Intelligent node seismograph and method for oil exploration

Abstract

The present application provides an intelligent node seismograph and method for oil exploration. The present application extracts wave impedance characteristics of each auxiliary waveform data based on seismic waveform data to obtain the wave impedance attenuation coefficient corresponding to each sub-node, and determines the azimuth weight corresponding to each sub-node according to the wave impedance attenuation coefficient corresponding to each sub-node and the azimuth interval in which it is located; then, a correlation model corresponding to each sub-node is constructed respectively, and seismic waveform data is auxiliary corrected according to all the correlation models to obtain seismic wave correction data; finally, the seismic wave correction data is used to perform data inversion, and the oil reservoir distribution in the target exploration area is predicted based on the inversion result, and the auxiliary waveform data can be collected to construct the correlation model and the seismic waveform data can be auxiliary corrected, thereby reducing the interference of underground rock fractures in the oil exploration process and improving the accuracy of oil exploration.

Description

Technical Field

[0001] The present application relates to the technical field of oil exploration, and more specifically, to an intelligent node seismograph and method for oil exploration. Background Art

[0002] Seismic exploration technology is to artificially stimulate seismic waves to propagate downward from the surface. During the propagation process, due to the differences in lithology and media between strata, seismic waves will be reflected and refracted to varying degrees. These reflected and refracted signals can be collected and analyzed by seismic exploration detectors, and combined with seismic wave theory, the lithology and resource distribution of the strata can be studied, thereby realizing the exploration and measurement of oil resources.

[0003] Existing experimental and theoretical studies have shown that rock cracks have a significant impact on longitudinal wave scattering, dispersion and attenuation during seismic wave propagation, especially under low-frequency conditions. Taking the reservoir in the Tarim Basin study area as an example, through seismic forward simulation and inversion analysis of geological and logging data, it was found that seismic wave attenuation is highly sensitive to crack density. When there are a large number of high-density cracks in the underground rock formations, seismic wave inversion is easily disturbed by cracks in oil resource exploration, which greatly reduces the accuracy of oil exploration. Therefore, how to reduce the interference of underground rock formation cracks in the process of oil exploration has become an urgent problem to be solved. Summary of the invention

[0004] The present application provides an intelligent node seismometer and method for oil exploration, which can collect auxiliary waveform data to construct a correlation model and perform auxiliary correction on the seismic waveform data, thereby reducing the interference of underground rock fractures during oil exploration and improving the accuracy of oil exploration.

[0005] In a first aspect, the present application provides an intelligent node exploration method for oil exploration, which can be executed by a network device, or can also be executed by a chip configured in the network device, and the present application does not limit this.

[0006] Specifically, the method includes:

[0007] Acquire well logging data of the target exploration area, extract well logging acoustic wave curves from the well logging data and perform time alignment to obtain seismic wave detection curves;

[0008] The seismic waveform data is obtained by detecting the main node; the auxiliary waveform data corresponding to each sub-node is obtained by detecting multiple sub-nodes;

[0009] Based on the seismic waveform data, wave impedance characteristics of each auxiliary waveform data are extracted to obtain the wave impedance attenuation coefficient corresponding to each sub-node, and the azimuth weight corresponding to each sub-node is determined according to the wave impedance attenuation coefficient corresponding to each sub-node and the azimuth interval in which the sub-node is located;

[0010] Constructing the correlation model corresponding to each sub-node according to the seismic wave detection curve, the auxiliary waveform data corresponding to each sub-node and the azimuth weight respectively, and performing seismic data auxiliary correction on the seismic waveform data according to all the correlation models to obtain seismic wave correction data;

[0011] The seismic wave correction data is used to perform data inversion, and the distribution of oil reservoirs in the target exploration area is predicted based on the inversion results.

[0012] In combination with the first aspect, in certain implementations of the first aspect, extracting the logging acoustic wave curve in the logging data and performing time alignment to obtain the seismic wave detection curve specifically includes:

[0013] Sampling the seismic wave detection curve at equal intervals to obtain a plurality of depth points;

[0014] Acquire each depth point in the well logging acoustic wave curve, and for each depth point, determine the two-way propagation time corresponding to each depth point based on a preset depth-time mapping function;

[0015] The logging acoustic wave curve is converted from the depth domain to the time domain according to the two-way propagation time corresponding to each depth point, and is aligned with the time axis of the standard seismic time section to obtain the seismic wave detection curve.

[0016] In combination with the first aspect, in certain implementations of the first aspect, extracting wave impedance features from each auxiliary waveform data based on the seismic waveform data to obtain the wave impedance attenuation coefficient corresponding to each secondary node specifically includes:

[0017] Performing modal decomposition on the seismic waveform data to obtain a waveform trend curve of a main node;

[0018] Obtain the auxiliary waveform data corresponding to each sub-node and perform modal decomposition to obtain the waveform trend curve corresponding to each sub-node;

[0019] Based on the attenuation ratio between the waveform trend curve of the main node and the waveform trend curves corresponding to each of the secondary nodes, the wave impedance attenuation coefficient corresponding to each of the secondary nodes is determined.

