Neural network training method, model construction method, device, equipment and medium

Abstract

The application provides a neural network training method, a model construction method, an apparatus, a device and a medium. When a two-phase medium wave characteristic learning network is trained, a reservoir physical property parameter is taken as input, a plurality of predicted wave equation coefficients of a sample two-phase porous medium elastic wave propagation model are predicted, a physical constraint mechanism based on plane wave analysis is combined, an error loss between predicted dispersion attenuation characteristics and real dispersion attenuation characteristics of the sample two-phase porous medium elastic wave propagation model is used to adjust parameters of the two-phase medium wave characteristic learning network, the network has stronger prediction stability and physical consistency through back propagation, the predicted wave equation coefficients output by the two-phase medium wave characteristic learning network give consideration to both data accuracy and physical consistency requirements, and therefore the physical consistency, expression accuracy and generalization ability of the constructed target two-phase porous medium elastic wave propagation model are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of geophysical exploration, in particular to a neural network training method, a model construction method, a device, equipment and a medium. BACKGROUND

[0002] Seismic wave propagation modeling is a key technical means in oil and gas exploration and underground medium imaging. Especially in complex media such as low porosity and permeability or multiphase flow, the propagation of waves is affected by the coupling of solid skeleton, pore fluid and viscoelastic effect, etc., and presents significant dispersion and attenuation characteristics. Accurate description of these complex wave behaviors is the core problem of constructing high-precision seismic simulation and reservoir inversion models. For example, the Biot model and other two-phase porous medium elastic wave propagation models are widely used to describe the propagation rules of P waves and S waves in fluid-saturated porous media.

[0003] However, the two-phase porous medium elastic wave propagation model has many parameters and complex physical meanings, and some parameters are difficult to obtain directly through measurement. How to effectively construct the two-phase porous medium elastic wave propagation model has become a problem to be solved. SUMMARY

[0004] Therefore, the present application provides a neural network training method, a model construction method, a device, equipment and a medium, which can effectively predict the wave equation coefficients of the two-phase porous medium elastic wave propagation model and improve the physical consistency, expression accuracy and generalization ability of the model by fusing the physical constraint mechanism of plane wave analysis on the basis of neural network deep learning.

[0005] Specifically, the present application is realized by the following technical solutions:

[0006] According to a first aspect of the present application, a neural network training method is provided, which comprises:

[0007] obtaining a sample data set, the sample data set comprising sample reservoir physical parameters associated with a sample two-phase porous medium elastic wave propagation model;

[0008] inputting the sample data set into a two-phase medium wave characteristic learning network, and outputting a plurality of predicted wave equation coefficients of the sample two-phase porous medium elastic wave propagation model;

[0009] performing plane wave analysis based on the plurality of predicted wave equation coefficients to determine the predicted dispersion and attenuation characteristics of the sample two-phase porous medium elastic wave propagation model;

[0010] According to an error loss between the predicted dispersion attenuation characteristic and a true dispersion attenuation characteristic of the sample dual-phase porous medium elastic wave propagation model, parameters of the dual-phase medium wave motion characteristic learning network are adjusted until a stop condition is met.

[0011] In an alternative embodiment, the plane wave analysis based on the plurality of predicted wave equation coefficients is used to determine the predicted dispersion attenuation characteristic of the sample dual-phase porous medium elastic wave propagation model, including:

[0012] The porosity fluid density and fluid viscosity coefficient corresponding to the sample dual-phase porous medium elastic wave propagation model are obtained;

[0013] The plane wave analysis based on the plurality of predicted wave equation coefficients, the porosity fluid density and the fluid viscosity coefficient is used to determine the predicted dispersion attenuation characteristic of the sample dual-phase porous medium elastic wave propagation model.

[0014] In an alternative embodiment, the predicted dispersion attenuation characteristic includes a predicted P-wave velocity and a predicted S-wave velocity, and the true dispersion attenuation characteristic includes a true P-wave velocity and a true S-wave velocity;

[0015] The error loss between the predicted dispersion attenuation characteristic and the true dispersion attenuation characteristic of the sample dual-phase porous medium elastic wave propagation model is determined by:

[0016] According to a deviation between the predicted P-wave velocity and the true P-wave velocity and a deviation between the predicted S-wave velocity and the true S-wave velocity, the error loss between the predicted dispersion attenuation characteristic and the true dispersion attenuation characteristic is determined;

[0017] Alternatively, the predicted dispersion attenuation characteristic includes a predicted P-wave velocity, a predicted S-wave velocity and a predicted P-wave inverse quality factor, and the true dispersion attenuation characteristic includes a true P-wave velocity, a true S-wave velocity and a true P-wave inverse quality factor;

[0018] The error loss between the predicted dispersion attenuation characteristic and the true dispersion attenuation characteristic of the sample dual-phase porous medium elastic wave propagation model is determined by:

[0019] According to a deviation between the predicted P-wave velocity and the true P-wave velocity, a deviation between the predicted S-wave velocity and the true S-wave velocity and a deviation between the predicted P-wave inverse quality factor and the true P-wave inverse quality factor, the error loss between the predicted dispersion attenuation characteristic and the true dispersion attenuation characteristic is determined.

[0020] In an alternative embodiment, the sample dual-phase porous medium elastic wave propagation model comprises a visco-elastic wave propagation model, the dual-phase medium wave motion feature learning network comprises a visco-elastic wave motion feature learning network, and at least part of the plurality of predicted wave equation coefficients are complex numbers.

[0021] Alternatively, the sample dual-phase porous medium elastic wave propagation model comprises an elastic wave propagation model, the dual-phase medium wave motion feature learning network comprises an elastic wave motion feature learning network, and all of the plurality of predicted wave equation coefficients are real numbers.

[0022] In an alternative embodiment, the dual-phase medium wave motion feature learning network comprises an input module, a plurality of wave motion feature learning modules, and an output module, the input module is configured to receive an input sample data set, each wave motion feature learning module is configured to determine a predicted coefficient intermediate variable based on the sample data set, and the output module is configured to generate the predicted wave equation coefficients based on the predicted coefficient intermediate variables, the predicted coefficient intermediate variable being a real part parameter and an imaginary part parameter that constitute the predicted wave equation coefficients.

[0023] In an alternative embodiment, the number of wave motion feature learning modules is consistent with the number of predicted coefficient intermediate variables.

[0024] In an alternative embodiment, the sample data set comprises at least one of:

[0025] angular frequency, solid matrix bulk modulus, Lame coefficient, porosity, permeability, and solid matrix density.

[0026] According to a second aspect of the present application, a model construction method is provided, the method comprising:

[0027] obtaining a target data set, the target data set comprising target reservoir physical property parameters associated with a target dual-phase porous medium elastic wave propagation model;

[0028] inputting the target data set into the trained dual-phase medium wave motion feature learning network to output a plurality of wave equation coefficients of the target dual-phase porous medium elastic wave propagation model; the trained dual-phase medium wave motion feature learning network is obtained by training the neural network training method described above;

[0029] constructing the target dual-phase porous medium elastic wave propagation model based on the plurality of wave equation coefficients.

[0030] In an alternative embodiment, the method further comprises:

[0031] performing plane wave analysis based on the plurality of wave equation coefficients to determine the dispersion attenuation characteristics of the target dual-phase porous medium elastic wave propagation model;

[0032] determine propagation information of the longitudinal wave and the transverse wave based on the dispersion attenuation feature.

[0033] According to a third aspect of the present application, a neural network training apparatus is provided, the apparatus comprising:

[0034] a sample obtaining module configured to obtain a sample dataset, the sample dataset comprising sample reservoir physical property parameters associated with a sample dual-phase porous medium elastic wave propagation model;

[0035] a network prediction module configured to input the sample dataset into a dual-phase medium wave feature learning network, and output a plurality of predicted wave equation coefficients of the sample dual-phase porous medium elastic wave propagation model;

[0036] a feature analysis module configured to perform plane wave analysis based on the plurality of predicted wave equation coefficients, and determine a predicted dispersion attenuation feature of the sample dual-phase porous medium elastic wave propagation model;

[0037] a parameter adjustment module configured to adjust parameters of the dual-phase medium wave feature learning network according to an error loss between the predicted dispersion attenuation feature and a true dispersion attenuation feature of the sample dual-phase porous medium elastic wave propagation model, until a cutoff condition is met.

