Permeability prediction method and system based on multi-source attribute coupling

Abstract

The invention discloses a permeability prediction method and system based on multi-source attribute coupling, and the method comprises the steps: obtaining multi-source attribute information and permeability data, the multi-source attribute information comprising fracture density, porosity and water inflow; constructing a multi-source attribute-permeability coupling prediction model, and training the multi-source attribute-permeability coupling prediction model based on the multi-source attribute information and the permeability data; inputting the multi-source attribute information into a trained multi-source attribute-permeability coupling prediction model to obtain predicted permeability; according to the method, a coupling relationship between permeability and multi-attribute information such as fracture density, porosity and water inflow is taken as a core of a standardized model, a mathematical formula is adopted to describe the coupling relationship among attributes, and experimental and numerical simulation data are combined so as to establish physical constraints in a deep learning model.

Description

Technical Field

[0001] The present invention relates to the fields of underground engineering, geotechnical engineering and geological exploration, and in particular to a permeability prediction method and system based on multi-source attribute coupling. Background Art

[0002] Permeability is a key parameter in geotechnical engineering and groundwater resource development. It reflects the ability of geotechnical media to flow fluids. The size of permeability directly affects the flow of groundwater, the grouting effect of the formation, the diffusion of pollutants, and the recovery of oil and gas in underground reservoirs. Therefore, accurately grasping the permeability of geological structures is of great significance to engineering design and implementation. In geotechnical engineering, permeability is widely used in the construction of hydraulic structures, underground engineering design, and foundation pit support. For example, in the construction of infrastructure such as tunnels and basements, permeability helps to evaluate the water level changes and water flow conditions of the formation to ensure the waterproofness and safety of the structure. In grouting engineering, permeability determines the effect of slurry diffusion and affects the reinforcement and stability of underground engineering. By understanding the permeability of the formation, engineers can optimize the grouting design to ensure that the slurry can effectively penetrate and fill the pores, thereby enhancing the bearing capacity and durability of the structure. Therefore, permeability is not only an important physical parameter in geotechnical engineering, but also a guiding factor in various underground engineering and environmental engineering projects.

[0003] In underground engineering and geological research, attribute parameters (fracture density, porosity and water inflow) and permeability are important indicators for describing the structure and physical properties of geological bodies. Attribute and permeability data of some areas can be obtained through drilling tests and laboratory tests, but due to the complexity of the strata and the limited data, these attributes usually have spatial differences, and the permeability information lacks full coverage, resulting in large errors in the modeling of underground structures; in addition, the existing permeability prediction models have problems such as low prediction accuracy and large errors, which need to be further improved and optimized. By accurately obtaining and optimizing the permeability model, engineers can better evaluate the flow characteristics of underground media, provide a scientific basis for the design and implementation of the project, and thus improve the safety, economy and sustainability of the project. Summary of the invention

[0004] In view of the problems existing in the prior art, the present invention provides a permeability prediction method and system based on multi-source attribute coupling, which realizes comprehensive and dynamic coupling of multi-attributes and permeability in space based on the joint iterative reconstruction of multi-source information, so as to improve the prediction accuracy and adaptability of the model.

[0005] The technical solution of the present invention is as follows:

[0006] In a first aspect of the present invention, a permeability prediction method based on multi-source attribute coupling is provided, comprising:

[0007] Acquire multi-source attribute information to be predicted and pre-process the multi-source attribute information, wherein the multi-source attribute information includes fracture density, porosity and water inflow;

[0008] The processed multi-source attribute information is input into the trained multi-source attribute-permeability coupling prediction model to perform prediction and obtain the predicted permeability;

[0009] Among them, the training process of the multi-source attribute-permeability coupling prediction model is: obtaining historical multi-source attribute information and permeability data, and processing the multi-source attribute information using a numerical interpolation method; then, based on the historical multi-source attribute information and permeability data, a deep learning prediction model combining physical constraints and multi-task learning is trained to obtain a complex relationship model of multi-attribute-permeability; finally, the complex relationship model of multi-attribute-permeability is reconstructed through multiple rounds of joint iterative reconstruction to obtain a multi-source attribute-permeability coupling prediction model.

