Method and apparatus for characterizing full bore microannulus gas leakage pathways

Abstract

This invention discloses a method and apparatus for characterizing the gas leakage path in the micro-annulus of the entire wellbore. The method includes: extracting fracturing engineering parameters and geological parameters from the analyzed well fracturing design documents to obtain a combination of fracturing parameters; establishing a finite element model based on the geological and fracturing engineering parameters, and calculating the plastic strain of the cement sheath using the finite element model; training a neural network model using the combination of fracturing parameters as input and the plastic strain of the cement sheath as output to obtain a trained plastic strain prediction model; inputting the fracturing parameter combination of the target well into the plastic strain prediction model, outputting the predicted plastic strain of the cement sheath, and calculating the micro-annulus width based on the predicted plastic strain; and combining the micro-annulus width with an established three-dimensional visualized wellbore trajectory to characterize the gas leakage path in the micro-annulus of the entire wellbore. This invention can improve the accuracy of micro-annulus leakage risk prediction and visually display the gas leakage path.

Description

Technical Field

[0001] This invention relates to the field of oil and gas extraction engineering technology, and in particular to a method and apparatus for characterizing gas leakage paths in the micro-annulus of the entire wellbore. Background Technology

[0002] This section is intended to provide background or context for the embodiments of the invention set forth in the claims. The description herein is not an admission that it is prior art simply because it is included in this section.

[0003] With the increasing depletion of conventional oil and gas resources, oil and gas drilling is gradually moving towards deeper shale formations. Shale gas has high recoverable resources, significant exploration and development results, and broad development prospects. Multi-stage hydraulic fracturing technology is currently the core technology for shale gas development. This technology mainly achieves fracture creation by injecting fracturing fluid into the reservoir, thereby crushing the formation and releasing natural gas from the reservoir to increase production. However, downhole conditions are unpredictable. Deep shale formations have high in-situ stress and rock strength, and wellbore integrity faces challenges from multiple coupled fields. A series of problems arise during hydraulic fracturing, one of the most prominent being the generation of micro-annular gaps in the wellbore cement sheath under cyclic loading. This failure of the wellbore seal creates a flow path, leading to high-pressure gas from the bottom hole flowing into the wellhead annulus and gradually accumulating into annular pressure. If the annular pressure problem is not properly controlled, it will lead to a decrease in wellbore productivity, affecting production efficiency and economic benefits; it will also increase the risk of accidents, causing wellbore safety issues and affecting the well's life cycle. Therefore, micro-annular gaps are an important cause of pressure in annular control. In order to ensure wellbore safety, it is necessary to effectively monitor and control the width of micro-annular gaps.

[0004] In multi-stage hydraulic fracturing, the alternating load generated by the cyclic loading and unloading of casing pressure is a significant cause of accumulated plastic strain on the inner wall of the cement sheath, leading to the formation of microannulus. However, in the entire wellbore environment, in addition to variations in casing pressure, other engineering geological parameters also vary, such as the elastic modulus and triaxial stress of formations at different depths. Therefore, the distribution of microannulus varies at different depths throughout the wellbore, and calculating them separately involves multiple complex parameters. Research on methods to characterize these parameters is of great significance.

[0005] To improve the annular pressure problem in wellbores, more precise and effective prevention and control measures must be proposed. Traditional methods mainly include mechanical experiments, analytical models, and numerical models. Evaluating the integrity of the wellbore cement sheath using experimental, analytical, and numerical simulation methods has promoted theoretical progress in shale oil and gas production capacity research. However, these methods are mainly based on laboratory experiments and mechanical models, introducing numerous assumptions and simplifications during the modeling process. This results in many limitations on model usage, significant differences from engineering realities, and low accuracy in predicting the plastic strain of the cement sheath. Numerous factors influence the failure of the cement sheath seal integrity in oil and gas wells. Complex nonlinear relationships exist between geological parameters, hydraulic fracturing parameters, and cement sheath failure parameters. Conventional numerical calculation methods are extremely inefficient, and currently, there is no method that can visually demonstrate the gas leakage path distribution in the entire wellbore micro-annulus. Summary of the Invention