[0020] In combination with the first aspect, in certain implementations of the first aspect, performing seismic data auxiliary correction on the seismic waveform data according to the entire correlation model to obtain seismic wave correction data specifically includes:

[0021] Obtain seismic waveform data and obtain auxiliary waveform data from each secondary node;

[0022] For the auxiliary waveform data corresponding to any secondary node, the auxiliary correction factors corresponding to different moments are determined according to the correlation model corresponding to the secondary node, and the auxiliary waveform data are weighted corrected according to the auxiliary correction factors corresponding to different moments, and then the seismic waveform data are superimposed and corrected;

[0023] Based on the auxiliary waveform data corresponding to all the secondary nodes, the seismic waveform data is subjected to auxiliary seismic data correction in the same manner to obtain the seismic wave correction data.

[0024] In combination with the first aspect, in certain implementations of the first aspect, using the seismic wave correction data to perform data inversion, and predicting the distribution of oil reservoirs in the target exploration area based on the inversion results specifically includes:

[0025] Acquire the seismic wave correction data, and convert the time information of each reflection point in the seismic wave correction data into a depth value according to the time section of the seismic wave correction data, so as to generate a depth section diagram;

[0026] Performing wave impedance analysis on the seismic wave correction data, determining the reflection coefficient of the rock layer interface according to the wave impedance difference of the medium, and forming a reflection coefficient matrix according to the time sequence;

[0027] In combination with the depth profile and the reflection coefficient matrix, a convolutional neural network model is used to predict the distribution of oil reservoirs at the main node position.

[0028] In combination with the first aspect, in some implementations of the first aspect, a seismic detector is used as a terminal acquisition device of the main node and the secondary node.

[0029] In combination with the first aspect, in certain implementations of the first aspect, before extracting the logging acoustic wave curves in the logging data and performing time alignment, the method further includes: performing denoising preprocessing on the logging acoustic wave curves.

[0030] In a second aspect, the present application provides an intelligent node seismometer for oil exploration, which includes an oil exploration unit, and the oil exploration unit includes:

[0031] A seismic data acquisition module is used to obtain well logging data in the target exploration area, extract well logging acoustic wave curves in the well logging data, and perform time alignment to obtain seismic wave detection curves;

[0032] The seismic data acquisition module is also used to obtain seismic waveform data through main node detection; and obtain auxiliary waveform data corresponding to each sub-node through multiple sub-node detection;

[0033] A seismic data processing module is used to extract wave impedance characteristics of each auxiliary waveform data based on the seismic waveform data, obtain the wave impedance attenuation coefficient corresponding to each sub-node, and determine the azimuth weight corresponding to each sub-node according to the wave impedance attenuation coefficient corresponding to each sub-node and the azimuth interval in which the sub-node is located;

[0034] The seismic data processing module is further used to construct the correlation model corresponding to each sub-node according to the seismic wave detection curve, the auxiliary waveform data corresponding to each sub-node and the azimuth weight, and perform seismic data auxiliary correction on the seismic waveform data according to all the correlation models to obtain seismic wave correction data;

[0035] The oil reservoir prediction module is used to perform data inversion using the seismic wave correction data, and predict the oil reservoir distribution in the target exploration area based on the inversion result.

[0036] In a third aspect, the present application provides a computer terminal device, which includes a memory and a processor, wherein the memory stores codes, and the processor is configured to obtain the codes and execute the above-mentioned intelligent node exploration method for oil exploration.

[0037] In a fourth aspect, the present application provides a computer-readable storage medium storing at least one computer program, wherein the computer program is loaded and executed by a processor to implement the operations performed by the above-mentioned intelligent node exploration method for oil exploration.

[0038] The technical solution provided by the embodiments disclosed in this application has the following beneficial effects:

[0039] In an intelligent node seismometer and method for oil exploration provided by the present application, firstly, well logging data of a target exploration area is acquired, well logging acoustic wave curves in the well logging data are extracted and time-aligned to obtain a seismic wave detection curve; seismic waveform data is obtained through main node detection; auxiliary waveform data corresponding to each sub-node is obtained through multiple sub-node detection; wave impedance characteristics of each auxiliary waveform data are extracted based on the seismic waveform data to obtain a wave impedance attenuation coefficient corresponding to each sub-node, and the azimuth weight corresponding to each sub-node is determined according to the wave impedance attenuation coefficient corresponding to each sub-node and the azimuth interval; a correlation model corresponding to each sub-node is constructed according to the seismic wave detection curve, the auxiliary waveform data corresponding to each sub-node, and the azimuth weight, and seismic data auxiliary correction is performed on the seismic waveform data according to all the correlation models to obtain seismic wave correction data; finally, data inversion is performed using the seismic wave correction data, and the oil reservoir distribution in the target exploration area is predicted based on the inversion result.

