is required in the seismic data used (i.e., seismic waveforms). In some embodiments, guided filtering is applied to the target seismic waveform to obtain a guided-filtered seismic waveform, which has a higher SNR than the target seismic waveform. That is, noise in the target seismic waveform is filtered out, thereby improving the SNR of the target seismic waveform.

[0093] In some embodiments, the target seismic waveform includes data corresponding to seismic waveforms of different frequencies and / or different amplitudes. Step 103 above includes at least one of the following:

[0094] The target seismic waveform is subjected to guided filtering to obtain the guided-filtered seismic waveform. The signal-to-noise ratio of the guided-filtered seismic waveform is better than that of the target seismic waveform.

[0095] High-frequency filtering is applied to the target seismic waveform to obtain the low-frequency seismic waveform of the target strike-slip fault fracture zone;

[0096] Low-frequency filtering is applied to the target seismic waveform to obtain the high-frequency seismic waveform of the target strike-slip fault fracture zone;

[0097] High-amplitude filtering is applied to the target seismic waveform to obtain the low-amplitude seismic waveform of the target strike-slip fault fracture zone;

[0098] Low-amplitude filtering is applied to the target seismic waveform to obtain the high-amplitude seismic waveform of the target strike-slip fault fracture zone.

[0099] Step 104: Match and analyze the seismic data of different waveforms with the feature sample dictionary to determine the predicted configuration of the target strike-slip fault fracture zone.

[0100] In some embodiments, the filtered seismic waveform is matched with a feature sample dictionary to determine the predicted configuration of the target strike-slip fault fracture zone.

[0101] In some embodiments, step 104 includes the following sub-steps:

[0102] 1. Match the low-frequency seismic waveform of the target strike-slip fault fracture zone with the feature sample dictionary to obtain the predicted configuration of the target strike-slip fault fracture zone corresponding to the low-frequency seismic waveform;

[0103] 2. Match the high-frequency seismic waveform of the target strike-slip fault fracture zone with the feature sample dictionary to obtain the predicted configuration of the target strike-slip fault fracture zone corresponding to the high-frequency seismic waveform;

[0104] 3. Based on the predicted configuration of the main fault zone of the target strike-slip fault fracture zone corresponding to the low-frequency seismic waveform, and the predicted configuration of the branch fault zones and associated fault zones of the target strike-slip fault fracture zone corresponding to the high-frequency seismic waveform, the predicted configuration of the target strike-slip fault fracture zone is obtained.

[0105] Because low-frequency seismic waveforms are suitable for predicting the configuration of faults with large scales, and the predicted configuration based on high-frequency seismic waveforms provides a better description of the details of the fault zone, after obtaining the predicted configuration of the target strike-slip fault fracture zone corresponding to low-frequency seismic waveforms, only the main fault zone is retained; after obtaining the predicted configuration of the target strike-slip fault fracture zone corresponding to high-frequency seismic waveforms, only the branch fault zones and associated fault zones are retained. These portions of the main fault zone, as well as the portions of the branch and associated fault zones, are combined to form the predicted configuration of the target strike-slip fault fracture zone. This simultaneously ensures that the predicted configuration of the target strike-slip fault fracture zone has fewer interfering details in the main fault zone and higher accuracy in the branch and associated fault zones.

[0106] In some possible implementations, step 104 above includes the following sub-steps:

[0107] 1. Match the low-amplitude seismic waveform of the target strike-slip fault fracture zone with the feature sample dictionary to obtain the predicted configuration of the target strike-slip fault fracture zone corresponding to the low-amplitude seismic waveform;

[0108] 2. Match the high-amplitude seismic waveforms of the target strike-slip fault fracture zone with the feature sample dictionary to obtain the predicted configuration of the target strike-slip fault fracture zone corresponding to the high-amplitude seismic waveforms;

[0109] 3. Based on the predicted configuration of the main fault zone of the target strike-slip fault fracture zone corresponding to the low-amplitude seismic waveform, and the predicted configuration of the branch fault zones and associated fault zones of the target strike-slip fault fracture zone corresponding to the high-amplitude seismic waveform, the predicted configuration of the target strike-slip fault fracture zone is obtained.