[0010] In some embodiments of the present invention, the multi-round joint iterative reconstruction process specifically includes: first, using known experimental and numerical simulation data to pre-train the complex relationship model of multiple attributes-permeability, so that the model can initially learn the coupling relationship between multiple attributes and permeability; then each time the newly collected drilling exposure information is added to the training data, and reconstruction is performed in an iterative manner. The model uses the new data as the input for the next round of training, and continuously updates the model parameters according to the new physical data constraints.

[0011] In some embodiments of the present invention, the multi-source attribute-permeability coupling prediction model includes an input layer, a feature extraction layer, a coupling relationship layer and a fusion layer, wherein the coupling relationship layer introduces a multi-task learning module, passes the input multi-attribute information into three parallel branch models, and outputs fracture permeability, pore permeability and water permeability respectively.

[0012] In some embodiments of the present invention, the three parallel branch models include: a coupling model of fracture density and permeability, a coupling model of porosity and permeability, and a coupling model of water inflow and permeability;

[0013] Among them, the coupling model of fracture density and permeability is:

[0014]

[0015] In the formula, k f represents the permeability under fracture control; D f is the crack density; a and b are constants determined by experiments;

[0016] The coupling model of porosity and permeability is:

[0017]

[0018] In the formula, k p represents the permeability under pore control; φ is the porosity; S is the specific surface area; C is a constant;

[0019] The coupling model of water inflow and permeability is:

[0020]

[0021] In the formula, Q is the water inflow; k w is the permeability under water inflow control; A is the flow cross-sectional area; Δh is the head difference; L is the flow path length.

[0022] In some embodiments of the present invention, the fusion layer performs weighted summation of the three permeabilities, namely, the fracture permeability, the pore permeability and the water inflow permeability, obtained by the coupling relationship layer, and outputs a comprehensive permeability as the predicted permeability.

[0023] In some embodiments of the present invention, a physical constraint layer is further included, wherein the physical constraint layer adds a physical constraint term to the loss function, and the loss function is defined as follows:

[0024]

[0025] in: is the mean square error between the model prediction and the true permeability; is the regularization loss term;

[0026] Physical consistency loss based on multi-attribute coupling formula

[0027]

[0028] where k f , k p and k w It is calculated by the branch output of the model; k is the comprehensive permeability; λ1 and λ2 are weight hyperparameters used to balance the impact of different loss terms; α, β, and γ are the weights of the factors.

[0029] In some embodiments of the present invention, the training and optimization process of the multi-attribute-permeability complex relationship model is as follows:

[0030] Initialize model parameters and weights: preset model hyperparameters, such as weights λ1 and λ2 in the loss function, and initialize network parameters;

[0031] Batch training: Update network parameters based on the back-propagation algorithm, and calculate the loss value and gradient through forward propagation and back-propagation of each small batch of data;

[0032] Physical constraint adjustment: In each iteration, the values ​​of α, β, and γ are adjusted so that the comprehensive permeability k output by the model satisfies the physical constraint relationship as much as possible, and the physical consistency is gradually optimized;

[0033] Evaluation and tuning: Evaluate the generalization ability and physical consistency of the model through cross-validation and loss curve analysis, and adjust the hyperparameters of the number of model layers and nodes when necessary.

[0034] In some implementations of the present invention, the numerical interpolation method uses a radial basis function interpolation method to expand the spatial coverage of multi-source attribute information.

[0035] In some embodiments of the present invention, the sources of the permeability data include drilling test data, laboratory test data, and numerical simulation data; the training of the deep learning model using the multi-source attribute information and permeability data includes coupling data from different sources, and using adjacent attributes as a guide to obtain a complex relationship model of multiple attributes-permeability through repeated training.