[0038] According to a fourth aspect of the present application, a model construction apparatus is provided, the apparatus comprising:

[0039] a data obtaining module configured to obtain a target dataset, the target dataset comprising target reservoir physical property parameters associated with a target dual-phase porous medium elastic wave propagation model;

[0040] a network processing module configured to input the target dataset into a trained dual-phase medium wave feature learning network, and output a plurality of wave equation coefficients of the target dual-phase porous medium elastic wave propagation model; the trained dual-phase medium wave feature learning network is trained by the neural network training method described above;

[0041] a model construction module configured to construct the target dual-phase porous medium elastic wave propagation model based on the plurality of wave equation coefficients.

[0042] According to a fifth aspect of the present application, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the neural network training method of the first aspect described above or the steps of the model construction method of the second aspect described above when executing the program.

[0043] According to a sixth aspect of the present application, a computer readable storage medium is provided, having stored thereon a computer program which, when executed by a processor, implements the steps of the neural network training method of the first aspect described above or the steps of the model construction method of the second aspect described above.

[0044] The neural network training method, the model construction method, the device, the equipment and the medium provided by the embodiments of the present application, when training the two-phase medium wave characteristic learning network, take the reservoir physical property parameters as the input, predict a plurality of predicted wave equation coefficients of the sample two-phase porous medium elastic wave propagation model, combine the physical constraint mechanism based on the plane wave analysis, adjust the parameters of the two-phase medium wave characteristic learning network according to the error loss between the predicted dispersion attenuation characteristics and the real dispersion attenuation characteristics of the sample two-phase porous medium elastic wave propagation model, make the network have stronger prediction stability and physical consistency through back propagation, ensure that the predicted wave equation coefficients output by the two-phase medium wave characteristic learning network take into account the data accuracy and the physical consistency requirement at the same time, and thus improve the physical consistency, the expression accuracy and the generalization ability of the constructed target two-phase porous medium elastic wave propagation model.

[0045] It should be understood that the foregoing general description and the following detailed description are only exemplary and explanatory, rather than limiting the technical solutions of the present disclosure.

[0046] In order to make the above-mentioned purposes, features and advantages of the present disclosure more obvious and easy to understand, the following preferred embodiments are specifically described below with reference to the accompanying drawings. BRIEF DESCRIPTION OF DRAWINGS

[0047] Figure 1 is a flowchart of a neural network training method according to an example embodiment of the present application;

[0048] Figure 2 is a structural schematic diagram of a neural network according to an example embodiment of the present application;

[0049] Figure 3 is a process schematic diagram of neural network training according to an example embodiment of the present application;

[0050] Figure 4 is a flowchart of a model construction method according to an example embodiment of the present application;

[0051] Figure 5 is a schematic diagram of P-wave dispersion characteristics according to an example embodiment of the present application;

[0052] Figure 6 is a schematic diagram of S-wave dispersion characteristics according to an example embodiment of the present application;

[0053] Figure 7is a schematic diagram of a neural network training apparatus according to an example embodiment of the present application;

[0054] Figure 8 is a schematic diagram of a model construction apparatus according to an example embodiment of the present application;

[0055] Figure 9 is a structural schematic diagram of a computer device according to an example embodiment of the present application. DETAILED DESCRIPTION

[0056] The example embodiments will be described in detail herein with reference to the attached drawings. In the following description, the same numbers are used to designate the same elements, unless otherwise indicated. The embodiments described in the following example embodiments are not representative of all embodiments consistent with the present application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the present application, as detailed in the appended claims.

[0057] The terminology used in the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the present application. As used in the present application and the appended claims, the singular forms "a," "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will also be understood that the term "and / or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.

[0058] It should be understood that although the terms first, second, third, etc. can be used herein to describe various information, these terms are not intended to denote a particular order or hierarchy. These terms are used merely to distinguish one from another. For example, a first information can be termed a second information, and similarly, a second information can be termed a first information, without departing from the scope of the present application. Depending on the context, the word "if' as used herein can be interpreted to mean "when" or "in response to determining" or "in response to a determination".

[0059] It is found through research that the dual-phase porous medium elastic wave propagation model has numerous parameters and complex physical meanings, and some parameters are difficult to be directly obtained through measurement or experiment, which limits the wide application of the dual-phase porous medium elastic wave propagation model. Therefore, how to effectively construct the dual-phase porous medium elastic wave propagation model becomes a problem to be solved.

[0060] Based on the above research, the application provides a neural network training method, a model construction method, a device, equipment and a medium. In training of a two-phase medium wave characteristic learning network, a reservoir physical property parameter is taken as input, a plurality of predicted wave equation coefficients of a sample two-phase porous medium elastic wave propagation model are predicted, a physical constraint mechanism based on plane wave analysis is combined, and through back propagation, the network has stronger prediction stability and physical consistency, so that the predicted wave equation coefficients output by the two-phase medium wave characteristic learning network give consideration to both data accuracy and physical consistency requirements, thereby improving the physical consistency, expression accuracy and generalization ability of the constructed target two-phase porous medium elastic wave propagation model.

[0061] To facilitate understanding of the present embodiment, first, a neural network training method and a model construction method disclosed by the present application embodiment are introduced in detail. The execution subject of the neural network training method and the model construction method provided by the present application embodiment is generally an electronic device with certain computing power. The electronic device can be a server. The server can be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud service, cloud database, cloud computing, cloud storage, big data and artificial intelligence platform. In some possible implementation manners, the neural network training method and the model construction method can be realized by a processor calling computer readable instructions stored in a memory.

[0062] Next, a neural network training method provided by the present application embodiment is described in combination with the accompanying drawings.

[0063] Referring to Figure 1 Fig. 1 is a flowchart of a neural network training method according to an example embodiment of the present application, as shown in Figure 1 The neural network training method provided by the present disclosure embodiment includes steps S101-S104, wherein:

[0064] S101: Obtain a sample data set, wherein the sample data set includes a sample reservoir physical property parameter associated with a sample two-phase porous medium elastic wave propagation model.

[0065] To better understand the present embodiment, first, a two-phase porous medium elastic wave propagation model is introduced. The two-phase porous medium elastic wave propagation model includes an elastic wave propagation model and a viscoelastic wave propagation model. The elastic wave propagation model has an elastic wave characteristic, and the viscoelastic wave propagation model has a viscoelastic wave characteristic.

[0066] Biot model is an elastic wave propagation model, which is widely used to describe the propagation of P-wave and S-wave in fluid-saturated porous media. However, the Biot model cannot effectively explain the high-frequency dispersion and strong attenuation of waves in the low-frequency band (especially in the seismic wave frequency band).

[0067] Therefore, the Biot-Squirt (BISQ) model is proposed, which is also an elastic wave propagation model. The BISQ model enhances the description ability of microscale energy loss by introducing a squirt mechanism, such as the friction loss caused by the squirt of fluid in the pore throat into the pore.

[0068] In most practical problems, the reservoir medium not only behaves as a multiphase medium, but also has obvious viscoelastic behavior. Accordingly, the viscoelastic BISQ model is proposed, which is a viscoelastic wave propagation model.

[0069] Specifically, the two-phase porous medium elastic wave propagation model can be represented by the following formula (1):

[0070] (1)

[0071] wherein, ( , , , ) represents the wave equation coefficient, and represent the solid phase and the flow phase displacement tensor, represent the solid phase strain tensor, represent the flow phase strain tensor, represent the fluid viscosity coefficient, represent the porosity, and K represents the permeability. , , , wherein represents the solid matrix density, represents the pore fluid density, represents the solid-fluid coupling density.

[0072] In practical applications, the wave equation coefficient is usually difficult to obtain directly. The embodiments of the present disclosure mainly solve the problem that the wave equation coefficient of the two-phase porous medium elastic wave propagation model is difficult to obtain directly.

[0073] In this embodiment of the disclosure, considering deep learning technology, especially physical information neural networks (PINNs), which support the introduction of partial differential equation information or prior knowledge into the neural network training process, the physical rationality and generalization ability of the network output are improved, providing a new approach for modeling complex physical systems. To this end, the idea of ​​elastic wave propagation model of two-phase porous media is embedded into the deep neural network structure to break through the existing modeling bottleneck.