[0006] This invention provides a method for characterizing the gas leakage path in the micro-annulus of the entire wellbore, to improve the prediction accuracy of the plastic strain of the cement sheath, and to visually display the distribution of the gas leakage path in the micro-annulus of the entire wellbore. The method includes:

[0007] Extract fracturing engineering parameters and geological parameters from the analyzed well fracturing design documents to obtain fracturing parameter combinations;

[0008] Based on geological parameters and fracturing engineering parameters, a finite element model was established, and the plastic strain of the cement sheath was calculated using the finite element model; the finite element model is a combination of casing, cement sheath, and formation.

[0009] Using the combination of fracturing parameters as input and the plastic strain of the cement sheath as output, the neural network model is trained to obtain the trained plastic strain prediction model.

[0010] The fracturing parameters of the target well are input into the plastic strain prediction model, and the plastic strain prediction results of the cement sheath are output. The micro-annulus width is calculated based on the plastic strain prediction results.

[0011] The micro-annular gap width is combined with the established three-dimensional visualized wellbore trajectory to characterize the leakage path of gas in the micro-annular gap throughout the wellbore; the three-dimensional visualized wellbore trajectory is established based on wellbore trajectory parameters using three-dimensional visualization technology.

[0012] This invention also provides a characterization device for gas leakage paths in the micro-annular space of the entire wellbore, to improve the prediction accuracy of plastic strain in the cement sheath and to visually display the distribution of gas leakage paths in the micro-annular space of the entire wellbore. The device includes:

[0013] The fracturing parameter combination acquisition module is used to extract fracturing engineering parameters and geological parameters from the parsed well fracturing design file to obtain fracturing parameter combinations.

[0014] The finite element model building module is used to build a finite element model based on geological parameters and fracturing engineering parameters, and to calculate the plastic strain of the cement sheath through the finite element model; the finite element model is a combination of casing, cement sheath and formation;

[0015] The plastic strain prediction model training module is used to train the neural network model with fracturing parameter combinations as input and the plastic strain of the cement sheath as output, so as to obtain the trained plastic strain prediction model.

[0016] The micro-annular gap width calculation module is used to input the combination of fracturing parameters of the target well into the plastic strain prediction model, output the plastic strain prediction results of the cement sheath, and calculate the micro-annular gap width based on the plastic strain prediction results;

[0017] The gas leakage path characterization module is used to combine the micro-annular gap width with the established three-dimensional visualized wellbore trajectory to characterize the leakage path of gas in the micro-annular gap of the entire wellbore; the three-dimensional visualized wellbore trajectory is established based on wellbore trajectory parameters using three-dimensional visualization technology.

[0018] This invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the above-described method for characterizing the gas leakage path in the micro-annulus of the entire wellbore.

[0019] This invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for characterizing the gas leakage path in the micro-annulus of the entire wellbore.

[0020] This invention also provides a computer program product, which includes a computer program that, when executed by a processor, implements the above-described method for characterizing the gas leakage path in the micro-annulus of the entire wellbore.