[0036] In a second aspect of the present invention, a permeability prediction system based on multi-source attribute coupling is provided, comprising:

[0037] The data processing module is configured to: obtain multi-source attribute information to be predicted and pre-process the multi-source attribute information, wherein the multi-source attribute information includes fracture density, porosity and water inflow;

[0038] The prediction module is configured to: input the processed multi-source attribute information into the trained multi-source attribute-permeability coupling prediction model for prediction to obtain the predicted permeability;

[0039] Among them, the training process of the multi-source attribute-permeability coupling prediction model is: first, the multi-source attribute information is processed by a numerical interpolation method; then, based on the multi-source attribute information and permeability data, a deep learning prediction model combining physical constraints and multi-task learning is trained to obtain a complex relationship model of multi-attribute-permeability; finally, the complex relationship model of multi-attribute-permeability is reconstructed through multiple rounds of joint iterative reconstruction to obtain a multi-source attribute-permeability coupling prediction model.

[0040] One or more technical solutions of the present invention have the following beneficial effects:

[0041] (1) The permeability prediction model adopted by the permeability prediction method provided by the present invention, in the coupling process of underground medium attributes, takes the coupling relationship between multi-attribute information such as fracture density, porosity, and water inflow and permeability as the core of the standardized model, uses mathematical formulas to describe the coupling relationship between various attributes, and combines experimental and numerical simulation data to establish its physical constraints in the deep learning model, thereby improving the accuracy of the permeability prediction results. In addition, a physical constraint layer and a physical consistency loss function based on a multi-attribute coupling formula are used to ensure that the model not only considers the prediction error during the optimization process, but also meets the requirements of physical laws. Through physical constraints, the output of the model is more in line with the permeability characteristics under actual geological conditions, avoiding the model from deviating from the actual physical process, thereby enhancing the credibility and reliability of the prediction results.

[0042] (2) The present invention establishes a more accurate and dynamically adaptive permeability prediction model by deeply coupling multi-source attribute information (such as fracture density, porosity and water inflow) with permeability data and combining it with a training strategy of multiple rounds of joint iterative reconstruction. Compared with the traditional model of a single data source, this method can comprehensively consider the complex relationship between different attributes, thereby significantly improving the accuracy and stability of permeability prediction and adapting to different geological conditions and engineering requirements.

[0043] (3) The permeability prediction model used in the permeability prediction method provided by the present invention can be automatically updated and optimized after each acquisition of new data (such as drilling exposure information) through multiple rounds of joint iterative reconstruction, thereby continuously improving the accuracy of the prediction. This dynamic iteration mechanism enables the model to reflect the changes in the structure of the geological body in real time over a long period of time, especially in the process of dynamic monitoring and engineering implementation, and can adjust the prediction results according to real-time data, thereby enhancing the flexibility and real-time performance of the model and adapting to the ever-changing complex conditions in the engineering environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 It is a flow chart of the permeability prediction method based on multi-source attribute coupling of the present invention;

[0045] Figure 2 This is a structural diagram of the multi-source attribute-permeability coupling prediction model of the present invention. DETAILED DESCRIPTION

[0046] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0047] Example 1

[0048] In a typical embodiment of the present invention, a permeability prediction method based on multi-source attribute coupling is proposed, such as Figure 1 As shown, including:

[0049] Input the multi-source attribute information to be predicted into the trained multi-source attribute-permeability coupling prediction model to obtain the predicted permeability;

[0050] Step 1: obtaining multi-source attribute information to be predicted and preprocessing the multi-source attribute information, wherein the multi-source attribute information includes fracture density, porosity and water inflow;

[0051] Among them, a numerical interpolation method is used to process multi-source attribute information; the numerical interpolation method uses a radial basis function interpolation method to expand the spatial coverage of the multi-source attribute information, and uses a numerical model for attribute modeling and interpolation analysis, which can fill the missing attribute data caused by uneven distribution of drilling holes. The interpolation method can use radial basis function interpolation or other suitable numerical interpolation methods to ensure the smoothness and consistency of the attribute data.

[0052] Specifically, the processing process includes:

[0053] First, the input multi-source attribute data (such as fracture density, porosity, water inflow, etc.) are gridded according to the geometric scope and resolution requirements of the study area. The study area is decomposed into uniform or adaptive three-dimensional grid cells through background grid generation technology. The attribute value of each grid cell can be obtained from existing data points through data interpolation technology (such as cubic spline interpolation and radial basis function interpolation) to ensure the continuity and integrity of the attribute data in space.

