Shale gas refracturing potential prediction method and system based on multi-modal data fusion

Abstract

The present application relates to the technical field of shale gas storage development and stimulation, in particular to a shale gas refracturing potential prediction method and system based on multi-modal data fusion. A data set is established according to the obtained shale gas well data, the data set includes a multi-dimensional sequence data set and a single-value data set, the multi-dimensional sequence data set includes logging curve data and fracturing operation curve data, the single-value data set includes geological data, reservoir physical property data, initial fracturing parameter data, production dynamic data and rock mechanics data, and the refracturing potential of the well section is marked through the production dynamic data; data cleaning and standardization processing are performed, and the data set is divided into a training set, a test set and a verification set; a shale gas refracturing potential prediction model is constructed, which meets the preset requirements and takes the multi-dimensional sequence data set and the single-value data set as input and the refracturing effect type as output. The present application can realize efficient prediction of the overall refracturing potential of the shale gas well.

Description

Technical Field

[0001] The present invention relates to the technical field of shale gas storage, development and production increase, and in particular to a shale gas refracturing potential prediction method and system based on multimodal data fusion. Background Art

[0002] The rapid and high-quality development of the shale gas industry is of great significance to the country's energy structure adjustment and energy conservation and emission reduction. Improving the final recovery rate of shale gas is a key research direction of China's oil and gas development.

[0003] As shale gas well development enters the middle and late stages, the conductivity of the first artificial fractures and the permeability of the surrounding formations gradually decrease due to factors such as scaling, particle migration, and fracture closure. This significantly reduces shale gas production capacity and makes oil and gas difficult to recover in some areas. Refractures create new fractures that extend in a different direction from the previous artificial fractures, redirecting the fractures and thus connecting to the untapped gas reservoirs of the old fractures on a larger scale. This can relieve reservoir damage and improve ultimate reservoir recovery, making it a necessary option for increasing the production of existing shale gas wells. Furthermore, shale gas wells are characterized by high initial production and rapid decline, while drilling new horizontal wells is expensive. Therefore, refracture of the reservoir is crucial for increasing and stabilizing shale gas production.

[0004] Key technologies for enhancing oil recovery, such as refracturing, carry significant risks and uncertainties, resulting in low success rates, poor production-increasing effects, and a short effective lifespan. These issues are primarily due to the lack of a systematic approach to determining remaining gas well production and reservoir susceptibility, as well as the difficulty in accurately determining the location and extent of refracturing "sweet spots." Therefore, predicting the refracturing potential of the entire shale gas wellbore and optimizing and accurately locating the refracturing "sweet spots" are key challenges currently facing refracturing.

[0005] Currently, the prediction of refracturing potential and the selection of refracturing sections primarily rely on manual evaluation using microseismic monitoring, temperature sensing, and proppant tracking technologies, or complex and extensive data analysis. This approach is time-consuming, costly, and lacks portability. Artificial intelligence prediction methods in the oil and gas sector primarily focus on resource production forecasts, using only single-value data such as geological and construction parameters without considering variations in various wellbore sections. Consequently, there is a lack of intelligent refracturing potential prediction methods that can accurately select and locate refracturing "sweet spots." Summary of the Invention

[0006] The purpose of the present invention is to provide a shale gas refracturing potential prediction method and system based on multimodal data fusion, so as to solve the problems of the lack of a systematic method for determining the remaining resource production of gas wells and the reformability of reservoirs in the existing refracturing process, and the difficulty in accurately grasping the location and range of the refracturing "sweet spot" section, so as to realize intelligent and digital evaluation of refracturing potential.

[0007] In order to achieve the above object, the technical solution adopted by the present invention is as follows:

[0008] In a first aspect, the present invention provides a method for predicting shale gas refracturing potential based on multimodal data fusion, which comprises:

[0009] A data set is established based on the acquired shale gas well data, the data set comprising a multidimensional sequence data set and a single-value data set, the multidimensional sequence data set comprising well logging curve data and fracturing operation curve data, the single-value data set comprising geological data, reservoir physical property data, initial fracturing parameter data, production performance data, and rock mechanics data; and the re-fracturing potential of the well section is marked using the production performance data;

[0010] Perform data cleaning and standardization, and then divide the data set into training set, test set and validation set;

[0011] Constructing a shale gas refracturing potential prediction model that takes a multidimensional sequence dataset and a single-value dataset as input and outputs refracturing potential, wherein the shale gas refracturing potential prediction model includes a multilayer perceptron model for processing the single-value dataset and a gated recurrent unit model based on an attention mechanism for processing the multidimensional sequence dataset;

[0012] A loss function is set, and the shale gas refracturing potential prediction model is iteratively trained and optimized using the training set. The shale gas refracturing potential prediction model is tested and verified using the test set and validation set, respectively, to obtain a shale gas refracturing potential prediction model that meets the preset requirements.