[0074] In practical applications, wave equation coefficients Often related to the viscoelastic modulus of a solid skeleton and Bio-Williams coefficient Biot fluid storage coefficient F, jet flow coefficient S, angular frequency ω, and solid matrix bulk modulus Lamé coefficient and Porosity Permeability K, fluid viscosity coefficient and solid matrix density Related to parameters. Through the wave equation coefficients It can reveal complex physical coefficients that are difficult to display or measure.

[0075] In this step, in order to train the network, various types of data can be collected in different environments to form sample datasets corresponding to different environmental complexities.

[0076] During network training, guidance is often based on physical information. In this embodiment, the elastic wave propagation model of a two-phase porous medium is used as the guiding physical information. Specifically, based on the elastic wave propagation model of the two-phase porous medium as the guiding physical information, reservoir property parameters that can improve the learning accuracy of the network are selected. A sample dataset is then constructed.

[0077] Optionally, a correlation analysis can be performed on the two-phase porous medium elastic wave propagation model and various reservoir physical parameters, and reservoir physical parameters with a correlation higher than a threshold with the two-phase porous medium elastic wave propagation model can be selected from the various reservoir physical parameters as sample reservoir physical parameters.

[0078] In some possible implementations, the sample dataset includes at least one of the following:

[0079] Angular frequency, bulk modulus of solid matrix, Lamé coefficient, porosity, permeability, and density of solid matrix.

[0080] The sample reservoir physical properties may include parameters inherent in the two-phase porous medium elastic wave propagation model itself, such as porosity. Permeability K and density of solid matrix may also include parameters related to the elastic wave propagation model of the two-phase porous medium, such as angular frequency ω, solid matrix bulk modulus and Lame coefficient and .

[0081] In this way, the above parameters are all key reservoir physical parameters of the elastic wave propagation model of the two-phase porous medium. By constructing a sample data set through these parameters, the physical characteristics of the elastic wave propagation model of the two-phase porous medium can be more comprehensively reflected, so that the two-phase medium wave characteristic learning network can learn more rich and accurate characteristics, which helps to further improve the prediction accuracy and physical consistency of the network for the elastic wave propagation model of the two-phase porous medium, enhances the generalization ability of the model, and makes the application of the model under different geological conditions more reliable and adaptable.

[0082] S102: inputting the sample data set into the two-phase medium wave characteristic learning network, and outputting a plurality of predicted wave equation coefficients of the sample elastic wave propagation model of the two-phase porous medium.

[0083] In this step, the sample data set can be input into the two-phase medium wave characteristic learning network, and the two-phase medium wave characteristic learning network can output a plurality of predicted wave equation coefficients of the sample elastic wave propagation model of the two-phase porous medium. , , , ).

[0084] In some possible implementations, the sample elastic wave propagation model of the two-phase porous medium includes a viscoelastic wave propagation model, the two-phase medium wave characteristic learning network includes a viscoelastic wave characteristic learning network, and at least part of the plurality of predicted wave equation coefficients are complex numbers; or, the sample elastic wave propagation model of the two-phase porous medium includes an elastic wave propagation model, the two-phase medium wave characteristic learning network includes an elastic wave characteristic learning network, and the plurality of predicted wave equation coefficients are all real numbers.

[0085] Here, in the case where the sample elastic wave propagation model of the two-phase porous medium includes an elastic wave propagation model, correspondingly, the two-phase medium wave characteristic learning network includes an elastic wave characteristic learning network, at this time, the plurality of predicted wave equation coefficients are all real numbers, that is , , , all only include real parts and do not include imaginary parts.

[0086] In the case that the sample dual-phase porous medium elastic wave propagation model comprises a viscoelastic wave propagation model, correspondingly, the dual-phase medium wave motion feature learning network comprises a viscoelastic wave motion feature learning network. For the viscoelastic wave propagation model, it means that in the process of seismic wave propagation, the medium response contains phase lag and energy dissipation, which needs to be described by physical quantities such as complex modulus. At least part of the plurality of predicted wave equation coefficients of the viscoelastic wave equation is often a frequency-dependent complex number, and the imaginary part directly reflects the absorption characteristics of the medium. The modeling of the viscoelastic wave propagation model inevitably involves complex number domain mathematical problems in theory.

[0087] Optionally, the plurality of predicted wave equation coefficients can all be complex numbers, that is, 、 、 、 all include real part parameters and imaginary part parameters.

[0088] In actual application, and the imaginary part parameters are small, if the imaginary part parameters of and are introduced into network calculation, the network may output and the imaginary part parameters of which are large, resulting in introduction of deviation. Alternatively, the plurality of predicted wave equation coefficients can be partially complex numbers and partially real numbers, thereby improving the accuracy of the dual-phase medium wave motion feature learning network.

[0089] Exemplarily, can be 、 complex numbers, 、 real numbers.

[0090] In this way, the specific types of the sample dual-phase porous medium elastic wave propagation model and the dual-phase medium wave motion feature learning network and the corresponding predicted wave equation coefficient forms are further clarified, so that learning can be performed on the two different types of models, namely the viscoelastic wave propagation model and the elastic wave propagation model, respectively, to ensure better adaptability and accuracy when processing different types of dual-phase porous medium elastic wave propagation models, further improve the physical consistency and generalization ability of the constructed target dual-phase porous medium elastic wave propagation model, and thus better meet the modeling needs of different types of dual-phase porous medium elastic wave propagation models in actual application.

[0091] In some possible implementation manners, the dual-phase medium wave characteristic learning network comprises an input module, a plurality of wave characteristic learning modules, and an output module, the input module is configured to receive an input sample data set, each wave characteristic learning module is configured to determine a predicted coefficient intermediate variable according to the sample data set, and the output module is configured to generate the predicted wave equation coefficient based on the predicted coefficient intermediate variable, the predicted coefficient intermediate variable being a real part parameter and an imaginary part parameter constituting the predicted wave equation coefficient.

[0092] Here, the wave characteristic learning modules are of the same structure. For example, each wave characteristic learning module comprises 50 neural units, and an optimizer adopts an adaptive moment estimation (Adam) optimization algorithm. When the wave characteristic learning module is configured to predict a predicted coefficient intermediate variable corresponding to a wave equation coefficient in a complex form, a linear rectification function (ReLU) is adopted as an activation function, and when the wave characteristic learning module is configured to predict a predicted coefficient intermediate variable corresponding to a wave equation coefficient in a real number form, a sigmoid function is adopted as an activation function.

[0093] For example, when the sample dual-phase porous medium elastic wave propagation model comprises an elastic wave propagation model, and the dual-phase medium wave characteristic learning network comprises an elastic wave characteristic learning network, the predicted wave equation coefficient can be obtained by using formula (2) as shown below:

[0094]

[0095]

[0096]

[0097] (2)

[0098] wherein, , , , represents a wave equation coefficient, , , , represents a predicted coefficient intermediate variable output by each wave characteristic learning module, represents an input sample data set, , , , represents a parameter of each wave characteristic learning module.

[0099] In the case where the sample dual-phase porous medium elastic wave propagation model comprises a viscoelastic wave propagation model, and the dual-phase medium wave motion feature learning network comprises a viscoelastic wave motion feature learning network, if the plurality of predicted wave equation coefficients are partly complex numbers and partly real numbers, the predicted wave equation coefficients can be represented by the following formula (3):

[0100]

[0101]

[0102]

[0103] (3)

[0104] wherein, , , , represents a wave equation coefficient, , , , , , represents a predicted coefficient intermediate variable output by each wave motion feature learning module, represents the input sample data set, , , , , , represents a parameter of each wave motion feature learning module.

[0105] In the case where the sample dual-phase porous medium elastic wave propagation model comprises a viscoelastic wave propagation model, and the dual-phase medium wave motion feature learning network comprises a viscoelastic wave motion feature learning network, if the plurality of predicted wave equation coefficients are complex numbers, the predicted wave equation coefficients can be represented by the following formula (4):

[0106]

[0107]

[0108]

[0109] (4)

[0110] wherein, , , , represents a wave equation coefficient, , 、 、 、 、 、 、 denote the prediction coefficient intermediate variables output by each wave characteristic learning module, denote the input sample dataset, 、 、 、 、 、 、 、 denote the parameters of each wave characteristic learning module.