[0054] Attribute interpolation and mapping:

[0055] For the attribute data of the unsampled area, the interpolation algorithm is used to calculate the attribute values ​​of the unknown points in the grid. For example, for the fracture density, radial basis function interpolation is used to calculate the density distribution of the surrounding grid points from the known fracture density points; for the porosity, the weighted average method based on the volume fraction is used to complete the interpolation; for the water inflow, the water inflow attributes of the unsampled points are predicted through time series analysis. This method can effectively solve the problem of data sparsity while maintaining the spatial consistency of physical properties.

[0056] Random point sampling:

[0057] After completing the grid division and attribute interpolation, a certain number of representative sampling points are randomly selected from the grid cells as the input data of the deep learning model. These points can be selected according to the following principles:

[0058] Uniformity: Through spatially uniform sampling, it is ensured that the selected points can fully cover the distribution of different attributes in the study area.

[0059] Representativeness: Based on the gradient changes of attribute data (such as fracture density gradient or porosity gradient), the density of sampling points is increased in areas with large attribute changes to improve the modeling accuracy of key areas.

[0060] Randomness: On the basis of uniformity and representativeness, random perturbations are added to ensure the diversity of input data and prevent model overfitting.

[0061] Feature preprocessing:

[0062] Normalize or standardize the attribute values ​​of the selected random sampling points to unify the dimensions and value ranges of different attributes. At the same time, design special encoding methods for different data types (such as scalar attributes and image attributes) to adapt them to the input format of the deep learning model. For example, convert the water inflow attribute into a time series input, and convert the crack density distribution into a two-dimensional image feature.

[0063] Batch generation:

[0064] Finally, the data of the sampling points are organized into batches, each batch contains a certain number of sample points, and the order of the data within the batch is randomly adjusted to enhance the robustness and generalization ability of model training.

[0065] Step 2: Input the processed multi-source attribute information into the trained multi-source attribute-permeability coupling prediction model to perform prediction and obtain the predicted permeability;

[0066] Among them, the training process of the multi-source attribute-permeability coupling prediction model is: obtaining historical multi-source attribute information and permeability data, and processing the multi-source attribute information using a numerical interpolation method; then, based on the historical multi-source attribute information and permeability data, a deep learning prediction model combining physical constraints and multi-task learning is trained to obtain a complex relationship model of multi-attribute-permeability; finally, the complex relationship model of multi-attribute-permeability is reconstructed through multiple rounds of joint iterative reconstruction to obtain a multi-source attribute-permeability coupling prediction model.

[0067] Specifically, a deep neural network model combining multi-task learning and physical constraints is constructed as a multi-source attribute-permeability coupling prediction model, such as Figure 2 As shown, it includes an input module, a feature extraction module, a coupling relationship module, a fusion module and a physical constraint module.

[0068] Input module: Receive multi-source attribute information, including fracture density, porosity, water inflow and other parameters, and input them according to attribute type. Input multi-source attribute information, including fracture density, porosity, water inflow and other parameters, and input them according to attribute type. Each input data can contain multiple spatiotemporal observation points, and has dynamic update characteristics, supporting real-time data flow.

[0069] Feature extraction module: Use multiple convolutional layers or multi-layer perceptrons (MLP) to extract complex nonlinear relationships between attributes.

[0070] Coupling relationship module: introduces a multi-task learning module to pass the input multi-attribute data into three parallel branches and output the fracture permeability k f , pore permeability k p , water permeability k w ; These branches share some network layers but have independent weights in feature extraction and fusion to capture the permeability characteristics of different attributes.

[0071] The three parallel branch models include: a coupling model of fracture density and permeability, a coupling model of porosity and permeability, and a coupling model of water inflow and permeability;

[0072] Among them, the coupling model of fracture density and permeability is:

[0073]

[0074] In the formula, k f represents the permeability under fracture control; D f is the fracture density; a and b are constants determined by experiments; this formula shows that with the increase of fracture density, the permeability increases nonlinearly. Based on the experimental and numerical simulation data, the values ​​of constants a and b can be determined to make the model more in line with the actual situation.