[0040] It can be seen that the present application arranges multiple sub-nodes in the target area. These nodes can collect auxiliary waveform data to record the changes in seismic waves in different directions and positions, thereby capturing the influence of local geological conditions on seismic wave propagation, especially the wave impedance changes and attenuation characteristics caused by rock fractures, making up for the limitations of single-point acquisition of the main node, and facilitating accurate analysis of the interference of fractures on seismic waves. The scheme extracts the wave impedance attenuation coefficient of each sub-node through the wave impedance characteristics, and can quantify the influence of fracture density and geological characteristics. Areas with high fracture density will cause significant wave impedance attenuation, highlighting the interference characteristics of fractures on seismic wave propagation, and improving the reliability of subsequent data analysis. By combining the spatial distribution of sub-nodes and the wave impedance attenuation coefficient, the azimuth weight of each sub-node is calculated, and the degree of influence of seismic wave propagation in different directions is quantified. The interference effect of fractures is not uniformly distributed in space, and the azimuth weight can help capture these uneven Uniformity, laying the foundation for building a correlation model; in the process of constructing a correlation model based on the seismic wave detection curve of the main node and the auxiliary waveform data of each sub-node, as well as the azimuth weight, the model evaluates the matching degree of the seismic wave data of each sub-node with the main node through a sliding time window and correlation calculation. The correlation model can identify the difference between fracture interference and actual reservoir response, thereby effectively eliminating fracture interference in the data correction process, and further reducing the impact of single node data anomalies on the overall correction through the superposition of models of multiple sub-nodes; the correlation model provides correction information of different sub-nodes, constructs a correlation model and performs auxiliary correction on the seismic waveform data, which can compensate for waveform distortion, energy loss or time delay caused by fractures, and finally uses seismic wave correction data for data inversion, thereby reducing underground rock fracture interference during oil exploration and improving the accuracy of oil exploration.

[0041] In summary, the present application provides an intelligent node seismograph and method for oil exploration, which can collect auxiliary waveform data to construct a correlation model and perform auxiliary correction on the seismic waveform data, thereby reducing the interference of underground rock fractures during oil exploration and improving the accuracy of oil exploration. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 is an exemplary flow chart of an intelligent node exploration method for oil exploration according to some embodiments of the present application;

[0043] Figure 2 is an exemplary flow chart for determining a seismic wave detection curve in some embodiments of the present application;

[0044] Figure 3 is a schematic diagram of the structure of an oil exploration unit according to some embodiments of the present application;

[0045] Figure 4It is a structural diagram of a computer terminal device for implementing an intelligent node exploration method for oil exploration according to some embodiments of the present application. DETAILED DESCRIPTION

[0046] The present application obtains the logging data of the target exploration area, extracts the logging acoustic wave curve in the logging data and performs time alignment to obtain the seismic wave detection curve; obtains the seismic waveform data through main node detection; obtains the auxiliary waveform data corresponding to each sub-node through multiple sub-node detection; extracts the wave impedance characteristics of each auxiliary waveform data based on the seismic waveform data to obtain the wave impedance attenuation coefficient corresponding to each sub-node, and determines the azimuth weight corresponding to each sub-node according to the wave impedance attenuation coefficient corresponding to each sub-node and the azimuth interval; constructs the correlation model corresponding to each sub-node according to the seismic wave detection curve, the auxiliary waveform data corresponding to each sub-node and the azimuth weight, performs seismic data auxiliary correction on the seismic waveform data according to all the correlation models to obtain seismic wave correction data; finally, uses the seismic wave correction data to perform data inversion, and predicts the oil reservoir distribution in the target exploration area based on the inversion result, so that the auxiliary waveform data can be collected to construct the correlation model and the seismic waveform data can be auxiliary corrected, thereby reducing the interference of underground rock fractures in the oil exploration process and improving the accuracy of oil exploration.

[0047] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods. Figure 1 , which is an exemplary flow chart of an intelligent node exploration method for oil exploration according to some embodiments of the present application. The intelligent node exploration method 100 for oil exploration mainly includes the following steps:

[0048] In step S101, well logging data of a target exploration area is acquired, and well logging acoustic wave curves in the well logging data are extracted and time-aligned to obtain seismic wave detection curves.

[0049] It should be noted that well logging data refers to various physical parameter data recorded in a drilled well by a well logging instrument, which reflects the properties of the underground rock formations, geological structure and fluid distribution. Well logging of a drilled well is mainly used to study the lithology, porosity, permeability, fluid properties and reservoir properties of the formations around the well. Well logging data is also an important basis for oil and gas exploration and development. Optionally, in some embodiments, in the process of obtaining well logging data of the target exploration area, acoustic logging can be performed during the exploration and logging process to obtain well logging data, and the well logging data specifically includes: well logging acoustic wave curves, density curves and resistivity curves, thermal neutron density curves, etc.

[0050] Optionally, in some embodiments, before extracting the logging acoustic wave curves in the logging data and performing time alignment, the method further includes: performing denoising preprocessing on the logging acoustic wave curves.

[0051] Optionally, in some embodiments, the denoising preprocessing of the logging acoustic wave curve may be implemented by the following steps: obtaining a preset filter frequency band, and performing denoising preprocessing of the logging acoustic wave curve using a bandpass filter according to the preset filter frequency band.

[0052] It should be noted that the propagation speed of seismic waves in underground media determines the relationship between depth and time. The logging acoustic wave curve provides the longitudinal wave velocity information of the formation. By integrating the depth variable, the depth value of the formation can be converted into the corresponding time value. In this application, the depth-time mapping function in the logging acoustic wave curve is preset as follows:

[0053]

[0054] Where t is the two-way propagation time, z is the logging depth, is the medium sound velocity, and dz is the differential of the logging depth value.