[0021] In this embodiment of the invention, fracturing engineering parameters and geological parameters are extracted from the analyzed well fracturing design documents to obtain a combination of fracturing parameters. Based on the geological parameters and fracturing engineering parameters, a finite element model is established, and the plastic strain of the cement sheath is calculated using the finite element model. The finite element model is a combination of casing, cement sheath, and formation. The neural network model is trained using the combination of fracturing parameters as input and the plastic strain of the cement sheath as output to obtain a trained plastic strain prediction model. The fracturing parameter combination of the target well is input into the plastic strain prediction model, and the plastic strain prediction result of the cement sheath is output. The micro-annular gap width is calculated based on the plastic strain prediction result. The micro-annular gap width is combined with the established three-dimensional visualized wellbore trajectory to characterize the leakage path of gas in the micro-annular gap of the entire wellbore. The three-dimensional visualized wellbore trajectory is established using three-dimensional visualization technology based on the wellbore trajectory parameters. In the above process, the embodiments of the present invention accurately calculate the plastic strain of the cement sheath based on the established finite element model of the casing-cement sheath-formation assembly, and train a neural network model with parameter combination as input and plastic strain as output to form a plastic strain prediction model, thereby achieving accurate prediction of the plastic strain of the cement sheath in the entire wellbore of the target well, significantly improving the accuracy of micro-annular leakage risk prediction; then, based on the prediction results of the cement sheath plastic strain, the micro-annular width is calculated, and the micro-annular width is dynamically combined with the wellbore trajectory to characterize the leakage path of gas in the micro-annular space of the entire wellbore, intuitively displaying the gas leakage path, and providing data support for fracturing parameter optimization and wellbore integrity protection. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. In the drawings:

[0023] Figure 1 This is a flowchart illustrating the method for characterizing the gas leakage path in the micro-annulus of the entire wellbore in an embodiment of the present invention;

[0024] Figure 2 This is a finite element model of the casing-cement sheath-formation assembly in an embodiment of the present invention;

[0025] Figure 3 This is a flowchart illustrating the calculation of the micro-annular gap width in an embodiment of the present invention;

[0026] Figure 4 This is a flowchart illustrating the generation of a gas leakage risk distribution map in an embodiment of the present invention;

[0027] Figure 5 This is a risk distribution diagram of gas leakage paths in an embodiment of the present invention;

[0028] Figure 6 This is a diagram of the cloud-based calculation interface for wellbore trajectory in an embodiment of the present invention;

[0029] Figure 7 This is a schematic diagram of a characterization device for the gas leakage path in the micro-annulus of the entire wellbore in an embodiment of the present invention. Detailed Implementation

[0030] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings. Here, the illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0031] The acquisition, storage, use, and processing of data in this application all comply with the relevant provisions of national laws and regulations.

[0032] Figure 1 This is a flowchart of a method for characterizing the gas leakage path in the micro-annulus of the entire wellbore, as described in an embodiment of the present invention. The method includes:

[0033] Step 101: Extract fracturing engineering parameters and geological parameters from the analyzed well fracturing design documents to obtain the fracturing parameter combination;

[0034] Step 102: Based on geological parameters and fracturing engineering parameters, establish a finite element model and calculate the plastic strain of the cement sheath using the finite element model; the finite element model is a combination of casing, cement sheath, and formation.

[0035] Step 103: Using the combination of fracturing parameters as input and the plastic strain of the cement sheath as output, train the neural network model to obtain the trained plastic strain prediction model.

[0036] Step 104: Input the fracturing parameter combination of the target well into the plastic strain prediction model, output the plastic strain prediction result of the cement sheath, and calculate the micro-annulus width based on the plastic strain prediction result;

[0037] Step 105: Combine the micro-annular gap width with the established three-dimensional visualized wellbore trajectory to characterize the leakage path of gas in the micro-annular gap of the entire wellbore; the three-dimensional visualized wellbore trajectory is established based on wellbore trajectory parameters using three-dimensional visualization technology.

[0038] Each step is explained in detail below.

[0039] In step 101, fracturing engineering parameters and geological parameters are extracted from the parsed well fracturing design document to obtain the fracturing parameter combination.