[0013] The refracturing potential of a target shale gas well is predicted using the shale gas refracturing potential prediction model that meets preset requirements.

[0014] Furthermore, the logging curve data includes lithology curve, resistivity curve, porosity curve, organic matter content curve, permeability, saturation, pore fluid, and gas content;

[0015] The fracturing operation curve data includes a pressure curve, a displacement curve and a sand ratio curve;

[0016] and / or, the geological data include mineral composition, rock structure, brittleness, fault distribution and fold morphology;

[0017] And / or, the reservoir physical property data includes gas saturation;

[0018] And / or, the primary fracturing parameter data includes the type and amount of fracturing fluid, the type and amount of proppant;

[0019] And / or, the production performance data includes shale gas well production data and pressure gradient data;

[0020] And / or, the rock mechanics data includes elastic modulus, Poisson's ratio and ground stress data.

[0021] Furthermore, the parameter settings of the shale gas refracturing potential prediction model include: defining the dataset as a tensor with a shape of (N, Q, M), where N is the number of samples in the dataset, Q is the maximum number of time steps among all variables, and M is the number of variables for each time step. The number of hidden layers of the multilayer perceptron model is 2, the number of neurons of the gated recurrent unit model is 64, and the ReLU activation function is used.

[0022] Furthermore, a loss function is set, and the training set is used to iteratively train and optimize the shale gas refracturing potential prediction model. Specifically, the loss function is set to categorical_crossentropy; the K-fold cross-validation method is used as the hyperparameter optimization algorithm, and the Adam optimizer is selected; the learning rate of the shale gas refracturing potential prediction model is set to 0.01, and the shale gas refracturing potential prediction model is iterated until the accuracy reaches the preset threshold.

[0023] Furthermore, the shale gas refracturing potential prediction model was tested and verified by accuracy and Kappa coefficient.

[0024] Furthermore, the output results of the multi-layer perceptron model and the output results of the gated recurrent unit model based on the attention mechanism are spliced ​​and merged through the splicing layer, and then enter the activation function layer for classification.

[0025] In the second aspect, the present invention provides a shale gas re-fracturing potential prediction system based on multimodal data fusion, which includes a data acquisition module, a data processing module and a model construction module; the data acquisition module is used to establish a data set based on the acquired shale gas well data, the data set includes a multidimensional sequence data set and a single-value data set, the multidimensional sequence data set includes logging curve data, the single-value data set includes geological data, reservoir physical property data, initial fracturing parameter data, production dynamic data and rock mechanics data; the re-fracturing potential of the well section is marked by the production dynamic data; the data processing module is used to perform data cleaning and standardization processing, and divide the data set into a training set, a test set and a validation set; the model construction module is used to construct A shale gas refracturing potential prediction model is established, which takes a multidimensional sequence data set and a single-value data set as input and a refracturing effect type as output, wherein the shale gas refracturing potential prediction model includes a multi-layer perceptron model for processing the single-value data set and a gated recurrent unit model based on an attention mechanism for processing the multidimensional sequence data set; a loss function is set, and the shale gas refracturing potential prediction model is iteratively trained and optimized using a training set, and the shale gas refracturing potential prediction model is tested and verified using a test set and a validation set, respectively, to obtain a shale gas refracturing potential prediction model that meets preset requirements; and the shale gas refracturing potential prediction model that meets the preset requirements is used to predict the refracturing potential of a target shale gas well.