[0055] It should be noted that since the frequency of logging sound waves is generally higher than that of seismic waves (the frequency of logging sound waves is usually below 20 kHz, while the frequency of seismic waves can usually reach 200 Hz), and the attenuation effect of rock fractures on low-frequency longitudinal waves is more obvious, the logging sound wave curves that are greatly affected by the attenuation of rock fractures can be time-aligned and used for consistency comparison with seismic waveform data, so as to examine the influence of rock fractures on seismic waveform data. Optionally, in some embodiments, reference Figure 2 As shown in FIG. 1 , this figure is an exemplary flow chart of determining a seismic wave detection curve in some embodiments of the present application. The following steps can be used to extract the well logging acoustic wave curve in the well logging data and perform time alignment to obtain the seismic wave detection curve:

[0056] In step S1011, the seismic wave detection curve is sampled at equal intervals to obtain a plurality of depth points;

[0057] In step S1012, each depth point in the well logging acoustic wave curve is obtained, and for each depth point, a two-way propagation time corresponding to each depth point is determined based on a preset depth-time mapping function;

[0058] In step S1013, the logging acoustic wave curve is converted from the depth domain to the time domain according to the two-way propagation time corresponding to each depth point, and aligned with the time axis of the standard seismic time section to obtain the seismic wave detection curve.

[0059] In specific implementation, the time axis of the seismic time section converted from historical seismic waveform data can be used as the time axis of the standard seismic time section and aligned with the well logging acoustic wave curve converted from the depth domain to the time domain.

[0060] In step S102, seismic waveform data is obtained through main node detection; auxiliary waveform data corresponding to each sub-node is obtained through multiple sub-node detection;

[0061] It should be noted that the main node refers to the terminal acquisition equipment at the preset seismic wave acquisition position, which is used to accurately receive the seismic wave signal and transmit it to the data processing center. The sub-node is the terminal acquisition equipment that covers the area around the main node in the form of a grid or array to perform auxiliary signal acquisition, and is used to correct or enhance the data collected by the main node.

[0062] Optionally, in some embodiments, a seismic detector may be used as a terminal acquisition device for a main node and a sub-node, and the seismic detector is used to collect seismic waveform data at the main node or the sub-node.

[0063] It should be noted that the present application arranges a main node in the exploration area to collect high-sensitivity seismic waveform data and record the main reflected wave signals. The main node is responsible for obtaining the overall waveform data of the seismic waves, including amplitude, frequency and propagation time; multiple sub-nodes are arranged around the main node to cover the area in a grid or array form, and the sub-nodes collect auxiliary waveform data to record the changes in seismic waves in different directions and positions; and because the sub-nodes cover the area in a grid or array form, the influence of local geological conditions on the propagation of seismic waves can be effectively captured, especially the wave impedance changes and attenuation characteristics caused by rock fractures; the collected data is more comprehensive, which makes up for the limitations of single-point collection of the main node and helps to accurately analyze the interference of fractures on seismic waves.

[0064] In step S103, wave impedance characteristics are extracted for each auxiliary waveform data based on the seismic waveform data to obtain the wave impedance attenuation coefficient corresponding to each sub-node, and the azimuth weight corresponding to each sub-node is determined according to the wave impedance attenuation coefficient corresponding to each sub-node and the azimuth interval in which it is located.

[0065] It should be noted that the wave impedance attenuation coefficient is used to quantify the influence of fracture density and geological characteristics on seismic waveform data; areas with high fracture density will cause significant wave impedance attenuation. Optionally, in some embodiments, wave impedance feature extraction is performed on each auxiliary waveform data based on the seismic waveform data to obtain the wave impedance attenuation coefficient corresponding to each sub-node, which can be achieved by the following steps:

[0066] Performing modal decomposition on the seismic waveform data to obtain a waveform trend comparison curve of a main node, and then performing wave impedance feature extraction on the waveform trend comparison curve to obtain a wave impedance comparison feature of the main node;

[0067] Obtain the auxiliary waveform data corresponding to each sub-node and perform modal decomposition to obtain the waveform trend attenuation curve corresponding to each sub-node, and then extract the wave impedance characteristics of each waveform trend curve to obtain the wave impedance attenuation characteristics corresponding to each sub-node;

[0068] Based on the attenuation ratio of the wave impedance comparison feature of the main node and the wave impedance attenuation feature corresponding to each secondary node, the wave impedance attenuation coefficient corresponding to each secondary node is determined.

[0069] Optionally, in some embodiments, empirical mode decomposition is used to perform modal decomposition on the seismic waveform data, and the mean of all extracted eigenmode functions is used as the waveform trend curve of the main node. The same method can also be used to determine the waveform trend curves corresponding to each sub-node. The present application does not limit this. In specific implementation, the mean of the waveform trend curve of the main node can be obtained as the wave impedance comparison feature; and then the mean of the waveform trend curve corresponding to each sub-node is used as the corresponding wave impedance attenuation feature. The ratio between the comparison feature and the attenuation feature is the wave impedance attenuation coefficient corresponding to each sub-node.

[0070] It should be noted that by combining the spatial distribution of sub-nodes and the wave impedance attenuation coefficient, the azimuth weight of each sub-node is calculated to quantify the degree of influence of seismic wave propagation in different azimuths. The interference effect of cracks is not uniformly distributed in space. The azimuth weight is used to help capture the non-uniformity of the crack interference effect, thereby laying the foundation for building a more accurate correlation model.