[0040] In a specific embodiment, text recognition technology is used to parse the text information in the well fracturing design document, extracting and storing key fracturing engineering parameters, wellbore trajectory parameters, and geological parameters. The fracturing parameter combination includes multiple controlling factors such as maximum horizontal stress, minimum horizontal stress, vertical stress, casing internal pressure, cement sheath elastic modulus, cement sheath Poisson's ratio, formation elastic modulus, formation Poisson's ratio, wellbore diameter, casing inner diameter, and casing outer diameter. Additionally, the fracturing engineering parameters also include: fracturing flow rate, fracturing pressure, fracturing time, fracturing friction, casing outer diameter, and casing wall thickness. Geological parameters include: elastic modulus, Poisson's ratio, internal friction angle, and cohesion. Wellbore trajectory parameters also include depth sounding, inclination angle, azimuth angle, vertical depth, dogleg degree, north-south displacement, east-west displacement, horizontal displacement, and closure azimuth.

[0041] In step 102, a finite element model is established based on geological parameters and fracturing engineering parameters, and the plastic strain of the cement sheath is calculated through the finite element model; the finite element model is a combination of casing, cement sheath and formation.

[0042] In a specific embodiment, the extracted geological parameters are used as attribute data for the finite element model to establish a casing-cement sheath-formation composite model, and boundary conditions and loads are applied to it according to fracturing engineering parameters. The finite element model numerical simulation can accurately simulate and calculate the strain state of the downhole cement sheath to determine whether there is a risk of gas leakage in the wellbore. Figure 2 The finite element model of the casing-cement sheath-formation assembly in this embodiment of the invention is as follows: Figure 2 As shown. The finite element model should include parameters such as the geometry, physical material properties, and surrounding wellbore environment (e.g., well depth, casing pressure, formation pressure, temperature, etc.) of the casing-cement sheath-formation assembly. During cyclic loading and unloading, plastic strain occurs at the cement sheath interface and accumulates continuously with alternating loads. To address this, considering the cement sheath damage process, cohesive elements are used for simulation calculations. Zero-thickness cohesive elements are set at the casing-cement sheath and cement sheath-formation interfaces to simulate the accumulated plastic strain on the cement sheath after each loading and unloading. Based on actual downhole conditions, parameters are grouped, and finite element analysis calculations are performed to simulate the failure of the cement sheath under these conditions. Then, the width of the micro-annulus is calculated based on the plastic strain of the cement sheath to determine whether there is a risk of gas leakage from the cement sheath.

[0043] In one embodiment, a finite element model is established based on geological parameters and fracturing engineering parameters. The plastic strain of the cement sheath is calculated using the finite element model, including:

[0044] The load conditions corresponding to the fracturing engineering parameters are input into the finite element model for response calculation, and the plastic strain data of the cement sheath are output; where the load conditions are the preset parameter variation range of the fracturing engineering parameters.

[0045] Based on the preset parameter variation range, finite element models with different parameter combinations are established, and the response of the finite element models in batches is calculated to obtain the plastic strain data of the cement ring under different load conditions. The micro-ring gap width is then calculated, and the failure status of the cement ring is determined based on the micro-ring gap width.

[0046] In step 103, the neural network model is trained using the combination of fracturing parameters as input and the plastic strain of the cement sheath as output, resulting in a trained plastic strain prediction model.

[0047] In a specific embodiment, before constructing the neural network model, a corresponding dataset needs to be prepared. Based on the finite element model parameters and batch calculation results, fracturing parameters and cement sheath failure results for different oil and gas wells and different well sections of each well are extracted and integrated to form structured data and stored. The output parameters collected in the database mainly include: cement sheath strain, a total of 1 output result, which is used to calculate the strain failure situation in conjunction with the micro-annular gap width. The input parameters collected in the database mainly include: maximum horizontal in-situ stress, minimum horizontal in-situ stress, vertical in-situ stress, casing internal pressure, cement sheath elastic modulus, cement sheath Poisson's ratio, formation elastic modulus, formation Poisson's ratio, and casing specifications, a total of 9 main controlling factors. The parameters of maximum horizontal stress, minimum horizontal stress, vertical stress, casing internal pressure, cement sheath elastic modulus, cement sheath Poisson's ratio, formation elastic modulus, and formation Poisson's ratio vary considerably. Based on the analysis of drilling and completion field data, the range and step size of these parameters can be determined, as shown in Table 1. The combination of wellbore diameter, casing inner diameter, and casing outer diameter is relatively fixed. Based on the actual parameter combinations on site, the parameters for numerical simulation calculations are determined, as shown in Table 2.