[0026] The present invention has the following unexpected beneficial effects:

[0027] The shale gas refracturing potential prediction model described in the present invention uses a multidimensional sequence dataset and a single-value dataset as input and the refracturing effect type as output. It predicts refracturing potential through a deep learning network model, significantly improving prediction efficiency and reducing the time and economic costs required for manual prediction. Unlike traditional prediction methods, which are significantly affected by differences in geological and engineering characteristics and are not transferable, this prediction model has excellent portability and adaptability to mines with different conditions. Furthermore, deep learning is used to optimize and locate the refracturing "sweet spot" section, thereby achieving prediction of the refracturing potential of the entire shale gas well, providing support for the intelligent implementation of the entire refracturing process. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 A schematic flow chart of the shale gas refracturing potential prediction method based on multimodal data fusion according to the present invention is shown.

[0029] Figure 2 A schematic diagram of the algorithm flow of the shale gas refracturing potential prediction model of the present invention is shown.

[0030] Figure 3 A schematic diagram of the structure of the shale gas refracturing potential prediction system based on multimodal data fusion according to the present invention is shown. DETAILED DESCRIPTION

[0031] The following describes the embodiments of the present invention with reference to the accompanying drawings and preferred embodiments. Those skilled in the art will readily appreciate the other advantages and benefits of the present invention from the disclosure herein. The present invention may also be implemented or applied through various other specific embodiments, and the various details in this specification may be modified or altered based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are intended only to illustrate the present invention and are not intended to limit the scope of protection of the present invention.

[0032] In one embodiment, see Figure 1 As shown, the present invention provides a shale gas re-fracturing potential prediction method based on multimodal data fusion, which includes:

[0033] S1. Establishing a data set based on acquired shale gas well data, the data set comprising a multidimensional sequence data set and a single-value data set, the multidimensional sequence data set comprising well logging curve data, the single-value data set comprising geological data, reservoir physical property data, initial fracturing parameter data, production performance data, and rock mechanics data; marking the refracturing potential of the well section using the production performance data;

[0034] S2, perform data cleaning and standardization, and then divide the dataset into training set, test set and validation set;

[0035] S3, constructing a shale gas refracturing potential prediction model that takes a multidimensional sequence dataset and a single-value dataset as input and outputs refracturing potential, wherein the shale gas refracturing potential prediction model includes a multilayer perceptron model for processing the single-value dataset and a gated recurrent unit model based on an attention mechanism for processing the multidimensional sequence dataset;

[0036] S4, setting a loss function, using the training set to iteratively train and optimize the shale gas refracturing potential prediction model, using the test set and validation set to test and validate the shale gas refracturing potential prediction model respectively, to obtain a shale gas refracturing potential prediction model that meets the preset requirements; using the shale gas refracturing potential prediction model that meets the preset requirements to predict the refracturing potential of the target shale gas well.

[0037] The shale gas refracturing potential prediction model described in the present invention uses a multidimensional sequence dataset and a single-value dataset as input and the refracturing effect type as output. It predicts refracturing potential through a deep learning network model, significantly improving prediction efficiency and reducing the time and economic costs required for manual prediction. Unlike traditional prediction methods, which are significantly affected by differences in geological and engineering characteristics and are not transferable, this prediction model has excellent portability and adaptability to mines with different conditions. Furthermore, deep learning is used to optimize and locate the refracturing "sweet spot" section, thereby achieving prediction of the refracturing potential of the entire shale gas well, providing support for the intelligent implementation of the entire refracturing process.

[0038] In a preferred embodiment, the logging curve data includes lithology curve, resistivity curve, porosity curve, organic matter content curve, permeability, saturation, pore fluid, and gas content.

[0039] The fracturing construction curve data includes a pressure curve, a displacement curve and a sand ratio curve.

[0040] The geological data include mineral composition, rock structure, brittleness, fault distribution and fold morphology.

[0041] The reservoir physical property data includes gas saturation.

[0042] The initial fracturing parameter data includes the type and amount of fracturing fluid, and the type and amount of proppant.

[0043] The production dynamic data includes shale gas well production data and pressure gradient data.

[0044] The rock mechanics data include elastic modulus, Poisson's ratio and ground stress data.

[0045] Exemplarily, the method for establishing the dataset specifically includes the following steps:

[0046] S1.1, Data Acquisition: Acquire multi-source data sets, including well logging data, fracturing operation curve data, geological data, reservoir physical property data, initial fracturing parameter data, production performance data and rock mechanics data.