[0111] In this way, by refining the dual-phase medium wave characteristic learning network into an input module, multiple wave characteristic learning modules, and an output module, the structure and functional division of the network are further optimized. This modular design not only improves the learning efficiency and accuracy of the network, but also enhances the adaptability and generalization ability of the network to complex dual-phase porous medium elastic wave propagation models, further improving the performance and reliability of network training.

[0112] In some possible implementations, the number of wave characteristic learning modules is consistent with the number of prediction coefficient intermediate variables.

[0113] For example, in combination with formula (2), it can be seen that, in the case where the sample dual-phase porous medium elastic wave propagation model includes an elastic wave propagation model and the dual-phase medium wave characteristic learning network includes an elastic wave characteristic learning network, the multiple prediction wave equation coefficients are all real numbers, at this time 、 、 、 each has 1 real part parameter, so there are 4 real part parameters in total, accordingly, 4 prediction coefficient intermediate variables need to be determined, so the number of wave characteristic learning modules is 4.

[0114] For another example, in combination with formula (3), it can be seen that, in the case where the sample dual-phase porous medium elastic wave propagation model includes a viscoelastic wave propagation model and the dual-phase medium wave characteristic learning network includes a viscoelastic wave characteristic learning network, the multiple prediction wave equation coefficients are partly complex numbers and partly real numbers, at this time 、 each has 1 real part parameter and 1 imaginary part parameter, 、 each has 1 real part parameter, so there are 4 real part parameters and 2 imaginary part parameters in total, accordingly, 6 prediction coefficient intermediate variables need to be determined, so the number of wave characteristic learning modules is 6.

[0115] For example, in combination with formula (4), it can be seen that when the sample dual-phase porous medium elastic wave propagation model includes a viscoelastic wave propagation model and the dual-phase medium wave feature learning network includes a viscoelastic wave feature learning network, the plurality of predicted wave equation coefficients are complex numbers, and at this time 、 、 、 each has 1 real part parameter and 1 imaginary part parameter, so there are 4 real parts and 4 imaginary parts in total, and accordingly, 8 predicted coefficient intermediate variables need to be determined, so the number of wave feature learning modules is 8.

[0116] In this way, by making the number of wave feature learning modules consistent with the number of predicted coefficient intermediate variables, the network structure is precisely matched with the task requirements, and each wave feature learning module is responsible for extracting and processing features related to one predicted coefficient intermediate variable, ensuring the pertinence and efficiency of feature extraction. This one-to-one module and variable correspondence relationship enables the network to learn and optimize each predicted coefficient intermediate variable more meticulously, thereby further improving the accuracy and reliability of the predicted wave equation coefficients. At the same time, this structural design also enhances the scalability and flexibility of the network, facilitating the adjustment of the number of modules according to different task requirements, and further improving the performance and adaptability of the dual-phase medium wave feature learning network.

[0117] For example, refer to Figure 2 , Figure 2 is a structural diagram of a neural network according to an example embodiment of the present application. As shown in Figure 2 , the present example illustrates the case of a viscoelastic wave propagation model in which part of the predicted wave equation coefficients shown in formula (3) are complex numbers, and the dual-phase medium wave feature learning network includes an input module, 6 wave feature learning modules, and an output module. The input module can receive a sample data set to provide a basis for subsequent processing; the wave feature learning module can extract and process key information in the sample data set to determine the predicted coefficient intermediate variable, which helps to capture complex wave features more meticulously; and the output module can generate predicted wave equation coefficients based on these predicted coefficient intermediate variables, making the prediction results more accurate and complete.

[0118] Thus, for the viscoelastic wave propagation model, to more accurately depict its dispersion and attenuation characteristics, the embodiment introduces a partial complex neural network structure, models the intermediate variables of the prediction coefficients involved in the wave characteristic learning module and the output module as complex numbers, specifically adopts a double-channel real part / imaginary part parallel representation method, and the network training process supports the back propagation of complex parameters, supports the expression of the intermediate variables of the prediction coefficients in the complex domain during the network training process, so that the dual-phase medium wave characteristic learning network has the expression ability to process viscoelastic characteristics such as frequency-dependent energy dissipation and phase lag, thereby enabling the dual-phase medium wave characteristic learning network to directly learn and output complex-form wave equation coefficients, thereby improving the expression ability and physical consistency of viscoelastic medium characteristics. The trained dual-phase medium wave characteristic learning network output can effectively reflect the physical mechanisms such as energy dissipation and phase lag in the medium under the condition of satisfying the complex constraint, and is closer to the real data.

[0119] For the viscoelastic wave propagation model shown in formula (2) or the viscoelastic wave propagation model in which all the prediction wave equation coefficients shown in formula (4) are complex numbers, the corresponding dual-phase medium wave characteristic learning network structure is similar to the dual-phase medium wave characteristic learning network structure corresponding to the viscoelastic wave propagation model in which part of the prediction wave equation coefficients shown in formula (3) are complex numbers, and only the number of wave characteristic learning modules needs to be adjusted accordingly.

[0120] S103: Perform plane wave analysis based on the plurality of prediction wave equation coefficients to determine the prediction dispersion and attenuation characteristics of the sample dual-phase porous medium elastic wave propagation model.

[0121] Here, in the traditional network training, if the dual-phase medium wave characteristic learning network outputs prediction wave equation coefficients, the real values of the wave equation coefficients are often used as network training labels for supervised learning. Considering that the real values of the wave equation coefficients are difficult to obtain directly in practice, the embodiment of the present disclosure adopts a training method driven by physical consistency, and uses the easily measured dispersion and attenuation characteristics as network training labels.

[0122] Alternatively, the prediction dispersion and attenuation characteristics include a predicted P-wave velocity and a predicted S-wave velocity. Alternatively, the prediction dispersion and attenuation characteristics include a predicted P-wave velocity, a predicted S-wave velocity, and a predicted P-wave inverse quality factor.

[0123] Here, the S-wave inverse quality factor has a small value, so it is not used as a network training label in the embodiment of the present disclosure.

[0124] In some possible implementations, the plane wave analysis based on the plurality of prediction wave equation coefficients to determine the prediction dispersion and attenuation characteristics of the sample dual-phase porous medium elastic wave propagation model includes:

[0125] acquire the porosity fluid density and the fluid viscosity coefficient corresponding to the sample two-phase porous medium elastic wave propagation model;

[0126] perform plane wave analysis based on the plurality of predicted wave equation coefficients, the porosity fluid density, and the fluid viscosity coefficient to determine the predicted dispersion attenuation characteristic of the sample two-phase porous medium elastic wave propagation model.

[0127] In the above steps, the porosity fluid density and the fluid viscosity coefficient corresponding to the sample two-phase porous medium elastic wave propagation model can be acquired, and a reference angular frequency can be acquired, plane wave analysis can be performed on an expression (such as formula (1)) of the two-phase porous medium elastic wave propagation model by using Helmholtz decomposition and Fourier transform based on the plurality of predicted wave equation coefficients, the porosity fluid density, the fluid viscosity coefficient, and the reference angular frequency, to obtain a correlation between wave equation coefficients and dispersion attenuation characteristics, and the predicted dispersion attenuation characteristic of the sample two-phase porous medium elastic wave propagation model can be determined based on the correlation between the wave equation coefficients and the dispersion attenuation characteristics, the plurality of predicted wave equation coefficients, the sample data set, the porosity fluid density, the fluid viscosity coefficient, and the reference angular frequency.

[0128] Specifically, the correlation between the wave equation coefficients and the dispersion attenuation characteristics can be shown in the following formula (5):

[0129]

[0130]

[0131]

[0132] wherein, represents a P-wave velocity, represents a S-wave velocity, represents a P-wave inverse quality factor, represents a P-wave calculation intermediate variable, represents a S-wave calculation intermediate variable.

[0133] Here, the P-wave velocity may be a phase velocity of the P-wave, and the S-wave velocity may be a phase velocity of the S-wave.