[0110] Because low-amplitude seismic waveforms are suitable for predicting the configuration of faults with large scales, while the predicted configuration based on high-amplitude seismic waveforms provides a better description of the details of the fault zone, after obtaining the predicted configuration of the target strike-slip fault fracture zone corresponding to low-amplitude seismic waveforms, only the main fault zone is retained; after obtaining the predicted configuration of the target strike-slip fault fracture zone corresponding to high-amplitude seismic waveforms, only the branch fault zones and associated fault zones are retained. These portions of the main fault zone, as well as the portions of the branch and associated fault zones, are combined to form the predicted configuration of the target strike-slip fault fracture zone. This simultaneously ensures that the predicted configuration of the target strike-slip fault fracture zone has fewer interfering details in the main fault zone and higher accuracy in the branch and associated fault zones.

[0111] In some embodiments, such as Figure 4 As shown, for a certain depression in the northern part of a basin, the predicted configuration of the strike-slip fault fracture zone is 15 when the amplitude of the seismic waveform is -3000 to 3000, and 16 when the amplitude of the seismic waveform is -2000 to 2000. It is easy to see that the smaller the amplitude range of the seismic waveform, the more detailed features are in the predicted configuration.

[0112] In some embodiments, a convolutional neural network is used to match and analyze the filtered seismic waveform with a feature sample dictionary to generate a probabilistic data volume of the target strike-slip fault fracture zone. Based on the probabilistic data volume of the target strike-slip fault fracture zone, the predicted configuration of the target strike-slip fault fracture zone is determined. That is, the filtered seismic waveform is input into the convolutional neural network, and the convolutional neural network will output the predicted configuration corresponding to the filtered seismic waveform (i.e., the predicted configuration of the target strike-slip fault fracture zone).

[0113] In some embodiments, seismic waveforms of different frequency bands are input into a convolutional neural network to obtain prediction configurations corresponding to multiple frequency bands. The parts with better prediction performance in each prediction configuration are retained, and the retained parts in each prediction configuration are combined to obtain the prediction configuration of the target strike-slip fault fracture zone.

[0114] In some embodiments, a convolutional neural network is used for automatic identification of strike-slip fracture zones, with an input layer of V, a kernel function of K, and an output feature map of Z. This convolutional function can then be defined as follows: (Formula 1)

[0115] (Formula 1)

[0116] Where K is the kernel tensor, V represents the kernel tensor of the i-th element, and V identifies the input data (i.e., the input seismic waveform). This represents the value in the (j+m-1)th row and (k+n-1)th column of channel l. The output Z is related to... They are in the same form.

[0117] Because the input data is too large, it is necessary to reduce the computational load by skipping some positions in the kernel. Therefore, it is necessary to downsample the output of the fully convolutional function. The downsampled convolutional function c is defined as shown in Formula 2 below:

[0118] (Formula 2)

[0119] Where K is the kernel function, V is the input data, Z is the output data, and s is the stride interval in each direction of the output. Based on this, the weights in the kernel are differentiated (as shown in Formula 3 below) to train a convolution with stride s and kernel K, applied to a multi-channel image V, defined as c(K,V,s) in Formula 2, where G is the tensor obtained in backpropagation, and J(V,K) is the loss function.