[0071] In some embodiments of the present application, the sub-nodes cover an area in the form of a grid or array, which is used to collect auxiliary waveform data and record seismic wave changes in the local environment. In specific implementation, based on a two-dimensional spatial coordinate system with the main node as the coordinate origin, eight 45° azimuths of east, west, south, north, southeast, southwest, northeast, and northwest are calibrated, and each azimuth has its own corresponding azimuth interval. The azimuth interval contains each sub-node and its corresponding collection data. The azimuth weight corresponding to each sub-node is determined by the wave impedance attenuation coefficient corresponding to the azimuth interval where each sub-node is located. The following steps can be used to achieve this: obtain the wave impedance attenuation coefficient corresponding to each sub-node in each azimuth interval and normalize them, and use the normalized mean of all wave impedance attenuation coefficients in each azimuth interval as the azimuth weight of the azimuth interval. For any sub-node, determine the azimuth weight corresponding to the sub-node based on the azimuth interval where it is located.

[0072] In step S104, a correlation model corresponding to each sub-node is constructed according to the seismic wave detection curve, the auxiliary waveform data corresponding to each sub-node and the azimuth weight, and the seismic waveform data is subjected to auxiliary correction according to all the correlation models to obtain seismic wave correction data.

[0073] It should be noted that, in the process of constructing a correlation model based on the seismic wave detection curve of the main node and the auxiliary waveform data of each sub-node, as well as the azimuth weight of the present application, the correlation model evaluates the matching degree of each sub-node with the seismic wave data of the main node through a sliding time window and membership calculation; the correlation model can identify the difference between fracture interference and actual reservoir response, thereby effectively eliminating fracture interference in the data correction process; by superimposing the models of multiple sub-nodes, the influence of single node data anomalies on the overall correction is reduced. Optionally, in some embodiments, the correlation model corresponding to each sub-node is constructed according to the seismic wave detection curve, the auxiliary waveform data corresponding to each sub-node, and the azimuth weight respectively, which can be implemented by the following steps:

[0074] For any secondary node, the auxiliary waveform data and the azimuth weight corresponding to the secondary node are obtained, and then a preset time window threshold is obtained, and a sliding time window is constructed according to the time window threshold;

[0075] Determine the basic membership of the sliding time window based on the seismic wave detection curve and the seismic waveform data within the sliding time window, and then determine the correlation index between the auxiliary waveform data corresponding to the slave node and the seismic waveform data of the master node;

[0076] Determine the auxiliary correction factor of the sliding time window according to the orientation weight, the basic membership and the correlation index, and determine the correlation model corresponding to the secondary node by using moving average autoregression based on the auxiliary correction factors of each sliding time window;

[0077] The same method is used to obtain the correlation models corresponding to other sub-nodes.

[0078] It should be noted that the orientation weight reflects the waveform attenuation effect of the geometric orientation of the secondary node relative to the main node, the basic membership reflects the consistency of the seismic wave detection curve and the seismic waveform data in the sliding time window, and is used to characterize the joint influence of rock fractures on the seismic waveform data and the seismic wave detection curve. The correlation index is used to reflect the degree of matching between the auxiliary waveform data and the main node waveform data, and is used to characterize the interference of rock fractures on seismic waves in different orientations of the target exploration area. In some embodiments, in specific implementation, the sampling points of the seismic wave detection curve and the seismic waveform data in the sliding time window can be used as vector data of a comparison vector respectively, and then the cosine similarity between the comparison vectors is determined as the basic membership of the sliding time window, and the Pearson correlation coefficient between the auxiliary waveform data corresponding to the secondary node in the sliding time window and the seismic waveform data of the main node is used as the correlation index.

[0079] Optionally, in some embodiments, the auxiliary correction factor of the sliding time window = (the product of the basic membership corresponding to the sliding time window and the correlation index) / the azimuth weight corresponding to the sub-node. It should be noted that the larger the azimuth weight corresponding to the sub-node, the greater the degree of the seismic wave signal corresponding to the azimuth of the sub-node. At this time, it is necessary to adjust the auxiliary correction factor according to the azimuth weight corresponding to the sub-node in a timely manner to reduce the influence of this part of the deviation signal on the seismic data correction. After determining the auxiliary correction factors corresponding to each sliding time window, based on the auxiliary correction factors of all sliding time windows, a moving average autoregressive model (ARMA) is used to construct a correlation model of the sub-node. The correlation model is used to comprehensively analyze the changes in waveform data within the time window and capture the time series characteristics of the auxiliary correction factor, thereby improving the accuracy of geological inversion and increasing the accuracy of oil exploration during the seismic data correction process.

[0080] It should be noted that the present application corrects the seismic waveform data through the constructed correlation model to generate more accurate seismic wave correction data, thereby providing a high-quality data basis for subsequent geological inversion and reservoir distribution prediction. Optionally, in some embodiments, the seismic waveform data is subjected to seismic data auxiliary correction according to all correlation models, and the seismic wave correction data can be obtained by the following steps:

[0081] Obtain seismic waveform data and obtain auxiliary waveform data from each secondary node;

[0082] For the auxiliary waveform data corresponding to any secondary node, the auxiliary correction factors corresponding to different moments are determined according to the correlation model corresponding to the secondary node, and the auxiliary waveform data are weighted corrected according to the auxiliary correction factors corresponding to different moments, and then the seismic waveform data are superimposed and corrected;

[0083] Based on the auxiliary waveform data corresponding to all the secondary nodes, the seismic waveform data is subjected to auxiliary seismic data correction in the same manner to obtain the seismic wave correction data.