[0048] Table 1. Parameter Value Table

[0049] Parameter name Parameter variation range Variation step Maximum horizontal ground stress (Mpa) 30-90 15 Minimum horizontal ground stress (Mpa) 20-65 15 Vertical ground stress (Mpa) 30-90 15 Stratum elastic modulus (Gpa) 20-80 15 Stratum Poisson's ratio 0.1-0.3 0.05 Casing internal pressure (Mpa) 60-140 20 Cement sheath elastic modulus (Gpa) 2-10 2 Cement sheath Poisson's ratio 0.1-0.3 0.05

[0050] Table 2. Combination Parameters of Wellbore Diameter, Casing Outer Diameter, and Casing Wall Thickness

[0051]

[0052] As shown in Table 1, the parameter range and step size can be obtained by using numerical calculation software to simulate the stress and strain of cement sheath under different parameter combinations. This can generate 5*4*5*5*5*5*5*5=312,500 sets of data. Combined with different combinations of wellbore diameter, casing inner diameter and casing outer diameter, a total of 312,500*8=2,500,000 sets of data can be generated, thus forming a large dataset.

[0053] In one embodiment, a neural network model is trained using a combination of fracturing parameters as input and the plastic strain of the cement sheath as output to obtain a trained plastic strain prediction model, including:

[0054] Using a combination of fracturing parameters as input and the plastic strain of the cement sheath as output, a BP neural network model is trained to obtain a trained plastic strain prediction model. The combination of fracturing parameters includes: maximum horizontal stress, minimum horizontal stress, vertical stress, casing internal pressure, cement sheath elastic modulus, cement sheath Poisson's ratio, formation elastic modulus, formation Poisson's ratio, and casing wall thickness, or any combination thereof.

[0055] In a specific embodiment, plastic strain calculations are performed under different load conditions based on the aforementioned finite element model. The calculation results of the plastic strain of the cement ring and the corresponding parameter combinations are saved as sample data. The parameter combinations are changed to perform the next set of ring plastic strain calculations until all cement ring plastic strain calculations under different parameter combinations are completed, thereby establishing a dataset for neural network training.

[0056] The resulting dataset was used to allocate training, validation, and test sets. A backpropagation (BP) neural network structure was designed, and the number of neurons in the input, output, and hidden layers was determined based on the input and output parameters. The activation function was determined, and the neural network model was trained. The neural network was designed to learn from the database and predict the risk of gas leakage caused by micro-annular gaps in cement rings.

[0057] In a specific embodiment, training data is extracted from the database to create a dataset, and missing values, outliers, and inconsistencies in the data are addressed. Necessary data preprocessing operations, such as normalization or standardization, are performed to ensure the effectiveness of the neural network training. The dataset is divided into training, validation, and test sets. A typical division ratio is 70% training, 15% validation, and 15% test. The training set is used to train the model, the validation set is used to adjust model hyperparameters and prevent overfitting, and the test set is used to finally evaluate the model's generalization ability. For a backpropagation (BP) neural network, a structure containing an input layer, several hidden layers, and an output layer is selected. The neural network is trained using the training set, a loss function is defined, and the model parameters are iteratively optimized. The model performance is then evaluated on the validation set, and the neural network's hyperparameters are adjusted. Finally, the model's performance is evaluated using the test set. Based on the test set results and practical application requirements, the neural network structure is adjusted or the model training process is improved to further optimize the neural network model.