[0120] (Formula 3)

[0121] Based on this, preprocessed seismic data (such as filtered seismic waveforms) are matched with a 3D seismic model to obtain a probability data volume for strike-slip fracture zones with probability values ​​belonging to the [0, 1] interval. The strike-slip fracture zone configuration identification data volume is then calibrated with drilling anomalies to determine a data threshold. Based on this threshold, the data volume is sculpted to obtain the predicted configuration of the target strike-slip fracture zone (also known as the 3D spatial sculpted body of the target strike-slip fracture zone). For example, as... Figure 5 As shown in Figure 17, based on the feature map of the strike-slip fracture zone, points with probability values ​​greater than or equal to the data threshold are assigned the value 1, and points with probability values ​​less than the data threshold are assigned the value 0. By performing three-dimensional spatial sculpting, the three-dimensional predicted configuration 18 of the target strike-slip fracture zone can be obtained.

[0122] In summary, the technical solution provided in this application establishes a feature sample dictionary by using the configurations of multiple strike-slip fault fracture zone samples and their corresponding seismic waveforms. This feature sample dictionary becomes a knowledge base of the relationship between the configuration of a strike-slip fault fracture zone and its corresponding seismic waves. Compared to the configuration of a strike-slip fault fracture zone predicted based on human experience, the predicted configuration of the target strike-slip fault fracture zone obtained by matching and analyzing the target seismic waveform with the feature sample dictionary has higher accuracy, thereby improving the prediction accuracy of the strike-slip fault fracture zone configuration.

[0123] In addition, the technical solution provided in this application does not rely on the experience of relevant technical personnel. By matching and analyzing the target seismic waveform with the feature sample dictionary, a high-precision predicted configuration of the strike-slip fault fracture zone can be automatically generated, thereby improving the stability of the prediction accuracy of the strike-slip fault fracture zone configuration.

[0124] In addition, since the target seismic waves were filtered before predicting the configuration of the target strike-slip fault fracture zone, the signal-to-noise ratio of the target seismic waves was improved, which further improved the prediction accuracy of the strike-slip fault fracture zone configuration.

[0125] This application's embodiments can three-dimensionally and intuitively reflect the spatial configuration characteristics of strike-slip fracture zones. Based on characterizing the longitudinal development differences of strike-slip fracture zones, including their thickness, continuity, segmentation, and connection patterns, a quantitative description is provided. This scheme was applied in an oilfield within a basin, with good results, reflecting the characteristics of strike-slip fracture zones with main fractures as the core, secondary fractures as the framework, and micro-fractures as the veins, providing a basis for analyzing the source and oil and gas transport capacity of strike-slip fractures. Based on this scheme, more accurate and detailed trap description work was achieved in this oilfield, identifying 40 new traps, deploying over 50 wells of various types, achieving a reservoir encounter rate of 96%, a drilling success rate of 95%, and a high-efficiency well ratio of 66%, providing strong support for further well deployment and comprehensive management in this oilfield.

[0126] In this application embodiment, "configuration" refers to the comprehensive term of the geological structure and physical property differences of the complex three-dimensional internal fracture network of the fault zone; "reservoir encounter rate" refers to the ratio of the number of wells with developed reservoirs due to drill string bleed, drilling fluid loss, or logging interpretation during the drilling process to the total number of wells drilled; "drilling success rate" refers to the ratio of the number of wells that obtained industrial oil and gas flow after drilling, completion, and oil testing operations to the total number of wells drilled; "high-efficiency well" refers to the ratio of the number of wells that achieved a cumulative oil and gas production of 50,000 tons after oil testing operations to the total number of wells that obtained industrial oil and gas flow.

[0127] The following are embodiments of the apparatus described in this application, which can be used to execute the embodiments of the method described in this application. For details not disclosed in the apparatus embodiments of this application, please refer to the embodiments of the method described in this application.

[0128] Please refer to Figure 6 This diagram illustrates a block diagram of a device for predicting strike-slip fracture zone configurations according to an embodiment of this application. The device has the functionality to implement the aforementioned example of a method for predicting strike-slip fracture zone configurations. This functionality can be implemented in hardware or by hardware executing corresponding software. The device can be the computer device described above, or it can be mounted on a computer device. The device 600 may include: a dictionary acquisition module 610, a waveform acquisition module 620, a waveform extraction module 630, and a configuration determination module 640.