[0075] The coupling model of porosity and permeability is:

[0076]

[0077] In the formula, k p represents the permeability under pore control; φ is the porosity; S is the specific surface area; C is a constant; this model reflects the nonlinear relationship between porosity and permeability, and specific values ​​can be obtained through experiments to adapt to different pore characteristics.

[0078] The coupling model of water inflow and permeability is:

[0079]

[0080] In the formula, Q is the water inflow; k w is the permeability under water inflow control; A is the flow cross-sectional area; Δh is the head difference; L is the flow path length; the relationship between water inflow and permeability can be described according to Darcy's law, and the permeability k can be calculated by measuring the water inflow in the experiment. w , thus constructing the coupling standard of permeability and water inflow.

[0081] Fusion module: According to the multi-attribute-permeability coupling formula, the three permeabilities are weighted summed and the comprehensive permeability k is output;

[0082] Time series modeling module: Based on the time series convolutional network, it captures the time series change rules and describes the dynamic behavior of the slurry diffusion process. Combined with the attention mechanism, it gives higher weights to key moments or regions and optimizes the extraction effect of spatiotemporal features.

[0083] The main functions of the spatiotemporal modeling module include:

[0084] (1) Capturing time characteristics: Tracking the diffusion trend of slurry at different time points and predicting the permeability changes at future moments.

[0085] (2) Spatial feature modeling: Combine geological data with drilling layout to simulate the distribution characteristics of slurry diffusion in space; unify the temporal and spatial characteristics through the time-space fusion layer to capture the "time-space" coupling characteristics of the slurry diffusion process.

[0086] (3) Dynamic weight adjustment: Combined with the attention mechanism, higher weights are given to key areas and key moments in the spatiotemporal dimension. For example, the weights of grid cells near the grouting point and the initial diffusion time points are strengthened to ensure that the model accurately depicts the initial diffusion behavior and the changes in spatial permeability gradients.

[0087] (4) Physical constraint embedding: Considering the physical constraints of the slurry, the constraints are directly embedded into the space-time module to ensure that the prediction results conform to the actual engineering physics laws.

[0088] Physical consistency embedding module: Add physical constraints to the loss function to ensure that the model meets the constraints of physical formulas as much as possible during training.

[0089] To achieve the optimization of the multi-source attribute-permeability coupling prediction model based on joint iterative reconstruction, the deep learning model can use physical constraints as a supervision mechanism to embed the relationship between multi-source attributes (fractures, pores, water inflow) and permeability into the model to ensure physical consistency during the training process.

[0090] Adding a regularization term based on physical constraints to the loss function allows the model to not only minimize the prediction error but also follow the physical constraint formula. The loss function is defined as follows:

[0091]

[0092] in: is the mean square error (MSE) between the model prediction and the true permeability; Physical consistency loss based on multi-attribute coupling formulation; It is a regularization loss term, which is used to guide the model to follow certain additional structures or constraints during the training process to ensure the stability and simplicity of the model or to follow certain prior assumptions.

[0093]

[0094] Among them, k f , k p and k w It is calculated by the branch output of the model; k is the comprehensive permeability; λ1 and λ2 are weight hyperparameters used to balance the impact of different loss terms; α, β, and γ are the weights of the factors.

[0095] The weight factors (α, β, γ and λ1, λ2) are dynamically adjusted during the training process to ensure a balance between physical consistency and prediction accuracy.

[0096] The above model structure has made the following improvements on the existing neural network structure:

[0097] Physical constraint embedding: To ensure physical consistency during the calculation process, the model embeds physical models and boundary conditions related to slurry diffusion during the training process. Specifically, the loss function of the neural network model not only considers the prediction error, but also combines the error of the physical model, making the output results more consistent with the actual physical laws.