[0047] S1.2, Data integration: Unify data formats to ensure data integrity and consistency.

[0048] S1.3, Data classification: Classify the data set according to its purpose into multidimensional sequence data set and single value data set.

[0049] S1.4, Data Marking: Based on the production and economic effects of old wells in the gas field after repeated fracturing, shale gas wells are segmented and marked into two types: qualified repeated fracturing effect and unqualified repeated fracturing effect.

[0050] Furthermore, the S2 specifically includes the following steps:

[0051] S2.1, Data cleaning: Check all collected data and remove abnormal data points caused by sensor failure or human error.

[0052] S2.2, Data standardization processing: Eliminate false information variations caused by dimensional differences, so as to avoid errors in analysis and calculation caused by different indicator dimensions, and maintain the original valuable information to the greatest extent.

[0053] In this embodiment, the normalization process adopts the Z-score calculation method, and the calculation formula is: Among them, z is the characteristic data after standardization, X is the original data, μ is the mean value of the data, and σ is the standard deviation of the data.

[0054] Data enhancement is performed by rotating, flipping, adding a small amount of noise to some data to increase the diversity of training data.

[0055] Step 2.2, data set division: divide the standardized data set into training set, test set and validation set with a ratio of 7:2:1.

[0056] Furthermore, the S3 specifically includes the following steps:

[0057] S3.1, Model Architecture: The collected well logging data and fracturing operation curve data sets are regarded as multidimensional sequence data sets, and the sequence data sets can be regarded as a set of observation data with the same interval. Therefore, the sequence classification problem of each sub-layer in the prediction of the fracturing potential of normal pressure shale gas is equivalent to a multidimensional sequence classification problem. Assume that there is a sequence data T with dimension n = {T1, T2, ..., T n}, the length of each sequence is m, that is, there are m observations, that is, T i = <t i1 ,t i2 ,…,t in >, its corresponding category is y i ,y i ∈{1,2,...,C}, where C represents the number of categories in the dataset. The single-valued data in each sublayer of the shale gas refracture potential prediction problem is considered a classification problem. The model needs to classify both sequence problems and single-valued data. Therefore, the present invention constructs a shale gas refracture potential prediction model that includes a multilayer perceptron model and a gated recurrent unit based on an attention mechanism.

[0058] The length of a fracturing well is generally more than a kilometer, and the average length of each section is 80 to 100 meters. In order to distinguish and sort the sections of the fracturing well, it is necessary to solve the long sequence machine learning problem. This invention builds a model based on a recurrent neural network, a type of neural network specially designed for processing sequential sequence data. For a given input sequence X = {X1, X2, ..., X t}, the neural network iteratively calculates the hidden vector h={h1,h2,…,h t} and the output sequence y={y1,y2,…,y t}.

[0059] h t =H(W xh x t +W hh h t-1 +b h );

[0060] y t =W hy h t +b y ;

[0061] Where W xh is the weight matrix from input x to hidden layer h, W hh is the weight matrix from the previous hidden layer to the next hidden layer, b is the bias of the corresponding layer, and H is the activation function of the hidden layer.

[0062] Given the small amount of data in shale gas extraction, gated recurrent units (GRUs) can better and faster process and predict sequence data, making them more suitable for solving practical gas well problems. Long-short-term memory (LSTM) neural networks (LSTMs) improve upon traditional recurrent neural networks by enabling them to memorize long-term input information, making them suitable for processing and predicting long-sequence data. GRUs, on the other hand, are an improvement on LSTMs, simplifying their parameters while maintaining their long-term memory function, effectively reducing overfitting.

[0063] Furthermore, to further improve the computational efficiency, generalization, and performance of deep learning models, the present invention incorporates an attention mechanism into traditional gated recurrent unit networks. This attention mechanism aims to address the problem of short-term memory forgetting in traditional recurrent neural networks. This method is conditioned on the context vector V of the output sequence y. The attention mechanism acts at every step in the time series decoding process, forcing the neural network to review the hidden vector corresponding to each instant in the original sequence, retaining important and useful information, which is then used to enhance the currently used hidden vector.

[0064] In one scenario example, the attention score of a segment is first calculated, that is, the similarity between the decoder state at the previous moment and the encoder output at each moment is calculated.