[0129] The dictionary acquisition module 610 is used to acquire a feature sample dictionary, which includes the seismic waveforms of multiple strike-slip fault fracture zone samples and the configurations of the multiple strike-slip fault fracture zone samples.

[0130] The waveform acquisition module 620 is used to acquire the target seismic waveform of the target strike-slip fault fracture zone;

[0131] The waveform extraction module 630 is used to extract the target seismic waveform to obtain seismic data with different waveforms;

[0132] The configuration determination module 640 is used to match and analyze the seismic data of different waveforms with the feature sample dictionary to determine the predicted configuration of the target strike-slip fault fracture zone.

[0133] In some embodiments, the target seismic waveform includes data corresponding to seismic waveforms of different frequencies and / or different amplitudes; the waveform extraction module 630 is used for:

[0134] The target seismic waveform is subjected to guided filtering to obtain a guided-filtered seismic waveform, and the signal-to-noise ratio of the guided-filtered seismic waveform is better than that of the target seismic waveform.

[0135] The target seismic waveform is subjected to high-frequency filtering to obtain the low-frequency seismic waveform of the target strike-slip fault fracture zone;

[0136] The target seismic waveform is subjected to low-frequency filtering to obtain the high-frequency seismic waveform of the target strike-slip fault fracture zone;

[0137] High-amplitude filtering is applied to the target seismic waveform to obtain the low-amplitude seismic waveform of the target strike-slip fault fracture zone;

[0138] The target seismic waveform is subjected to low-amplitude filtering to obtain the high-amplitude seismic waveform of the target strike-slip fault fracture zone.

[0139] In some embodiments, the configuration determination module 640 is configured to:

[0140] The low-frequency seismic waveform of the target strike-slip fault fracture zone is matched with the feature sample dictionary to obtain the predicted configuration of the target strike-slip fault fracture zone corresponding to the low-frequency seismic waveform.

[0141] The high-frequency seismic waveform of the target strike-slip fault fracture zone is matched with the feature sample dictionary to obtain the predicted configuration of the target strike-slip fault fracture zone corresponding to the high-frequency seismic waveform;

[0142] Based on the predicted configuration of the main fault zone of the target strike-slip fracture zone corresponding to the low-frequency seismic waveform, and the predicted configuration of the branch fault zones and associated fault zones of the target strike-slip fracture zone corresponding to the high-frequency seismic waveform, the predicted configuration of the target strike-slip fracture zone is obtained.

[0143] In some embodiments, the configuration determination module 640 is configured to:

[0144] The low-amplitude seismic waveform of the target strike-slip fault fracture zone is matched with the feature sample dictionary to obtain the predicted configuration of the target strike-slip fault fracture zone corresponding to the low-amplitude seismic waveform.

[0145] The high-amplitude seismic waveform of the target strike-slip fault fracture zone is matched with the feature sample dictionary to obtain the predicted configuration of the target strike-slip fault fracture zone corresponding to the high-amplitude seismic waveform;

[0146] Based on the predicted configuration of the main fault zone of the target strike-slip fracture zone corresponding to the low-amplitude seismic waveform, and the predicted configuration of the branch fault zones and associated fault zones of the target strike-slip fracture zone corresponding to the high-amplitude seismic waveform, the predicted configuration of the target strike-slip fracture zone is obtained.

[0147] In some embodiments, the dictionary acquisition module 610 is configured to:

[0148] Obtain the interpretation configuration corresponding to the strike-slip fracture zone sample;

[0149] And / or,

[0150] The configuration of the strike-slip fault fracture zone sample is determined by forward modeling based on the seismic waveform of the sample.

[0151] In some embodiments, the configuration determination module 640 is configured to:

[0152] A convolutional neural network is used to match and analyze the filtered seismic waveform with the feature sample dictionary to generate a probabilistic data volume of the target strike-slip fault fracture zone.