[0084] In specific implementation, the auxiliary correction factors corresponding to different sliding time windows in the correlation model can be used as correction coefficients to perform proportional correction on the corresponding auxiliary waveform data in the time window, and then averagely superimpose them with the seismic waveform data to complete the superposition correction of the seismic waveform data.

[0085] In step S105, the seismic wave correction data is used to perform data inversion, and the distribution of oil reservoirs in the target exploration area is predicted based on the inversion results.

[0086] Optionally, in some embodiments, corresponding learning labels can be set for the peaks, troughs and critical points of the seismic wave correction data, and machine learning can be used to obtain the distribution of oil reservoirs in the target exploration area; in specific implementation, random forest or support vector machine can also be used as a reservoir classification model, and the reservoir classification model can be learned and trained through historical seismic waveform data, wherein the input features of the model include: the time information of the seismic wave correction data, the amplitude of the seismic wave correction data and its changing trend, and the contrast features of adjacent waveforms of the seismic wave correction data, so as to output a reservoir distribution probability map of the target exploration area, indicating information such as oil content, reservoir thickness, and fracture density.

[0087] Optionally, in some embodiments, data inversion is performed using the seismic wave correction data, and the distribution of oil reservoirs in the target exploration area is predicted based on the inversion results, which can be achieved by the following steps:

[0088] Acquire the seismic wave correction data, and convert the time information of each reflection point in the seismic wave correction data into a depth value according to the time section of the seismic wave correction data, so as to generate a depth section diagram;

[0089] Performing wave impedance analysis on the seismic wave correction data, determining the reflection coefficient of the rock layer interface according to the wave impedance difference of the medium, and forming a reflection coefficient matrix according to the time sequence;

[0090] In combination with the depth profile and the reflection coefficient matrix, a convolutional neural network model is used to predict the distribution of oil reservoirs at the main node position.

[0091] In a specific implementation, the input data of the convolutional neural network includes: a depth profile (including formation depth information) and a rock formation reflection coefficient (reflecting changes in wave impedance); the output data of the convolutional neural network includes a prediction of the oil reservoir distribution at the main node position.

[0092] Optionally, in some embodiments, the convolutional neural network structure includes: input layer: receiving depth profile and reflection coefficient matrix; hidden layer: including multiple convolutional layers, used to extract the spatial characteristics of depth, wave impedance and reservoir distribution; output layer: output predicted oil reservoir distribution map. In specific implementation, the area with known oil reservoir distribution can be selected as training samples, and the reservoir thickness, location and lithology characteristics can be marked. The historical wave impedance analysis results and depth profile can also be input during the training process to train the convolutional neural network model and optimize the parameters; finally, by inputting the depth profile and reflection coefficient matrix extracted from the seismic wave correction data of the main node, the convolutional neural network performs feature extraction and pattern recognition on the input data, and outputs the oil reservoir distribution at the main node position.

[0093] In addition, in another aspect of the present application, in some embodiments, the present application provides an intelligent node seismograph for oil exploration, wherein the intelligent node seismograph includes an oil exploration unit, Figure 3 , which is a schematic diagram of the structure of an oil exploration unit according to some embodiments of the present application. The oil exploration unit 200 includes: a seismic data acquisition module 201, a seismic data processing module 202 and an oil reservoir prediction module 203, which are respectively described as follows:

[0094] The seismic data acquisition module 201 is used in some specific embodiments of the present application to obtain well logging data of the target exploration area, extract well logging acoustic wave curves in the well logging data and perform time alignment to obtain seismic wave detection curves;

[0095] The seismic data acquisition module 201, in some specific embodiments of the present application, is also used to obtain seismic waveform data through main node detection; and obtain auxiliary waveform data corresponding to each sub-node through multiple sub-node detection;

[0096] The seismic data processing module 202 is used in some specific embodiments of the present application to extract wave impedance characteristics of each auxiliary waveform data based on the seismic waveform data, obtain the wave impedance attenuation coefficient corresponding to each sub-node, and determine the azimuth weight corresponding to each sub-node according to the wave impedance attenuation coefficient corresponding to each sub-node and the azimuth interval in which the sub-node is located;

[0097] The seismic data processing module 202, in some specific embodiments of the present application, is further used to construct a correlation model corresponding to each sub-node according to the seismic wave detection curve, the auxiliary waveform data corresponding to each sub-node, and the azimuth weight, and perform seismic data auxiliary correction on the seismic waveform data according to all the correlation models to obtain seismic wave correction data;

[0098] The oil reservoir prediction module 203 is used in some specific embodiments of the present application to perform data inversion using the seismic wave correction data, and predict the oil reservoir distribution in the target exploration area based on the inversion results.

[0099] The above describes in detail an example of an intelligent node seismometer and method for oil exploration provided in an embodiment of the present application. It can be understood that in order to realize the above functions, the corresponding device includes a hardware structure and / or software module corresponding to executing each function.