[0098] Multi-source data fusion: By introducing multi-source data (such as resistivity, radar signals and drilling data, etc.), the model can realize joint learning of different data types. This process requires a special fusion module to achieve the synergy of different data.

[0099] Spatiotemporal feature learning: Focusing on the diffusion of slurry in complex geological environments, the model is specially designed with a structure that can handle spatiotemporal features to ensure accurate capture of slurry diffusion at different time points.

[0100] Dynamic training and updating mechanism: In order to cope with the dynamic changes of field monitoring data, the model is designed with a mechanism that can be continuously updated and adjusted to ensure effective predictions at different working stages (such as before grouting, after grouting, re-drilling, etc.).

[0101] Specifically, the model iteratively updates and trains the data according to the following process to improve its adaptability and accuracy to different geological conditions.

[0102] 1. Initial data training: First, the model is pre-trained using known experimental and numerical simulation data so that the model can initially learn the coupling relationship between multiple attributes and permeability.

[0103] Specifically, they include:

[0104] (1) A numerical interpolation method is used to process multi-source attribute information; the numerical interpolation method uses a radial basis function interpolation method to expand the spatial coverage of the multi-source attribute information, uses a numerical model to perform attribute modeling and interpolation analysis, and can fill in the missing attribute data caused by uneven borehole distribution. The interpolation method can use a radial basis function interpolation method or other appropriate numerical interpolation methods to ensure the smoothness and consistency of the attribute data.

[0105] (2) Based on multi-source attribute and permeability data, the deep learning model is trained to obtain a complex relationship model between multi-attribute and permeability; the multi-source attribute information and permeability data are used to train the deep learning model, including coupling data from different sources, and using adjacent attributes as a guide to obtain a complex relationship model between multi-attribute and permeability through repeated training. The deep learning model can use a convolutional neural network or other network structure suitable for geological attribute representation to ensure that it can capture the spatial nonlinear relationship between geological attributes.

[0106] Among them, coupling data from different sources refers to integrating and associating multi-source attribute data (such as fracture density, porosity, and water inflow) from different sources with permeability data so that they can be trained through deep learning models. The core of coupling is to merge these different types of data into a unified input format, so that the deep learning model can simultaneously consider the mutual influence between these different attributes and their relationship with permeability during the learning process.

[0107] Coupling data from different sources includes:

[0108] Data splicing: Attribute data from different sources (such as drilling tests, laboratory measurements, numerical simulations, etc.) are spliced ​​into a multidimensional vector and used as the input of the model. These attribute information are combined into a unified data structure through splicing for deep learning model processing.

[0109] Weighted fusion: Assign different weights to attribute data from different sources, and perform weighted averaging based on the reliability or importance of different data to form a comprehensive input data.

[0110] Feature interaction: The relationships and interaction features between different attributes are automatically learned through neural network layers or convolution operations in deep learning. For example, convolutional neural networks (CNNs) can capture the spatial relationships of geological attributes through convolution operations.

[0111] "Adjacent attributes as guidance" in this process means that during the training process, the model will pay attention to adjacent attributes (such as the relationship between water content and permeability) and optimize the model through repeated training to better capture the spatial nonlinear relationship between attributes.

[0112] 2. Joint iterative reconstruction: Each newly acquired drill hole exposure information is added to the training data and reconstructed in an iterative manner. The model uses the new data as the input for the next round of training and continuously updates the model parameters according to the new physical data constraints to optimize the prediction accuracy of the coupled model.

[0113] Specifically, after building the coupling relationship of the deep learning model through test data and numerical simulation data, the model is updated step by step. In each round of iteration, the latest drilling exposure information (i.e., field data) is used as new data input, and the multi-attribute-permeability coupling relationship is continuously optimized based on the deep learning model, gradually refining the accuracy and applicability of the model.

[0114] Based on multiple rounds of joint iterative reconstruction, a multi-source attribute-permeability coupling prediction model that meets engineering needs is formed and refined into a standardized form of the model so that it can be quickly adapted to different underground engineering applications and realize the rapid integration and modeling of multiple attribute and permeability information.