[0153] Based on the probabilistic data of the target strike-slip fracture zone, the predicted configuration of the target strike-slip fracture zone is determined.

[0154] In summary, the technical solution provided in this application establishes a feature sample dictionary by using the configurations of multiple strike-slip fault fracture zone samples and their corresponding seismic waveforms. This feature sample dictionary becomes a knowledge base of the relationship between the configuration of a strike-slip fault fracture zone and its corresponding seismic waves. Compared to the configuration of a strike-slip fault fracture zone predicted based on human experience, the predicted configuration of the target strike-slip fault fracture zone obtained by matching and analyzing the target seismic waveform with the feature sample dictionary has higher accuracy, thereby improving the prediction accuracy of the strike-slip fault fracture zone configuration.

[0155] It should be noted that the apparatus provided in the above embodiments is only illustrated by the division of the above functional modules when implementing its functions. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the apparatus and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process can be found in the method embodiments, which will not be repeated here.

[0156] Please refer to Figure 7 This diagram illustrates the structural block diagram of a computer device according to an embodiment of this application. The computer device is used to implement the method for predicting strike-slip fracture zone configurations provided in the above embodiments. Specifically:

[0157] The computer device 700 includes a CPU (Central Processing Unit) 701, a system memory 704 including RAM (Random Access Memory) 702 and ROM (Read-Only Memory) 703, and a system bus 705 connecting the system memory 704 and the central processing unit 701. The computer device 700 also includes a basic I / O (Input / Output) system 706 that facilitates information transfer between various components within the computer, and a mass storage device 707 for storing the operating system 713, application programs 714, and other program modules 715.

[0158] The basic input / output system 706 includes a display 708 for displaying information and an input device 709 for user input, such as a mouse or keyboard. Both the display 708 and the input device 709 are connected to the central processing unit 701 via an input / output controller 710 connected to the system bus 705. The basic input / output system 706 may also include the input / output controller 710 for receiving and processing input from multiple other devices such as a keyboard, mouse, or electronic stylus. Similarly, the input / output controller 710 also provides output to a display screen, printer, or other types of output devices.

[0159] The mass storage device 707 is connected to the central processing unit 701 via a mass storage controller (not shown) connected to the system bus 705. The mass storage device 707 and its associated computer-readable media provide non-volatile storage for the computer device 700. That is, the mass storage device 707 may include computer-readable media (not shown) such as a hard disk or a CD-ROM (Compact Disc Read-Only Memory) drive.

[0160] Without loss of generality, the computer-readable medium may include computer storage media and communication media. Computer storage media include volatile and non-volatile, removable and non-removable media implemented using any method or technology for storing information such as computer-readable instructions, data structures, program modules, or other data. Computer storage media include RAM, ROM, EPROM (Erasable Programmable Read Only Memory), EEPROM (Electrically Erasable Programmable Read Only Memory), flash memory or other solid-state storage, CD-ROM, DVD (Digital Video Disc) or other optical storage, magnetic tape cassettes, magnetic tape, disk storage, or other magnetic storage devices. Of course, those skilled in the art will recognize that the computer storage media are not limited to the above-mentioned types. The system memory 704 and mass storage device 707 described above can be collectively referred to as memory.

[0161] According to various embodiments of this application, the computer device 700 can also be connected to a remote computer on a network, such as the Internet. That is, the computer device 700 can be connected to a network 712 via a network interface unit 711 connected to the system bus 705, or the network interface unit 711 can be used to connect to other types of networks or remote computer systems (not shown).

[0162] In an exemplary embodiment, a computer-readable storage medium is also provided, wherein a computer program is stored therein, which, when executed by a processor, implements the above-described method for predicting the strike-slip fracture zone configuration.

[0163] In an exemplary embodiment, a computer program product is also provided, which is loaded and executed by a processor to implement the above-described method for predicting the strike-slip fracture zone configuration.