[0134] wherein, the P-wave calculation intermediate variable and the S-wave calculation intermediate variable may be determined by the following formula (6):

[0135] (6)

[0136] wherein, represents a longitudinal wave calculation intermediate variable, represents a transverse wave calculation intermediate variable, , , , ) represents a wave equation coefficient, , , , , , , , represents a solid matrix density, represents a pore fluid density, represents a solid-fluid coupling density, represents a reference angular frequency, represents an imaginary unit, represents an angular frequency, represents a correlation relationship calculation intermediate variable, represents a porosity, represents a fluid viscosity coefficient, and K represents a permeability.

[0137] Here, it can be seen in combination with formula (6) that the first expression therein is a quadratic equation about , and two roots can be solved through the expression, and two longitudinal wave speeds can be obtained, one is a fast P-wave speed, and one is a slow P-wave speed, and the fast P-wave speed is greater than the slow P-wave speed. Since the value of the slow P-wave speed is small, the fast P-wave speed is only used as the network training label in the embodiment of the present disclosure, that is, the longitudinal wave speed in the embodiment of the present disclosure represents the fast P-wave speed.

[0138] In this way, by introducing the pore fluid density and the fluid viscosity coefficient in the plane wave analysis process, the determination process of the predicted dispersion attenuation characteristic is further improved, so that the physical phenomena in the two-phase porous medium can be more comprehensively reflected, the predicted dispersion attenuation characteristic is more accurately close to the real situation, which is helpful for subsequent more accurate evaluation of the error loss between the predicted dispersion attenuation characteristic and the real dispersion attenuation characteristic, so as to more effectively adjust the parameters of the two-phase medium wave characteristic learning network, and then improve the accuracy and reliability of the predicted wave equation coefficient output by the network, which is helpful to enhance the physical consistency and generalization ability of the constructed target two-phase porous medium elastic wave propagation model.

[0139] S104: According to the error loss between the predicted dispersion attenuation characteristic and the real dispersion attenuation characteristic of the sample two-phase porous medium elastic wave propagation model, adjust the parameters of the two-phase medium wave characteristic learning network until the cutoff condition is met. ​

[0140] In this step, after determining the predicted dispersion attenuation characteristics, a loss function can be constructed in combination with the physical constraints of the sample dual-phase porous medium elastic wave propagation model to determine the error loss between the predicted dispersion attenuation characteristics and the true dispersion attenuation characteristics of the sample dual-phase porous medium elastic wave propagation model, so as to adjust the parameters of the dual-phase medium wave characteristic learning network according to the error loss until a stop condition is met.

[0141] In this way, the relationship between the predicted wave equation coefficients and the predicted dispersion attenuation characteristics can be established in the back propagation process of network training, so that the physical model information is explicitly constrained in the network structure during the training process. By adding physical constraints in network training, the physical consistency of network output can be effectively improved, and the shortcomings of traditional end-to-end neural networks such as poor interpretability and “black box” can be overcome.

[0142] Alternatively, the training stop condition can be that the error loss between the predicted dispersion attenuation characteristics and the true dispersion attenuation characteristics is less than a preset error, or the number of training iterations of the dual-phase medium wave characteristic learning network reaches a preset number, etc.

[0143] In some possible implementations, the predicted dispersion attenuation characteristics include a predicted P-wave velocity and a predicted S-wave velocity, and the true dispersion attenuation characteristics include a true P-wave velocity and a true S-wave velocity.

[0144] The error loss between the predicted dispersion attenuation characteristics and the true dispersion attenuation characteristics of the sample dual-phase porous medium elastic wave propagation model is determined by the following steps:

[0145] The error loss between the predicted dispersion attenuation characteristics and the true dispersion attenuation characteristics is determined according to the deviation between the predicted P-wave velocity and the true P-wave velocity and the deviation between the predicted S-wave velocity and the true S-wave velocity.

[0146] Alternatively, the predicted dispersion attenuation characteristics include a predicted P-wave velocity, a predicted S-wave velocity, and a predicted P-wave inverse quality factor, and the true dispersion attenuation characteristics include a true P-wave velocity, a true S-wave velocity, and a true P-wave inverse quality factor.

[0147] The error loss between the predicted dispersion attenuation characteristics and the true dispersion attenuation characteristics of the sample dual-phase porous medium elastic wave propagation model is determined by the following steps:

[0148] The error loss between the predicted dispersion attenuation characteristics and the true dispersion attenuation characteristics is determined according to the deviation between the predicted P-wave velocity and the true P-wave velocity, the deviation between the predicted S-wave velocity and the true S-wave velocity, and the deviation between the predicted P-wave inverse quality factor and the true P-wave inverse quality factor.

[0149] For example, the error loss can be determined by formula (7) as follows:

[0150] (7)

[0151] wherein Loss represents the error loss, represents the predicted P-wave velocity, represents the true P-wave velocity, represents the predicted S-wave velocity, represents the true S-wave velocity, represents the predicted P-wave inverse quality factor, represents the true P-wave inverse quality factor, and N is the number of samples. and respectively correspond to the weights of the deviations between the predicted P-wave velocity and the true P-wave velocity, the deviations between the predicted S-wave velocity and the true S-wave velocity, and the deviations between the predicted P-wave inverse quality factor and the true P-wave inverse quality factor.

[0152] Here, if some data is missing, the corresponding weight can be set to 0.

[0153] In this way, the dispersion attenuation feature is selected as the network training label, and the correlation between the dispersion attenuation feature and the wave equation coefficient is derived through the plane wave analysis method, so that the loss function contains the velocity deviation, the inverse quality factor deviation, and the physical constraint information of the sample two-phase porous medium elastic wave propagation model, thereby guiding the network output to meet the data accuracy and physical consistency requirements, and the correlation is not embedded in the forward propagation path of the network training, but is used in the backward propagation stage as a physical constraint term to constrain the error loss in the determination, so that the network training process has stronger prediction stability and physical consistency.

[0154] In some possible implementations, when training the two-phase medium wave feature learning network, a supervised learning method is adopted, the sample data set and the true dispersion attenuation feature can be constructed by synthetic data or laboratory measurement data, and during the training process, a batch gradient descent strategy can be adopted, and learning rate decay, regularization, and early stopping strategies can be combined to improve the training efficiency and accuracy, so that the network can stably converge under different parameter conditions, the predicted dispersion attenuation feature determined according to the predicted wave equation coefficient has a high fitting degree with the actual data, and has good generalization ability.

[0155] For a clearer display of the training process of the neural network, please refer to Figure 3 , Figure 3 is a process diagram of the training of a neural network shown in an exemplary embodiment of the present application. As Figure 3As shown in the foregoing embodiments, the sample dataset is acquired, the sample dataset is input into the dual-phase medium wave motion feature learning network, a plurality of predicted wave equation coefficients of the sample dual-phase porous medium elastic wave propagation model are output, plane wave analysis is performed based on the plurality of predicted wave equation coefficients, a predicted dispersion attenuation feature of the sample dual-phase porous medium elastic wave propagation model is determined, parameters of the dual-phase medium wave motion feature learning network are adjusted according to an error loss between the predicted dispersion attenuation feature and a true dispersion attenuation feature of the sample dual-phase porous medium elastic wave propagation model until a stop condition is met. In this way, on the basis of following the wave motion law of the dual-phase porous medium elastic wave propagation model, the dependence of the dual-phase porous medium elastic wave propagation model on a large number of physical parameters is avoided, so that the trained dual-phase medium wave motion feature learning network has good physical consistency, interpretability, expression accuracy and generalization ability at the same time, and is suitable for a variety of complex reservoir environments. For specific descriptions, reference can be made to the foregoing embodiments, which will not be described here again.

[0156] The neural network training method provided by the embodiments of the present application, when training the dual-phase medium wave motion feature learning network, takes the reservoir physical parameters as input, predicts a plurality of predicted wave equation coefficients of the sample dual-phase porous medium elastic wave propagation model, combines a physical constraint mechanism based on plane wave analysis, adjusts the parameters of the dual-phase medium wave motion feature learning network according to an error loss between the predicted dispersion attenuation feature and the true dispersion attenuation feature of the sample dual-phase porous medium elastic wave propagation model, and makes the network have stronger prediction stability and physical consistency through back propagation, so as to ensure that the predicted wave equation coefficients output by the dual-phase medium wave motion feature learning network take into account both data accuracy and physical consistency requirements, thereby improving the physical consistency, expression accuracy and generalization ability of the constructed target dual-phase porous medium elastic wave propagation model.