[0115] 3. Multi-source data fusion: The model gradually accumulates more collected data (such as laboratory data, numerical simulation data and drilling exposure data), and performs multi-source data normalization processing to ensure the continuity and consistency between new data and old data, and avoid model deviations due to differences in data from different sources.

[0116] Adding physical constraints to the above model for optimization training includes:

[0117] 1. Initialize model parameters and weights: preset model hyperparameters, such as weights λ1 and λ2 in the loss function, and initialize network parameters.

[0118] 2. Batch training: Update network parameters based on the back-propagation algorithm, and calculate the loss value and gradient through forward propagation and back-propagation of each small batch of data.

[0119] 3. Physical constraint adjustment: In each iteration, the values ​​of α, β, and γ are adjusted so that the comprehensive permeability k output by the model satisfies the physical constraint relationship as much as possible, and the physical consistency is gradually optimized.

[0120] 4. Evaluation and tuning: Evaluate the generalization ability and physical consistency of the model through cross-validation and loss curve analysis, and adjust hyperparameters such as the number of model layers and nodes when necessary.

[0121] After training, the model can automatically update the comprehensive permeability prediction based on newly collected multi-source data, and be applied to real-time permeability monitoring and dynamic regulation of underground projects. The comprehensive permeability k output by the model can be directly used for engineering prediction and provide guidance for drilling layout, seepage control, etc.

[0122] Example 2

[0123] In a typical embodiment of the present invention, a permeability prediction method based on multi-source attribute coupling is provided, comprising:

[0124] The data processing module is configured to: obtain multi-source attribute information to be predicted and pre-process the multi-source attribute information, wherein the multi-source attribute information includes fracture density, porosity and water inflow;

[0125] The prediction module is configured to: input the processed multi-source attribute information into the trained multi-source attribute-permeability coupling prediction model for prediction to obtain the predicted permeability;

[0126] Among them, the training process of the multi-source attribute-permeability coupling prediction model is: obtaining historical multi-source attribute information and permeability data, and processing the multi-source attribute information using a numerical interpolation method; then, based on the historical multi-source attribute information and permeability data, a deep learning prediction model combining physical constraints and multi-task learning is trained to obtain a complex relationship model of multi-attribute-permeability; finally, the complex relationship model of multi-attribute-permeability is reconstructed through multiple rounds of joint iterative reconstruction to obtain a multi-source attribute-permeability coupling prediction model.

[0127] Although the above describes the specific implementation mode of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without creative work are still within the scope of protection of the present invention.

Claims

1. A permeability prediction method based on multi-source attribute coupling, characterized in that: include: Acquire multi-source attribute information to be predicted and pre-process the multi-source attribute information, wherein the multi-source attribute information includes fracture density, porosity and water inflow; The processed multi-source attribute information is input into the trained multi-source attribute-permeability coupling prediction model to perform prediction and obtain the predicted permeability; Among them, the training process of the multi-source attribute-permeability coupling prediction model is: obtaining historical multi-source attribute information and permeability data, and processing the multi-source attribute information using a numerical interpolation method; then, based on the historical multi-source attribute information and permeability data, a deep learning prediction model combining physical constraints and multi-task learning is trained to obtain a complex relationship model of multi-attribute-permeability; finally, the complex relationship model of multi-attribute-permeability is reconstructed through multiple rounds of joint iterative reconstruction to obtain a multi-source attribute-permeability coupling prediction model.

2. The permeability prediction method based on multi-source attribute coupling according to claim 1, characterized in that: The multi-round joint iterative reconstruction process specifically includes: firstly, using known test and numerical simulation data to pre-train the complex relationship model of multi-attribute-permeability, so that the model can initially learn the coupling relationship between multi-attributes and permeability; then, each newly collected drilling exposure information is added to the training data, and reconstruction is performed in an iterative manner. The model uses the new data as the input for the next round of training, and continuously updates the model parameters according to the new physical data constraints.

3. The permeability prediction method based on multi-source attribute coupling according to claim 1, characterized in that: The multi-source attribute-permeability coupling prediction model includes an input module, a feature extraction module, a coupling relationship module, a fusion module and a physical constraint module, wherein the coupling relationship module introduces a multi-task learning module, transfers the input multi-attribute information into three parallel branch models, and outputs fracture permeability, pore permeability and water permeability respectively.