[0100] Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiments disclosed in this document, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function in the application is executed in hardware or in a computer software-driven hardware manner depends on the specific application and design constraints of the technical solution. Therefore, professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0101] In addition, the present application also provides a computer terminal device, which includes a memory and a processor, wherein the memory stores codes, and the processor is configured to obtain the codes and execute the above-mentioned intelligent node exploration method for oil exploration.

[0102] In some embodiments, reference Figure 4 , which is a schematic diagram of the structure of a computer terminal device for implementing an intelligent node exploration method for oil exploration according to some embodiments of the present application. An intelligent node exploration method for oil exploration in the above embodiment can be Figure 4 The computer terminal device 300 shown in the figure is implemented, and the computer terminal device 300 includes at least one communication bus 301, a communication interface 302, a processor 303 and a memory 304.

[0103] The processor 303 may be a general-purpose central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more processors for controlling the execution of an intelligent node exploration method for oil exploration in the present application.

[0104] The communication bus 301 may include a path for transmitting information between the above-mentioned components.

[0105] The memory 304 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, an optical disc storage (including a compressed optical disc, a laser disc, an optical disc, a digital versatile disc, a Blu-ray disc, etc.), a magnetic disk or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of an instruction or data structure and can be accessed by a computer, but is not limited thereto. The memory 304 may exist independently and be connected to the processor 303 via the communication bus 301. The memory 304 may also be integrated with the processor 303.

[0106] The memory 304 is used to store the program code for executing the solution of the present application, and the execution is controlled by the processor 303. The processor 303 is used to execute the program code stored in the memory 304. The program code may include one or more software modules. The determination of the wave impedance attenuation coefficient in the above embodiment can be implemented by the processor 303 and one or more software modules in the program code in the memory 304.

[0107] The communication interface 302 uses any transceiver or other device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0108] Optionally, the computer terminal device 300 may further include a power supply 305 for providing power to various devices or circuits in the real-time computer terminal device.

[0109] In a specific implementation, as an embodiment, a computer terminal device may include multiple processors, each of which may be a single-CPU processor or a multi-CPU processor. The processor here may refer to one or more devices, circuits, and / or processing cores for processing data (such as computer program instructions).

[0110] The above-mentioned computer terminal device may be a general-purpose computer terminal device or a dedicated computer terminal device. In a specific implementation, the computer terminal device may be a desktop computer, a portable computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device or an embedded device. The embodiment of the present application does not limit the type of computer terminal device.

[0111] In addition, in other aspects of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores at least one computer program, and the computer program is loaded and executed by a processor to implement the operations performed by the above-mentioned intelligent node exploration method for oil exploration.

[0112] In summary, in an intelligent node seismometer and method for oil exploration disclosed in an embodiment of the present application, firstly, well logging data of a target exploration area is acquired, well logging acoustic wave curves in the well logging data are extracted and time-aligned to obtain a seismic wave detection curve; seismic waveform data is obtained by main node detection; auxiliary waveform data corresponding to each sub-node is obtained by multiple sub-node detection; wave impedance characteristics of each auxiliary waveform data are extracted based on the seismic waveform data to obtain the wave impedance attenuation coefficient corresponding to each sub-node; and each sub-node is determined according to the wave impedance attenuation coefficient corresponding to each sub-node and the azimuth interval in which it is located. The invention discloses a method for detecting the seismic wave of a sub-node and a sub-node of a petroleum reservoir. The method comprises the following steps: first, determining the azimuth weights corresponding to the points respectively; second, constructing the correlation models corresponding to the sub-nodes according to the seismic wave detection curve, the auxiliary waveform data corresponding to the sub-nodes and the azimuth weights respectively; and performing auxiliary correction on the seismic waveform data according to all the correlation models to obtain the seismic wave correction data; finally, performing data inversion with the seismic wave correction data, and predicting the distribution of oil reservoirs in the target exploration area based on the inversion results; and collecting the auxiliary waveform data to construct the correlation model and performing auxiliary correction on the seismic waveform data, thereby reducing the interference of underground rock fractures in the process of oil exploration and improving the accuracy of oil exploration.

[0113] The above is only an embodiment of the present application, and the common knowledge such as the specific technical scheme or characteristics in the scheme is not described in detail here. It should be pointed out that for those skilled in the art, without departing from the technical scheme of the present application, several modifications and improvements can be made, which should also be regarded as the scope of protection of the present application, and these will not affect the effect of the implementation of the present application and the practicality of the patent.

[0114] The scope of protection claimed by this application shall be based on the content of its claims. The specific implementation methods and other records in the specification can be used to interpret the content of the claims. Obviously, those skilled in the art can make various changes and modifications to this application without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalents, this application is also intended to include these modifications and variations.