[0157] It can be understood that after the training of the dual-phase medium wave motion feature learning network is completed, the trained dual-phase medium wave motion feature learning network can be used to generate wave equation coefficients for the construction of the dual-phase porous medium elastic wave propagation model. Therefore, the embodiments of the present disclosure also provide a model construction method, which is described with reference to Figure 4 , Figure 4 The flowchart of the model construction method provided by the embodiments of the present disclosure is shown in FIG. 13. Figure 4 As shown in the foregoing embodiments, the model construction method provided by the embodiments of the present disclosure includes steps S401-S403, wherein:

[0158] S401: Acquire a target dataset, the target dataset including target reservoir physical parameters associated with a target dual-phase porous medium elastic wave propagation model.

[0159] In this step, when it is needed to build the dual-phase porous medium elastic wave propagation model, the target data set can be obtained and the dual-phase medium wave characteristic learning network trained according to the neural network training method described above.

[0160] Here, the way of determining the target data set is similar to that of determining the sample data set, and the specific steps are described in the foregoing embodiments, which will not be repeated here.

[0161] S402: inputting the target data set into the trained dual-phase medium wave characteristic learning network to output a plurality of wave equation coefficients of the target dual-phase porous medium elastic wave propagation model; the trained dual-phase medium wave characteristic learning network is trained by the neural network training method described above.

[0162] In this step, the target data set can be input into the trained dual-phase medium wave characteristic learning network, and the dual-phase medium wave characteristic learning network can output a plurality of predicted wave equation coefficients of the target dual-phase porous medium elastic wave propagation model.

[0163] Here, the application process of the dual-phase medium wave characteristic learning network is similar to the training process, and the specific steps are described in the foregoing embodiments, which will not be repeated here.

[0164] S403: constructing the target dual-phase porous medium elastic wave propagation model based on the plurality of wave equation coefficients.

[0165] Here, after obtaining the plurality of wave equation coefficients, the target dual-phase porous medium elastic wave propagation model can be constructed, and an expression of the target dual-phase porous medium elastic wave propagation model as shown in formula (1) is obtained.

[0166] In some possible implementation manners, the method further includes:

[0167] performing plane wave analysis based on the plurality of wave equation coefficients to determine the dispersion attenuation characteristics of the target dual-phase porous medium elastic wave propagation model;

[0168] determining the propagation information of the longitudinal wave and the transverse wave based on the dispersion attenuation characteristics.

[0169] Here, the dispersion attenuation characteristics of the target dual-phase porous medium elastic wave propagation model can also be directly predicted by means of the plane wave analysis mechanism adopted during network training, so that the propagation information of the longitudinal wave and the transverse wave is determined based on the dispersion attenuation characteristics.

[0170] The propagation information of the longitudinal wave and the transverse wave can include the longitudinal wave velocity, the transverse wave velocity, etc.

[0171] In this way, not only the wave equation coefficients can be obtained, but also the wave propagation characteristics closely related to practical applications can be obtained. This conversion from theoretical coefficients to actual wave propagation information enhances the practicality and interpretability of the model, enabling it to more intuitively serve practical application scenarios such as geological exploration and reservoir evaluation, and further improving the application value and guiding significance of the target dual-phase porous medium elastic wave propagation model.

[0172] The dual-phase porous medium elastic wave propagation model constructed by the embodiments of the present disclosure can accurately depict the dispersion and attenuation behavior of the medium under multiple frequency bands. Compared with other traditional models, the physical consistency, expression accuracy and generalization ability are significantly improved, and significant advantages are shown in wave velocity prediction accuracy, wave propagation feature description ability and adaptability to complex reservoirs. For example, refer to Figure 5 and Figure 6 , Figure 5 FIG. 1 is a schematic diagram of the P-wave dispersion characteristics according to an example embodiment of the present disclosure, Figure 6 FIG. 2 is a schematic diagram of the S-wave dispersion characteristics according to an example embodiment of the present disclosure. As shown in Figure 5 and Figure 6 , the dashed line represents the P-wave dispersion characteristics and the S-wave dispersion characteristics predicted by the Biot model, the solid line represents the P-wave dispersion characteristics and the S-wave dispersion characteristics obtained by the embodiments of the present disclosure, and the circle point represents the real data collected. It can be seen that, compared with the Biot model, the P-wave dispersion characteristics and the S-wave dispersion characteristics obtained by the embodiments of the present disclosure are more consistent with the real data, and can effectively reflect the physical mechanisms such as energy dissipation and phase lag in the medium. In particular, in low porosity and permeability, fracture type or strong dissipation shale and other dissipative complex media, the embodiments of the present disclosure can still accurately model without measuring all model parameters, significantly reducing the modeling threshold, improving the engineering applicability and promotion value of the method, expanding the application boundary of complex neural networks in the field of geophysical modeling, and having good engineering applicability and realizability.

[0173] The model construction method provided by the embodiments of the present disclosure can efficiently output a plurality of wave equation coefficients of the target dual-phase porous medium elastic wave propagation model through the dual-phase medium wave feature learning network trained by the neural network training method, so as to construct the target dual-phase porous medium elastic wave propagation model. Since the dual-phase medium wave feature learning network has strong prediction stability and physical consistency, the output wave equation coefficients not only meet the data accuracy requirements, but also satisfy the physical consistency constraints, thereby improving the physical consistency, expression accuracy and generalization ability of the constructed target dual-phase porous medium elastic wave propagation model.

[0174] Those skilled in the art can understand that the sequence of writing each step in the foregoing method of the specific embodiment does not mean a strict execution sequence and does not constitute any limitation on the implementation process. The specific execution sequence of each step should be determined by its function and possible internal logic.

[0175] Corresponding to the foregoing embodiment of the neural network training method, the present application also provides an embodiment of a neural network training device.

[0176] Please refer to Figure 7 A schematic diagram of a neural network training device according to an example embodiment of the present application is shown. As shown in Figure 7 The neural network training device 700 provided by the embodiment of the present application includes:

[0177] The sample acquisition module 701 is configured to acquire a sample data set, wherein the sample data set includes sample reservoir physical property parameters associated with a sample dual-phase porous medium elastic wave propagation model.

[0178] The network prediction module 702 is configured to input the sample data set into a dual-phase medium wave characteristic learning network, and output a plurality of predicted wave equation coefficients of the sample dual-phase porous medium elastic wave propagation model.

[0179] The feature analysis module 703 is configured to perform plane wave analysis based on the plurality of predicted wave equation coefficients, and determine a predicted dispersion attenuation characteristic of the sample dual-phase porous medium elastic wave propagation model.

[0180] The parameter adjustment module 704 is configured to adjust parameters of the dual-phase medium wave characteristic learning network according to an error loss between the predicted dispersion attenuation characteristic and a true dispersion attenuation characteristic of the sample dual-phase porous medium elastic wave propagation model until a cutoff condition is met.

[0181] In some possible implementation manners, the feature analysis module 703 is specifically configured to:

[0182] acquire a pore fluid density and a fluid viscosity coefficient corresponding to the sample dual-phase porous medium elastic wave propagation model;

[0183] perform plane wave analysis based on the plurality of predicted wave equation coefficients, the pore fluid density and the fluid viscosity coefficient, and determine a predicted dispersion attenuation characteristic of the sample dual-phase porous medium elastic wave propagation model.

[0184] In some possible implementation manners, the predicted dispersion attenuation characteristic includes a predicted P-wave velocity and a predicted S-wave velocity, and the true dispersion attenuation characteristic includes a true P-wave velocity and a true S-wave velocity.

[0185] The parameter adjustment module 704 determines the error loss between the predicted dispersion attenuation characteristics and the real dispersion attenuation characteristics of the sample dual-phase porous medium elastic wave propagation model by the following steps:

[0186] According to the deviation between the predicted P-wave velocity and the real P-wave velocity, the deviation between the predicted S-wave velocity and the real S-wave velocity, and the deviation between the predicted P-wave inverse quality factor and the real P-wave inverse quality factor, the error loss between the predicted dispersion attenuation characteristics and the real dispersion attenuation characteristics is determined.