[0164] It should be understood that "multiple" as used in this article refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. The character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0165] The above description is merely an exemplary embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for predicting the configuration of strike-slip fracture zones, characterized in that, The method includes: Obtain a feature sample dictionary, which includes the seismic waveforms of multiple strike-slip fault fracture zone samples and the configurations of the multiple strike-slip fault fracture zone samples; Acquire the target seismic waveform of the target strike-slip fault fracture zone, wherein the target seismic waveform includes data corresponding to seismic waveforms of different frequencies and / or different amplitudes; The target seismic waveform is extracted to obtain seismic data with different waveforms; wherein, the extraction of the target seismic waveform to obtain seismic data with different waveforms includes at least one of the following: The target seismic waveform is subjected to guided filtering to obtain a guided-filtered seismic waveform, and the signal-to-noise ratio of the guided-filtered seismic waveform is better than that of the target seismic waveform. The target seismic waveform is subjected to high-frequency filtering to obtain the low-frequency seismic waveform of the target strike-slip fault fracture zone; The target seismic waveform is subjected to low-frequency filtering to obtain the high-frequency seismic waveform of the target strike-slip fault fracture zone; High-amplitude filtering is applied to the target seismic waveform to obtain the low-amplitude seismic waveform of the target strike-slip fault fracture zone; Low-amplitude filtering is applied to the target seismic waveform to obtain the high-amplitude seismic waveform of the target strike-slip fault fracture zone; Matching and analyzing the seismic data of different waveforms with the feature sample dictionary to determine the predicted configuration of the target strike-slip fault fracture zone; wherein, the matching and analysis of the seismic data of different waveforms with the feature sample dictionary to determine the predicted configuration of the target strike-slip fault fracture zone includes: The low-frequency seismic waveform of the target strike-slip fault fracture zone is matched with the feature sample dictionary to obtain the predicted configuration of the target strike-slip fault fracture zone corresponding to the low-frequency seismic waveform; the high-frequency seismic waveform of the target strike-slip fault fracture zone is matched with the feature sample dictionary to obtain the predicted configuration of the target strike-slip fault fracture zone corresponding to the high-frequency seismic waveform; based on the predicted configuration of the main fault zone of the target strike-slip fault fracture zone corresponding to the low-frequency seismic waveform, and the predicted configuration of the branch fault zones and associated fault zones of the target strike-slip fault fracture zone corresponding to the high-frequency seismic waveform, the predicted configuration of the target strike-slip fault fracture zone is obtained. The low-amplitude seismic waveform of the target strike-slip fault fracture zone is matched with the feature sample dictionary to obtain the predicted configuration of the target strike-slip fault fracture zone corresponding to the low-amplitude seismic waveform; the high-amplitude seismic waveform of the target strike-slip fault fracture zone is matched with the feature sample dictionary to obtain the predicted configuration of the target strike-slip fault fracture zone corresponding to the high-amplitude seismic waveform; based on the predicted configuration of the main fault zone of the target strike-slip fault fracture zone corresponding to the low-amplitude seismic waveform, and the predicted configuration of the branch fault zones and associated fault zones of the target strike-slip fault fracture zone corresponding to the high-amplitude seismic waveform, the predicted configuration of the target strike-slip fault fracture zone is obtained.

2. The method according to claim 1, characterized in that, The process of obtaining the feature sample dictionary includes: Obtain the interpretation configuration corresponding to the strike-slip fracture zone sample; And / or, The configuration of the strike-slip fault fracture zone sample is determined by forward modeling based on the seismic waveform of the sample.

3. The method according to claim 1, characterized in that, The step of matching and analyzing the seismic data of different waveforms with the feature sample dictionary to determine the predicted configuration of the target strike-slip fault fracture zone includes: A convolutional neural network is used to match and analyze the filtered seismic waveform with the feature sample dictionary to generate a probabilistic data volume of the target strike-slip fault fracture zone. Based on the probabilistic data of the target strike-slip fracture zone, the predicted configuration of the target strike-slip fracture zone is determined.