[0065] e t,i =F(h i ,s t-1 ), where e t,i is the i-th attention score output by the decoder to the encoder at time t, h i is the i-th output of the encoder, s t-1 is the output state of the encoder at time t-1, and F is the transformation function when calculating the attention score.

[0066] Then perform Softmax transformation on the attention score to obtain the probability distribution of the attention score. The calculation formula is β t =softmax(e t ), where e t is the attention score vector of the decoder to the encoder at time t, β t for e t The probability distribution of attention scores.

[0067] Next, the attention vector a at time t is calculated using the probability distribution and the states of all encoders t ,

[0068] Finally, the attention vector is combined with the decoder's current input to form new input information, and then the decoding operation is performed, as shown in the following formula.

[0069] s t =f([c t ,a t ],s t-1 );

[0070] Where c t is the input of the decoder at time t, and f is the transformation function when calculating the decoded input.

[0071] The present invention incorporates an attention mechanism into the gated recurrent unit model, enabling the sequence modeling problem of shale gas wellbore segmentation to break the distance constraint and use a smaller time interval to improve the recognition accuracy of the model without considering the negative impact of sequence length.

[0072] The evaluation of each section's refracturing potential can be viewed as a classification problem involving single-valued data that influences refracturing potential. A multi-layer perceptron model is used. The computation of each neuron in the perceptron involves three steps:

[0073] The first step is to superimpose one or more weighted input values ​​to obtain a cumulative value.

[0074] In the second step, the activation function is used to perform nonlinear transformation on the accumulated value.

[0075] The third step is to pass the transformed value to the neurons in the lower layer.

[0076] In addition to the input and output layers, the multi-layer perceptron model can also have multiple hidden layers in the middle, and the layers are all fully connected structures.

[0077] In the present invention, it is assumed that the current multilayer perceptron has L layers, the first layer is the input layer, the Lth layer is the output layer, and the input data of the first input layer is {x1, x2, ..., x n}, the output data of the Lth layer is {y1,y2,…,y n}, the rest are hidden layers. Assume that there are n l neurons, the output data of the lth hidden layer is {h1 (l) ,h2 (l) ,…,h n (l)}The calculation formula is as follows.

[0078]

[0079] In the formula, f() is the activation function, o i (l) ——The i-th neuron in the l-th layer, w ij (l) is the weight from the jth neuron in the l-1th layer to the ith neuron in the lth layer, b i (l) ——The bias of the i-th neuron in the l-th layer.

[0080] The multi-layer perceptron model will learn each neuron in each layer according to the data set, and use the back propagation algorithm to make the learned neural network model better fit the data set. Assume that the pre-processed fracturing potential prediction data is {(x1,y1),(x2,y2),…,(x n ,y n )}, the calculation formula of the back propagation function is as follows.

[0081] Where y k is the true value of the training sample; Output values ​​for the model.

[0082] The weights W and biases B in the multilayer perceptron also need to be iteratively updated, as calculated by the following formula. This iterative update of network weights and biases enables the multilayer perceptron to accomplish complex nonlinear tasks.

[0083]

[0084]

[0085] Where α is the learning rate, and its value range is (0,1).

[0086] S3.2, parameter setting: Since the problem to be solved by the present invention is the modeling problem of multivariate sequence plus single-valued data, it is necessary to apply the univariate GRU to the multivariate problem. The dataset is defined as a tensor of shape (N, Q, M), where N is the number of samples in the dataset, Q is the maximum number of time steps among all variables, and M is the number of variables at each time step. The gated recurrent unit model accepts a single input at each time step, that is, M = 1. This model is a multi-classification problem and accepts M inputs at each time step.

[0087] Preferably, the attention gated recurrent unit is combined with the multi-layer perceptron, and the two branches will produce different results, which are spliced ​​and merged through the Concat layer and finally enter the Softmax layer, i.e., the activation function layer, for classification.

[0088] Furthermore, the S4 specifically includes the following steps:

[0089] S4.1. Determination of loss function: Since the present invention studies classification problems, the loss function is categorical_crossentropy.

[0090] S4.2. Optimization Algorithm Selection: Different hyperparameter combinations require empirical validation. Based on this experience, we selected eight parameters that have the greatest impact on performance for optimization. To eliminate potential overfitting caused by the split between training and test sets, we used K-fold cross-validation (K=10) to verify hyperparameters, using Adam as the optimizer.