4. The permeability prediction method based on multi-source attribute coupling according to claim 3 is characterized in that: The three parallel branch models include: a coupling model of fracture density and permeability, a coupling model of porosity and permeability, and a coupling model of water inflow and permeability; Among them, the coupling model of fracture density and permeability is: In the formula, k f represents the permeability under fracture control; D f is the crack density; a and b are constants determined by experiments; The coupling model of porosity and permeability is: In the formula, k p represents the permeability under pore control; φ is the porosity; S is the specific surface area; C is a constant; The coupling model of water inflow and permeability is: In the formula, Q is the water inflow; k w is the permeability under water inflow control; A is the flow cross-sectional area; Δh is the head difference; l is the flow path length.

5. The permeability prediction method based on multi-source attribute coupling according to claim 3, characterized in that: The fusion layer performs weighted summation of the three permeabilities according to the fracture permeability, pore permeability and water inflow permeability obtained in the coupling relationship layer, and outputs the comprehensive permeability as the predicted permeability.

6. The permeability prediction method based on multi-source attribute coupling according to claim 3, characterized in that: It also includes a physical constraint layer, which adds physical constraint terms to the loss function. The loss function is defined as follows: in: is the mean square error between the model prediction and the true permeability; is the regularization loss term; Physical consistency loss based on multi-attribute coupling formula Among them, k f , k p and k w It is calculated by the branch output of the model; k is the comprehensive permeability; λ1 and λ2 are weight hyperparameters used to balance the impact of different loss terms; α, β, and γ are the weights of the factors.

7. The permeability prediction method based on multi-source attribute coupling according to claim 6, characterized in that: The training and optimization process of the complex relationship model of multi-attribute-permeability is as follows: Initialize model parameters and weights: preset model hyperparameters, such as weights λ1 and λ2 in the loss function, and initialize network parameters; Batch training: Update network parameters based on the back-propagation algorithm, and calculate the loss value and gradient through forward propagation and back-propagation of each small batch of data; Physical constraint adjustment: In each iteration, the values ​​of α, β, and γ are adjusted so that the comprehensive permeability k output by the model satisfies the physical constraint relationship as much as possible, and the physical consistency is gradually optimized; Evaluation and tuning: Evaluate the generalization ability and physical consistency of the model through cross-validation and loss curve analysis, and adjust the hyperparameters of the number of model layers and nodes when necessary.

8. The permeability prediction method based on multi-source attribute coupling according to claim 1, characterized in that: The numerical interpolation method uses a radial basis function interpolation method to expand the spatial coverage of multi-source attribute information.

9. The permeability prediction method based on multi-source attribute coupling according to claim 1, characterized in that: The sources of the permeability data include drilling test data, laboratory test data and numerical simulation data; the training of the deep learning model using the multi-source attribute information and permeability data includes coupling data from different sources and using adjacent attributes as a guide to obtain a complex multi-attribute-permeability relationship model through repeated training.

10. A permeability prediction method based on multi-source attribute coupling, characterized in that: include: The data processing module is configured to: obtain multi-source attribute information to be predicted and pre-process the multi-source attribute information, wherein the multi-source attribute information includes fracture density, porosity and water inflow; The prediction module is configured to: input the processed multi-source attribute information into the trained multi-source attribute-permeability coupling prediction model for prediction to obtain the predicted permeability; Among them, the training process of the multi-source attribute-permeability coupling prediction model is: obtaining historical multi-source attribute information and permeability data, and processing the multi-source attribute information using a numerical interpolation method; then, based on the historical multi-source attribute information and permeability data, a deep learning prediction model combining physical constraints and multi-task learning is trained to obtain a complex relationship model of multi-attribute-permeability; finally, the complex relationship model of multi-attribute-permeability is reconstructed through multiple rounds of joint iterative reconstruction to obtain a multi-source attribute-permeability coupling prediction model.

Images