[0058] Neural networks are widely used for predicting and simulating complex systems due to their ability to process large amounts of complex data and learn patterns from them. Neural network models can accurately predict the risk points and flow paths of gas leaks in complex environments by learning from a large amount of historical data on cement ring failures and real-time monitoring data.

[0059] In step 104, the fracturing parameters of the target well are input into the plastic strain prediction model, and the plastic strain prediction results of the cement sheath are output. The micro-annulus width is calculated based on the plastic strain prediction results.

[0060] In a specific embodiment, a neural network model is used to calculate and evaluate the gas leakage risk that different fractured wells may face under specific design parameters by inputting the main controlling factors of cement sheath failure such as different geological features and engineering parameters, and to test the correctness of the optimized model. The trained and established adjusted neural network model is deployed in the cloud, and the information of a well in the same area is loaded and sent to the cloud. The trained model is used to predict the cement sheath strain corresponding to the new input parameters, calculate the micro-annular gap width to judge the leakage risk of fluid loss along the micro-annular gap, and combine it with the three-dimensional visualized wellbore trajectory to form a characterization of the gas leakage path of the entire wellbore.

[0061] In one embodiment, calculating the micro-annular gap width based on plastic strain prediction results includes:

[0062] The micro-annular gap width is calculated based on the plastic strain prediction results and the cement ring thickness.

[0063] In one embodiment, the micro-annular gap width is calculated based on the predicted plastic strain and the cement ring thickness, including:

[0064] The width of the micro-annulus gap is calculated using the following formula:

[0065] L = H·ε;

[0066] Where L is the width of the micro-annulus, H is the thickness of the cement annulus, and ε is the predicted result of plastic strain.

[0067] In step 105, the micro-annular gap width is combined with the established three-dimensional visualized wellbore trajectory to characterize the leakage path of gas in the micro-annular gap throughout the wellbore; the three-dimensional visualized wellbore trajectory is established based on wellbore trajectory parameters using three-dimensional visualization technology.

[0068] Figure 3 This is a flowchart illustrating the calculation of the micro-annulus width in an embodiment of the present invention. In one embodiment, the fracturing parameters of the target well are input into a plastic strain prediction model, which outputs the plastic strain prediction results of the cement sheath. The micro-annulus width is then calculated based on the plastic strain prediction results, including:

[0069] Step 301: Input the combination of fracturing parameters corresponding to each well depth in the target well into the plastic strain prediction model. For each well depth, output the plastic strain prediction result of the corresponding cement sheath through the plastic strain prediction model.

[0070] Step 302: Calculate the corresponding micro-annular gap width based on the plastic strain prediction results at each well depth.

[0071] Figure 4 This is a flowchart illustrating the generation of a gas leakage risk distribution map in an embodiment of the present invention. In one embodiment, the micro-annular gap width is combined with the established three-dimensional visualized wellbore trajectory to characterize the leakage path of gas in the micro-annular gap throughout the wellbore, including:

[0072] Step 401: Based on the well depth, inclination angle and azimuth angle in the well trajectory parameters, generate the three-dimensional spatial coordinates of the well trajectory using three-dimensional visualization technology;

[0073] Step 402: Map the micro-annular gap width at each well depth to the three-dimensional spatial coordinates of the wellbore trajectory;

[0074] Step 403: Based on the preset micro-annular gap width threshold, the risk level is divided, and different color codes are used to mark the risk level on the wellbore trajectory to generate a gas leakage risk distribution map. The gas leakage risk distribution map is used to characterize the leakage path of gas in the micro-annular gap of the entire wellbore.

[0075] Figure 5 This invention provides a gas leakage path risk distribution map in an embodiment of the invention. Specifically, the plastic strain prediction results output by the neural network are combined with 3D wellbore trajectory data. The plastic strain prediction results correspond one-to-one with the well depth location to generate a full-well gas leakage path risk distribution map, ensuring accurate display of the wellbore trajectory and crossflow risk distribution. Simultaneously, the visualized wellbore trajectory is designed for good interactivity, providing a user-friendly interface and controls, allowing users to freely rotate, zoom, and browse the 3D scene. Color coding is used as a visual means to represent different risk levels of gas leakage, providing interpretation and analysis of the gas leakage path prediction results, helping users understand the crossflow risk at different well depths.