[0091] S4.3, model iteration: Set the learning rate of the model to 0.01, and iterate the model continuously until the model prediction results meet the expectations.

[0092] S4.5. Model evaluation and validation: Evaluate and validate the prediction model using accuracy and Kappa coefficient. Model evaluation and validation is an important means of testing model reliability and robustness, and is a key factor in model performance.

[0093] Using accuracy to evaluate the model: Accuracy is the most commonly used indicator for evaluating model performance. It refers to the ratio of the number of correctly classified samples of given data to the total number. This invention uses accuracy as one of the evaluation indicators of the model.

[0094] The calculation formula for accuracy acc is In the formula, total is the number of all samples, TP j is the number of true positives, TN jis the number of true negative examples.

[0095] Kappa coefficient evaluation: As a statistical method used to assess consistency, it is also used to evaluate the accuracy of multi-classification models. In classification problems, consistency refers to whether the model classification results are consistent with the actual classification results. The Kappa coefficient is calculated based on the confusion matrix and its value is usually between 0 and 1.

[0096]

[0097]

[0098] Where, P O is the prediction accuracy, P e For accidental consistency, a ii is the i-th element on the diagonal, N is the total number of samples involved in the classification, a i+ is the number of samples predicted to be of class i, a +i is the number of samples that actually belong to the i-th class.

[0099] The prediction model is evaluated using the above two evaluation indicators, namely accuracy and Kappa coefficient. If the evaluation result is qualified, the construction of the shale gas refracturing potential prediction model is completed; if the evaluation result is unqualified, the accuracy of the database is tested and the parameters and thresholds of the model are adjusted, and the model is rebuilt before model evaluation.

[0100] The number of neurons in the gated recurrent unit model is 64.

[0101] See also Figure 2 As shown in the figure, the trained shale gas re-fracturing potential prediction model includes a multi-layer perceptron model for processing single-value data sets and a gated recurrent unit model based on the attention mechanism for processing multi-dimensional sequence data sets.

[0102] During the training process, Dropout regularization randomly "drops out" (sets their output to 0) a portion of neurons. For example, in a hidden layer with 100 neurons, if the dropout rate is set to 0.5, then in each training iteration, the output of approximately 50 neurons will be set to 0. The main purpose is to prevent the neural network from overfitting. Overfitting refers to a situation where the model performs very well on the training data, but performs poorly on new, unseen data (test data). By randomly dropping neurons, dropout prevents the gated recurrent unit model from over-relying on certain specific neurons, thereby prompting the neural network to learn more robust and generalizable features.

[0103] The number of hidden layers of the multi-layer perceptron model is 2, and the ReLU activation function is used.

[0104] The output of the multilayer perceptron model and the output of the attention-based gated recurrent unit model are concatenated and merged through the concatenation layer. The concatenation is then processed into the activation function layer for classification. This concatenation is then normalized using a normalized exponential function to obtain the classification result.

[0105] In one embodiment, see Figure 3 As shown, a shale gas re-fracturing potential prediction system based on multimodal data fusion is provided. The prediction system 10 includes a data acquisition module 11, a data processing module 11 and a model building module 12.

[0106] The data acquisition module 11 is used to establish a data set based on the acquired shale gas well data, wherein the data set includes a multidimensional sequence data set and a single-value data set. The multidimensional sequence data set includes well logging curve data, and the single-value data set includes geological data, reservoir physical property data, initial fracturing parameter data, production dynamic data and rock mechanics data; the repeated fracturing potential of the well section is marked by the production dynamic data.

[0107] The data processing module 12 is used to perform data cleaning and standardization, and divide the data set into a training set, a test set, and a validation set.

[0108] The model construction module 13 is used to construct a shale gas re-fracturing potential prediction model with a multidimensional sequence data set and a single-value data set as input and a re-fracturing effect type as output, wherein the shale gas re-fracturing potential prediction model includes a multi-layer perceptron model for processing the single-value data set and a gated recurrent unit model based on an attention mechanism for processing the multidimensional sequence data set; a loss function is set, and the shale gas re-fracturing potential prediction model is iteratively trained and optimized using a training set, and the shale gas re-fracturing potential prediction model is tested and verified using a test set and a validation set, respectively, to obtain a shale gas re-fracturing potential prediction model that meets preset requirements; and the shale gas re-fracturing potential prediction model that meets the preset requirements is used to predict the re-fracturing potential of a target shale gas well.