Claims

1. An intelligent node exploration method for oil exploration, characterized in that: include: Acquire well logging data of the target exploration area, extract well logging acoustic wave curves from the well logging data and perform time alignment to obtain seismic wave detection curves; The seismic waveform data is obtained by detecting the main node; the auxiliary waveform data corresponding to each sub-node is obtained by detecting multiple sub-nodes; Based on the seismic waveform data, wave impedance characteristics of each auxiliary waveform data are extracted to obtain the wave impedance attenuation coefficient corresponding to each sub-node, and the azimuth weight corresponding to each sub-node is determined according to the wave impedance attenuation coefficient corresponding to each sub-node and the azimuth interval in which the sub-node is located; Constructing the correlation model corresponding to each sub-node according to the seismic wave detection curve, the auxiliary waveform data corresponding to each sub-node and the azimuth weight respectively, and performing seismic data auxiliary correction on the seismic waveform data according to all the correlation models to obtain seismic wave correction data; The seismic wave correction data is used to perform data inversion, and the distribution of oil reservoirs in the target exploration area is predicted based on the inversion results.

2. The method according to claim 1, characterized in that Extracting the logging acoustic wave curve in the logging data and performing time alignment to obtain the seismic wave detection curve specifically includes: Sampling the seismic wave detection curve at equal intervals to obtain a plurality of depth points; Acquire each depth point in the well logging acoustic wave curve, and for each depth point, determine the two-way propagation time corresponding to each depth point based on a preset depth-time mapping function; The logging acoustic wave curve is converted from the depth domain to the time domain according to the two-way propagation time corresponding to each depth point, and aligned with the time axis of the standard seismic time section to obtain the seismic wave detection curve.

3. The method according to claim 1, characterized in that Based on the seismic waveform data, the wave impedance characteristics of each auxiliary waveform data are extracted to obtain the wave impedance attenuation coefficient corresponding to each sub-node, which specifically includes: Performing modal decomposition on the seismic waveform data to obtain a waveform trend curve of a main node; Obtain the auxiliary waveform data corresponding to each sub-node and perform modal decomposition to obtain the waveform trend curve corresponding to each sub-node; Based on the attenuation ratio between the waveform trend curve of the main node and the waveform trend curves corresponding to each of the secondary nodes, the wave impedance attenuation coefficient corresponding to each of the secondary nodes is determined.

4. The method according to claim 1, characterized in that Performing seismic data auxiliary correction on the seismic waveform data according to the whole correlation model to obtain seismic wave correction data specifically includes: Obtain seismic waveform data and obtain auxiliary waveform data from each secondary node; For the auxiliary waveform data corresponding to any secondary node, the auxiliary correction factors corresponding to different moments are determined according to the correlation model corresponding to the secondary node, and the auxiliary waveform data are weighted corrected according to the auxiliary correction factors corresponding to different moments, and then the seismic waveform data are superimposed and corrected; Based on the auxiliary waveform data corresponding to all the secondary nodes, the seismic waveform data is subjected to auxiliary seismic data correction in the same manner to obtain the seismic wave correction data.

5. The method according to claim 1, characterized in that The seismic wave correction data is used to perform data inversion, and the distribution of oil reservoirs in the target exploration area is predicted based on the inversion results, specifically including: Acquire the seismic wave correction data, and convert the time information of each reflection point in the seismic wave correction data into a depth value according to the time section of the seismic wave correction data, so as to generate a depth section diagram; Performing wave impedance analysis on the seismic wave correction data, determining the reflection coefficient of the rock layer interface according to the wave impedance difference of the medium, and forming a reflection coefficient matrix according to the time sequence; In combination with the depth profile and the reflection coefficient matrix, a convolutional neural network model is used to predict the distribution of oil reservoirs at the main node position.

6. The method according to claim 1, characterized in that A seismic detector is used as the terminal acquisition device of the main node and the sub-node.

7. The method according to claim 1, characterized in that Before extracting the logging acoustic wave curves in the logging data and performing time alignment, the method further includes: performing denoising preprocessing on the logging acoustic wave curves.

8. An intelligent node seismograph for oil exploration, comprising an oil exploration unit, characterized in that: The oil exploration unit comprises: A seismic data acquisition module is used to obtain well logging data in the target exploration area, extract well logging acoustic wave curves in the well logging data, and perform time alignment to obtain seismic wave detection curves; The seismic data acquisition module is also used to obtain seismic waveform data through main node detection; and obtain auxiliary waveform data corresponding to each sub-node through multiple sub-node detection; A seismic data processing module is used to extract wave impedance characteristics of each auxiliary waveform data based on the seismic waveform data, obtain the wave impedance attenuation coefficient corresponding to each sub-node, and determine the azimuth weight corresponding to each sub-node according to the wave impedance attenuation coefficient corresponding to each sub-node and the azimuth interval in which the sub-node is located; The seismic data processing module is further used to construct the correlation model corresponding to each sub-node according to the seismic wave detection curve, the auxiliary waveform data corresponding to each sub-node and the azimuth weight, and perform seismic data auxiliary correction on the seismic waveform data according to all the correlation models to obtain seismic wave correction data; The oil reservoir prediction module is used to perform data inversion using the seismic wave correction data, and predict the oil reservoir distribution in the target exploration area based on the inversion result.

9. A computer terminal device, characterized in that: The computer terminal device includes a memory and a processor, the memory stores codes, and the processor is configured to obtain the codes and execute the intelligent node exploration method for oil exploration as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing at least one computer program, characterized in that: The computer program is loaded and executed by a processor to implement the operations performed by the intelligent node exploration method for oil exploration as described in any one of claims 1 to 7.

Images