[0187] Alternatively, the predicted dispersion attenuation characteristics include a predicted P-wave velocity, a predicted S-wave velocity, and a predicted P-wave inverse quality factor, and the real dispersion attenuation characteristics include a real P-wave velocity, a real S-wave velocity, and a real P-wave inverse quality factor.

[0188] The parameter adjustment module 704 determines the error loss between the predicted dispersion attenuation characteristics and the real dispersion attenuation characteristics of the sample dual-phase porous medium elastic wave propagation model by the following steps:

[0189] According to the deviation between the predicted P-wave velocity and the real P-wave velocity, the deviation between the predicted S-wave velocity and the real S-wave velocity, and the deviation between the predicted P-wave inverse quality factor and the real P-wave inverse quality factor, the error loss between the predicted dispersion attenuation characteristics and the real dispersion attenuation characteristics is determined.

[0190] In some possible implementation manners, the sample dual-phase porous medium elastic wave propagation model includes a viscoelastic wave propagation model, the dual-phase medium wave characteristic learning network includes a viscoelastic wave characteristic learning network, and at least part of the plurality of predicted wave equation coefficients are complex numbers.

[0191] Alternatively, the sample dual-phase porous medium elastic wave propagation model includes an elastic wave propagation model, the dual-phase medium wave characteristic learning network includes an elastic wave characteristic learning network, and all of the plurality of predicted wave equation coefficients are real numbers.

[0192] In some possible implementation manners, the dual-phase medium wave characteristic learning network includes an input module, a plurality of wave characteristic learning modules, and an output module, the input module is configured to receive the input sample data set, each of the wave characteristic learning modules is configured to determine a predicted coefficient intermediate variable according to the sample data set, and the output module is configured to generate the predicted wave equation coefficient based on the predicted coefficient intermediate variable, the predicted coefficient intermediate variable being a real part parameter and an imaginary part parameter that constitute the predicted wave equation coefficient.

[0193] In some possible implementation manners, the number of the wave characteristic learning modules is consistent with the number of the predicted coefficient intermediate variables.

[0194] In some possible implementation manners, the sample data set comprises at least one of the following:

[0195] The angular frequency, the solid matrix volume modulus, the Lame coefficient, the porosity, the permeability, and the solid matrix density.

[0196] Corresponding to the foregoing model construction method embodiments, the present application also provides model construction device embodiments.

[0197] Referring to Figure 8 FIG. 1 is a schematic diagram of a model construction device according to an example embodiment of the present application. As shown in FIG. 1, Figure 8 The model construction device 800 provided by the embodiment of the present application comprises:

[0198] The data acquisition module 801 is configured to acquire a target data set comprising a target reservoir physical property parameter associated with a target dual-phase porous medium elastic wave propagation model.

[0199] The network processing module 802 is configured to input the target data set into a trained dual-phase medium wave motion feature learning network, and output a plurality of wave equation coefficients of the target dual-phase porous medium elastic wave propagation model; the trained dual-phase medium wave motion feature learning network is obtained by training the neural network according to the neural network training method described above.

[0200] The model construction module 803 is configured to construct the target dual-phase porous medium elastic wave propagation model based on the plurality of wave equation coefficients.

[0201] In some possible implementation manners, the model construction device 800 further comprises an information determination module 804, which is configured to:

[0202] determine the dispersion attenuation characteristics of the target dual-phase porous medium elastic wave propagation model based on the plane wave analysis of the plurality of wave equation coefficients;

[0203] determine the propagation information of the longitudinal wave and the transverse wave based on the dispersion attenuation characteristics.

[0204] The implementation process of the functions and roles of each module in the above device is specifically described in the implementation process of the corresponding steps in the above method, and will not be repeated here.

[0205] For the apparatus embodiment, since it basically corresponds to the method embodiment, the relevant part can be seen from the part of the method embodiment. The apparatus embodiment described above is only illustrative, wherein the modules described as separate components can or can not be physically separated, and the components displayed as modules can or can not be physical units, i.e., can be located in one place or distributed on multiple network units. Part or all of the modules can be selected to achieve the purpose of the application scheme according to actual needs. Those skilled in the art can understand and implement it without creative labor.

[0206] Based on the same technical concept, the embodiment of the application also provides a computer device 900, as shown in Figure 9 The structure diagram of a computer device according to an example embodiment of the application is shown, which includes:

[0207] The processor 910, the memory 920, and the bus 930. The memory 920 is used to store the execution instructions, including the memory 921 and the external memory 922; the memory 921 here is also called the internal memory, used to temporarily store the operation data in the processor 910 and the data exchanged with the external memory 922 such as a hard disk, and the processor 910 exchanges data with the external memory 922 through the memory 921.

[0208] In the embodiment of the application, the memory 920 is specifically used to store the application program code for executing the scheme of the application, and is controlled to execute by the processor 910. That is, when the electronic device 900 is running, the processor 910 and the memory 920 communicate through the bus 930, or the processor 910 communicates with the memory 920 through other ways, so that the processor 910 executes the application program code stored in the memory 920, and further executes the steps of the neural network training method or the model construction method described in any of the preceding embodiments.

[0209] The memory 920 can be, but is not limited to, a random access memory (RAM), a read only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), etc.

[0210] Processor 910 may be an integrated circuit chip with signal processing capabilities. The aforementioned processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this invention. The general-purpose processor can be a microprocessor or any conventional processor.

[0211] It is understood that the structures illustrated in the embodiments of this application do not constitute a specific limitation on the electronic device 900. In other embodiments of this application, the electronic device 900 may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0212] This disclosure also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the neural network training method or model building method described in the above method embodiments. The storage medium can be a volatile or non-volatile computer-readable storage medium.

[0213] This disclosure also provides a computer program product, which stores a computer program. When the computer program is run by a processor, it executes the steps of the neural network training method or model building method provided in any of the above embodiments of this disclosure. For details, please refer to the above method embodiments, which will not be repeated here.

[0214] The aforementioned computer program product can be implemented through hardware, software, or a combination thereof. In one optional embodiment, the computer program product is specifically embodied in a computer storage medium, which can be a volatile or non-volatile computer-readable storage medium. In another optional embodiment, the computer program product is specifically embodied in a software product, such as a software development kit (SDK), etc.

[0215] Furthermore, embodiments of the subject matter and functional operation described in this specification can be implemented in the following ways: digital electronic circuits, tangibly embodied computer software or firmware, computer hardware including the structures disclosed in this specification and their structural equivalents, or combinations thereof. Embodiments of the subject matter described in this specification can be implemented as one or more computer programs, i.e., one or more modules of computer program instructions encoded on a tangible, non-transitory program carrier for execution by a data processing apparatus or for controlling the operation of a data processing apparatus. Alternatively or additionally, program instructions may be encoded on artificially generated propagation signals, such as machine-generated electrical, optical, or electromagnetic signals, which are generated to encode information and transmit it to a suitable receiving device for execution by the data processing apparatus. The computer storage medium may be a machine-readable storage device, a machine-readable storage substrate, a random or serial access memory device, or combinations thereof.

[0216] The processing and logic flow described in this specification can be executed by one or more programmable computers that execute one or more computer programs to perform corresponding functions by operating on input data and generating output. The processing and logic flow can also be executed by dedicated logic circuitry—such as FPGAs (Field-Programmable Gate Arrays) or ASICs (Application-Specific Integrated Circuits), and the device can also be implemented as dedicated logic circuitry.

[0217] Suitable computers for executing computer programs include, for example, general-purpose and / or special-purpose microprocessors, or any other type of central processing unit. Typically, the central processing unit receives instructions and data from read-only memory and / or random access memory. The basic components of a computer include a central processing unit for implementing or executing instructions and one or more memory devices for storing instructions and data. Typically, a computer will also include one or more mass storage devices for storing data, such as disks, magneto-optical disks, or optical disks, or the computer will be operatively coupled to such mass storage devices to receive data from or transfer data to them, or both. However, a computer is not required to have such devices. Furthermore, a computer can be embedded in another device, such as a mobile phone, a personal digital assistant (PDA), a mobile audio or video player, a game console, a global positioning system (GPS) receiver, or a portable storage device such as a universal serial bus (USB) flash drive, to name a few.