[0109] In order to enable those skilled in the art to more clearly understand the solution of the present application, the following examples are given for illustration.

[0110] 1. Obtain basic data for each section of shale gas re-fractured wells.

[0111] The basic parameters of the target shale gas well are collected. See Tables 1 and 2 for details. The obtained data set includes single-value data and multidimensional sequence data, laying the foundation for the next step of data preprocessing.

[0112] A comparison table of the difference between the expected shale gas production during repeated fracturing of each section of the target well and the actual production after fracturing is compiled. When the ratio of expected production to actual production is greater than 90% and the overall return on investment of the project is above 60%, the shale gas well repeated fracturing effect is marked as qualified and recorded as 1; otherwise, it is marked as unqualified and recorded as 0.

[0113] Table 1 Parameters of each section of shale gas well in specific embodiment

[0114]

[0115] Table 2 Evaluation of historical refracturing effects of various sections in a specific example shale gas well

[0116]

[0117] 2. Data preprocessing: The collected refracturing potential data of 2,147 fracturing sections from 396 shale gas refracturing wells were screened, and samples with missing values ​​were deleted, leaving 1,985 valid data. The basic parameters and refracturing potential data were standardized, and the characteristic data were converted.

[0118] 3. A shale gas refracturing potential prediction model is constructed, which takes multidimensional sequence data sets and single-value data sets as input and refracturing potential as output. This model considers both single-value data and continuously changing multidimensional sequence data, and can more comprehensively reflect the characteristic changes in the gas production process.

[0119] 4. Model training and optimization: Based on the preprocessed and organized production dynamic prediction standard dataset, a machine learning model is trained and generated. For the 1,985 samples in the training dataset, the number of training iterations is set to 300. 100 samples are extracted from the training dataset each time for training until the entire training dataset is traversed.

[0120] During the training process, we used categorical_crossentropy as the loss function and a hyperparameter optimization algorithm for iterative training and model optimization of the deep learning model. The hyperparameter optimization results are shown in Table 3. This resulted in a recurrent neural network model with high computational efficiency and accuracy.

[0121] Table 3 Hyperparameter optimization results

[0122]

[0123] 5. Model evaluation.

[0124] For the validation dataset, the trained shale gas refracturing potential prediction model was used to predict the refracturing potential corresponding to each input data point in the validation dataset. Accuracy and the Kappa coefficient were used as evaluation metrics, and the prediction results were compared with the refracturing potential data in the validation dataset to analyze and evaluate the accuracy of the machine learning model. If the network model's predictions did not meet expectations, the network structure and hyperparameters (such as the number of hidden layers in the multilayer perceptron and the number of neurons in the gated recurrent unit) were adjusted and the network model was retrained.

[0125] For the test set, the verified model is used for testing, and the model is continuously adjusted until it passes the test, and finally a trained shale gas re-fracturing potential prediction model is obtained.

[0126] This example demonstrates the accurate prediction of shale gas well production potential and precise location of the refracturing "sweet spot" section. The system, tested on a test set, achieved an accuracy rate of 91.2% for refracturing "sweet spot" locations, demonstrating the effectiveness and practicality of this method in predicting refracturing potential and locating refracturing "sweet spot" sections.

[0127] The above embodiments are only preferred embodiments for fully illustrating the present invention, and the protection scope of the present invention is not limited thereto. Any equivalent substitution or modification made by those skilled in the art based on the present invention is within the protection scope of the present invention.