4. A device for predicting the configuration of a strike-slip fracture zone, characterized in that, The device includes: The dictionary acquisition module is used to acquire a feature sample dictionary, which includes the seismic waveforms of multiple strike-slip fault fracture zone samples and the configurations of the multiple strike-slip fault fracture zone samples. The waveform acquisition module is used to acquire the target seismic waveform of the target strike-slip fault fracture zone, wherein the target seismic waveform includes data corresponding to seismic waveforms of different frequencies and / or different amplitudes; A waveform extraction module is used to extract the target seismic waveform to obtain seismic data with different waveforms. Specifically, the waveform extraction module performs guided filtering on the target seismic waveform to obtain a guided-filtered seismic waveform with a signal-to-noise ratio superior to the target seismic waveform; performs high-frequency filtering on the target seismic waveform to obtain a low-frequency seismic waveform of the target strike-slip fault fracture zone; performs low-frequency filtering on the target seismic waveform to obtain a high-frequency seismic waveform of the target strike-slip fault fracture zone; performs high-amplitude filtering on the target seismic waveform to obtain a low-amplitude seismic waveform of the target strike-slip fault fracture zone; and performs low-amplitude filtering on the target seismic waveform to obtain a high-amplitude seismic waveform of the target strike-slip fault fracture zone. The configuration determination module is used to match and analyze the seismic data of different waveforms with the feature sample dictionary to determine the predicted configuration of the target strike-slip fault fracture zone; wherein, the configuration determination module is used to match the low-frequency seismic waveform of the target strike-slip fault fracture zone with the feature sample dictionary to obtain the predicted configuration of the target strike-slip fault fracture zone corresponding to the low-frequency seismic waveform; match the high-frequency seismic waveform of the target strike-slip fault fracture zone with the feature sample dictionary to obtain the predicted configuration of the target strike-slip fault fracture zone corresponding to the high-frequency seismic waveform; based on the predicted configuration of the main fault zone of the target strike-slip fault fracture zone corresponding to the low-frequency seismic waveform, and the branch fault zones and associated fault zones of the target strike-slip fault fracture zone corresponding to the predicted configuration of the target strike-slip fault fracture zone, the configuration is determined by matching the low-frequency seismic waveform of the main fault zone of the target strike-slip fault fracture zone with the feature sample dictionary to obtain the predicted configuration of the target strike-slip fault fracture zone corresponding to the low-frequency seismic waveform; The predicted configuration of the high-frequency seismic waveform is used to obtain the predicted configuration of the target strike-slip fault fracture zone. The low-amplitude seismic waveform of the target strike-slip fault fracture zone is matched with the feature sample dictionary to obtain the predicted configuration of the target strike-slip fault fracture zone corresponding to the low-amplitude seismic waveform. The high-amplitude seismic waveform of the target strike-slip fault fracture zone is matched with the feature sample dictionary to obtain the predicted configuration of the target strike-slip fault fracture zone corresponding to the high-amplitude seismic waveform. Based on the predicted configuration of the main fault zone of the target strike-slip fault fracture zone corresponding to the low-amplitude seismic waveform, and the predicted configuration of the branch fault zones and associated fault zones of the target strike-slip fault fracture zone corresponding to the high-amplitude seismic waveform, the predicted configuration of the target strike-slip fault fracture zone is obtained.

5. A computer device, characterized in that, The computer device includes a processor and a memory, the memory storing a computer program, which is loaded and executed by the processor to implement the method for predicting the strike-slip fracture zone configuration as described in any one of claims 1 to 3.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, which is loaded and executed by a processor to implement the method for predicting the strike-slip fracture zone configuration as described in any one of claims 1 to 3.

7. A computer program product, characterized in that, The computer program product is loaded and executed by a processor to implement the method for predicting the strike-slip fracture zone configuration as described in any one of claims 1 to 3.

Images