[0218] Computer-readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media, and memory devices, such as semiconductor memory devices (e.g., EPROM, EEPROM, and flash memory devices), magnetic disks (e.g., internal hard disks or removable disks), magneto-optical disks, and CD-ROM and DVD-ROM disks. Processors and memory may be supplemented by or incorporated into dedicated logic circuitry.

[0219] While this specification contains numerous specific implementation details, these should not be construed as limiting the scope of any invention or the scope of the claims, but rather are primarily intended to describe features of specific embodiments of a particular invention. Certain features described in the various embodiments herein may also be implemented in combination in a single embodiment. Conversely, various features described in a single embodiment may also be implemented separately in various embodiments or in any suitable sub-combination. Furthermore, while features may function in certain combinations as described above and even initially claimed in this way, one or more features from a claimed combination may be removed from that combination in some cases, and a claimed combination may refer to a sub-combination or a variation thereof.

[0220] Similarly, although the operations are depicted in a specific order in the accompanying drawings, this should not be construed as requiring these operations to be performed in the specific order shown or sequentially, or requiring all illustrated operations to be performed to achieve the desired result. In some cases, multitasking and parallel processing may be advantageous. Furthermore, the separation of various system modules and components in the above embodiments should not be construed as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product or packaged into multiple software products.

[0221] Thus, specific embodiments of the subject matter have been described. Other embodiments are within the scope of the appended claims. In some cases, the actions recited in the claims may be performed in a different order and still achieve the desired result. Furthermore, the processes depicted in the drawings are not necessarily shown in a specific order or sequence to achieve the desired result. In some implementations, multitasking and parallel processing may be advantageous.

[0222] The above description is merely a preferred 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 scope of protection of this application.

Claims

1. A neural network training method, characterized in that, The method includes: Obtain a sample dataset, which includes sample reservoir physical property parameters associated with the elastic wave propagation model of the sample two-phase porous medium; The sample dataset is input into a two-phase medium wave characteristic learning network, which outputs multiple predicted wave equation coefficients of the sample two-phase porous medium elastic wave propagation model. Plane wave analysis is performed based on the coefficients of the multiple predicted wave equations to determine the predicted dispersion attenuation characteristics of the elastic wave propagation model of the sample two-phase porous medium. Based on the error loss between the predicted dispersion attenuation characteristics and the actual dispersion attenuation characteristics of the sample two-phase porous medium elastic wave propagation model, the parameters of the two-phase medium wave characteristic learning network are adjusted until the cutoff condition is met.

2. The method according to claim 1, characterized in that, The step of performing plane wave analysis based on the multiple predicted wave equation coefficients to determine the predicted dispersion attenuation characteristics of the elastic wave propagation model of the sample two-phase porous medium includes: Obtain the pore fluid density and fluid viscosity coefficient corresponding to the elastic wave propagation model of the sample two-phase porous medium; Plane wave analysis is performed based on the coefficients of the multiple predicted wave equations, the pore fluid density, and the fluid viscosity coefficient to determine the predicted dispersion attenuation characteristics of the elastic wave propagation model of the sample two-phase porous medium.

3. The method according to claim 1, characterized in that, The predicted dispersion attenuation features include the predicted P-wave velocity and the predicted S-wave velocity, and the actual dispersion attenuation features include the actual P-wave velocity and the actual S-wave velocity. The error loss between the predicted dispersion attenuation characteristics and the true dispersion attenuation characteristics of the sample two-phase porous medium elastic wave propagation model is determined by the following steps: Based on the deviation between the predicted P-wave velocity and the actual P-wave velocity, and the deviation between the predicted S-wave velocity and the actual S-wave velocity, the error loss between the predicted dispersion attenuation feature and the actual dispersion attenuation feature is determined. Alternatively, the predicted dispersion attenuation features include the predicted P-wave velocity, the predicted S-wave velocity, and the predicted inverse P-wave quality factor, and the actual dispersion attenuation features include the actual P-wave velocity, the actual S-wave velocity, and the actual inverse P-wave quality factor. The error loss between the predicted dispersion attenuation characteristics and the true dispersion attenuation characteristics of the sample two-phase porous medium elastic wave propagation model is determined by the following steps: The error loss between the predicted dispersion attenuation feature and the actual dispersion attenuation feature is determined based on the deviation between the predicted P-wave velocity and the actual P-wave velocity, the deviation between the predicted S-wave velocity and the actual S-wave velocity, and the deviation between the predicted P-wave inverse quality factor and the actual P-wave inverse quality factor.

4. The method according to claim 1, characterized in that, The sample two-phase porous medium elastic wave propagation model includes a viscoelastic wave propagation model, the two-phase medium wave characteristic learning network includes a viscoelastic wave characteristic learning network, and at least some of the coefficients of the plurality of predicted wave equations are complex numbers. Alternatively, the sample two-phase porous medium elastic wave propagation model includes an elastic wave propagation model, the two-phase medium wave characteristic learning network includes an elastic wave characteristic learning network, and the coefficients of the plurality of predicted wave equations are all real numbers.

5. The method according to any one of claims 1-4, characterized in that, The two-phase medium wave characteristic learning network includes an input module, multiple wave characteristic learning modules, and an output module. The input module is used to receive the input sample dataset. Each wave characteristic learning module is used to determine intermediate variables of the prediction coefficients based on the sample dataset. The output module is used to generate the predicted wave equation coefficients based on the intermediate variables of the prediction coefficients. The intermediate variables of the prediction coefficients are the real part parameters and imaginary part parameters that make up the predicted wave equation coefficients.

6. The method according to claim 5, characterized in that, The number of the fluctuation feature learning modules is the same as the number of intermediate variables of the prediction coefficients.

7. The method according to claim 1, characterized in that, The sample dataset includes at least one of the following: Angular frequency, bulk modulus of solid matrix, Lamé coefficient, porosity, permeability, and density of solid matrix.

8. A model construction method, characterized in that, The method includes: Obtain the target dataset, which includes target reservoir physical property parameters associated with the target two-phase porous medium elastic wave propagation model; The target dataset is input into a pre-trained two-phase medium wave characteristic learning network, which outputs multiple wave equation coefficients of the target two-phase porous medium elastic wave propagation model; the pre-trained two-phase medium wave characteristic learning network is trained by the neural network training method described in any one of claims 1-7; Based on the multiple wave equation coefficients, an elastic wave propagation model for the target two-phase porous medium is constructed.

9. The method according to claim 8, characterized in that, The method further includes: Plane wave analysis is performed based on the multiple wave equation coefficients to determine the dispersion attenuation characteristics of the elastic wave propagation model of the target two-phase porous medium. Based on the aforementioned dispersion attenuation characteristics, the propagation information of longitudinal and transverse waves is determined.

10. A neural network training device, characterized in that, The device includes: The sample acquisition module is used to acquire a sample dataset, which includes sample reservoir physical property parameters associated with the elastic wave propagation model of the sample two-phase porous medium. The network prediction module is used to input the sample dataset into the two-phase medium wave characteristic learning network and output multiple predicted wave equation coefficients of the sample two-phase porous medium elastic wave propagation model. The feature analysis module is used to perform plane wave analysis based on the coefficients of the multiple predicted wave equations to determine the predicted dispersion attenuation characteristics of the elastic wave propagation model of the sample two-phase porous medium. The parameter adjustment module is used to adjust the parameters of the two-phase medium wave characteristic learning network according to the error loss between the predicted dispersion attenuation characteristics and the actual dispersion attenuation characteristics of the sample two-phase porous medium elastic wave propagation model, until the cutoff condition is met.

11. A model building apparatus, characterized in that, The device includes: The data acquisition module is used to acquire the target dataset, which includes target reservoir physical property parameters associated with the elastic wave propagation model of the target two-phase porous medium. The network processing module is used to input the target dataset into a trained two-phase medium wave characteristic learning network and output multiple wave equation coefficients of the target two-phase porous medium elastic wave propagation model; the trained two-phase medium wave characteristic learning network is trained by the neural network training method described in any one of claims 1-7; The model building module is used to construct the elastic wave propagation model of the target two-phase porous medium based on the multiple wave equation coefficients.

12. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the neural network training method according to any one of claims 1 to 7 or the model building method according to any one of claims 8 to 9.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps of the neural network training method according to any one of claims 1 to 7 or the model building method according to any one of claims 8 to 9.

Images