Claims

1. A method for predicting shale gas re-fracturing potential based on multimodal data fusion, characterized in that: include: A data set is established based on the acquired shale gas well data, the data set comprising a multidimensional sequence data set and a single-value data set, the multidimensional sequence data set comprising well logging curve data and fracturing operation curve data, the single-value data set comprising geological data, reservoir physical property data, initial fracturing parameter data, production performance data, and rock mechanics data; and the re-fracturing potential of the well section is marked using the production performance data; Perform data cleaning and standardization, and then divide the data set into training set, test set and validation set; Constructing a shale gas refracturing potential prediction model that takes a multidimensional sequence dataset and a single-value dataset as input and outputs refracturing potential, wherein the shale gas refracturing potential prediction model includes a multilayer perceptron model for processing the single-value dataset and a gated recurrent unit model based on an attention mechanism for processing the multidimensional sequence dataset; A loss function is set, and the shale gas refracturing potential prediction model is iteratively trained and optimized using the training set. The shale gas refracturing potential prediction model is tested and verified using the test set and validation set, respectively, to obtain a shale gas refracturing potential prediction model that meets the preset requirements. The refracturing potential of a target shale gas well is predicted using the shale gas refracturing potential prediction model that meets preset requirements.

2. The method for predicting shale gas refracturing potential based on multimodal data fusion according to claim 1, characterized in that: The logging curve data includes lithology curve, resistivity curve, porosity curve, organic matter content curve, permeability, saturation, pore fluid, and gas content; The fracturing operation curve data includes a pressure curve, a displacement curve and a sand ratio curve; and / or, the geological data include mineral composition, rock structure, brittleness, fault distribution and fold morphology; And / or, the reservoir physical property data includes gas saturation; And / or, the primary fracturing parameter data includes the type and amount of fracturing fluid, the type and amount of proppant; And / or, the production performance data includes shale gas well production data and pressure gradient data; And / or, the rock mechanics data includes elastic modulus, Poisson's ratio and ground stress data.

3. The method for predicting shale gas re-fracturing potential based on multimodal data fusion according to claim 1, characterized in that: The parameter settings of the shale gas refracturing potential prediction model include: defining the dataset as a tensor with a shape of (N, Q, M), where N is the number of samples in the dataset, Q is the maximum number of time steps among all variables, and M is the number of variables per time step. The number of hidden layers of the multilayer perceptron model is 2, the number of neurons of the gated recurrent unit model is 64, and the ReLU activation function is used.

4. The method for predicting shale gas refracturing potential based on multimodal data fusion according to claim 1, characterized in that: The loss function is set and the training set is used to iteratively train and optimize the shale gas refracturing potential prediction model. Specifically, the following steps are involved: Set the loss function to categorical_crossentropy; Use K-fold cross validation as the hyperparameter optimization algorithm, and Adam as the optimizer; The learning rate of the shale gas re-fracturing potential prediction model is set to 0.01, and the shale gas re-fracturing potential prediction model is iterated until the accuracy reaches the preset threshold.

5. The method for predicting shale gas refracturing potential based on multimodal data fusion according to claim 1, characterized in that: The shale gas refracturing potential prediction model was tested and verified by accuracy and Kappa coefficient.

6. The method for predicting shale gas refracturing potential based on multimodal data fusion according to claim 1, characterized in that: The output results of the multi-layer perceptron model and the output results of the gated recurrent unit model based on the attention mechanism are spliced ​​and merged through the splicing layer, and then enter the activation function layer for classification.

7. A shale gas re-fracturing potential prediction system based on multimodal data fusion, characterized in that: include: A data acquisition module is used to establish a data set based on the acquired shale gas well data, wherein the data set includes a multidimensional sequence data set, a single-value data set, and a repeated fracturing effect type data set. The multidimensional sequence data set includes well logging curve data, and the single-value data set includes geological data, reservoir physical property data, primary fracturing parameter data, production performance data, and rock mechanics data. The data processing module is used to clean and standardize the data and divide the data set into training set, test set and validation set; A model construction module is used to construct a shale gas re-fracturing potential prediction model with a multidimensional sequence data set and a single-value data set as input and a re-fracturing effect type as output, wherein the shale gas re-fracturing potential prediction model includes a multi-layer perceptron model for processing the single-value data set and a gated recurrent unit model based on an attention mechanism for processing the multidimensional sequence data set; a loss function is set, and the shale gas re-fracturing potential prediction model is iteratively trained and optimized using a training set, and the shale gas re-fracturing potential prediction model is tested and verified using a test set and a validation set, respectively, to obtain a shale gas re-fracturing potential prediction model that meets preset requirements; and the shale gas re-fracturing potential prediction model that meets the preset requirements is used to predict the re-fracturing potential of a target shale gas well.

Images