[0076] Figure 6 This diagram illustrates the cloud-based wellbore trajectory calculation interface in this embodiment of the invention. A trained and adjusted cement sheath micro-annular gas leakage prediction model is deployed in the cloud. Information about a well in the same area is loaded and sent to the cloud-based cement sheath micro-annular gas leakage prediction model. Finally, the cloud-based model calculates and predicts the potential cement sheath failure and crossflow risk of the target well based on the input parameters. This prediction is then combined with a 3D visualized wellbore trajectory for intuitive representation. Figure 6 As shown, users select a wellhead and input corresponding parameters according to their needs, submitting the data to the cloud for rapid calculation. The model quickly predicts the risk of cement sheath failure, and the results are assigned to the 3D wellbore trajectory, intuitively displaying the potential crossflow risks at different locations throughout the well. Through the cloud platform, the gas leakage risk at different locations in the wellbore can be calculated and displayed in real time. Based on the actual situation inside the well, the fracturing parameters can be adjusted in real time using the model's calculation results to protect the integrity of the wellbore.

[0077] This invention leverages neural networks, widely used for predicting and simulating complex systems due to their ability to process large amounts of complex data and learn patterns. The neural network model can accurately predict risk points and crossflow paths for gas leaks in complex environments by learning from historical data on cement sheath failures and real-time monitoring data. Combined with 3D wellbore visualization technology, the prediction results can be visually displayed, identifying potential problem areas and risk zones. This early detection helps to adjust hydraulic fracturing design and wellbore structure in a timely manner, reducing potential engineering problems and economic losses. It can also calculate the micro-annulus width at any location throughout the well under different parameters, and thereby assess the risk of gas leaks causing crossflow. Furthermore, combining the neural network model with 3D visualization to predict and characterize the formation risk of crossflow paths effectively addresses the challenges of complex oil and gas extraction environments, improves the accuracy and efficiency of engineering decisions, and reduces risks and costs during the extraction process.

[0078] This invention also provides a characterization device for gas leakage paths in the micro-annular gaps of the entire wellbore, as described in the following embodiments. Since the principle behind this device is similar to the characterization method for gas leakage paths in the micro-annular gaps of the entire wellbore, its implementation can be referred to the implementation of the characterization method for gas leakage paths in the micro-annular gaps of the entire wellbore; repeated details will not be elaborated further.

[0079] Figure 7 This is a schematic diagram of a characterization device for the gas leakage path in the micro-annulus of the entire wellbore, as described in an embodiment of the present invention. The device includes:

[0080] The fracturing parameter combination acquisition module 701 is used to extract fracturing engineering parameters and geological parameters from the parsed well fracturing design file to obtain the fracturing parameter combination.

[0081] The finite element model establishment module 702 is used to establish a finite element model based on geological parameters and fracturing engineering parameters, and to calculate the plastic strain of the cement sheath through the finite element model; the finite element model is a combination of casing, cement sheath and formation;

[0082] The plastic strain prediction model training module 703 is used to train the neural network model with the combination of fracturing parameters as input and the plastic strain of the cement sheath as output, so as to obtain the trained plastic strain prediction model.

[0083] The micro-annular gap width calculation module 704 is used to input the combination of fracturing parameters of the target well into the plastic strain prediction model, output the plastic strain prediction results of the cement sheath, and calculate the micro-annular gap width based on the plastic strain prediction results.

[0084] The gas leakage path characterization module 705 is used to combine the micro-annular gap width with the established three-dimensional visualized wellbore trajectory to characterize the leakage path of gas in the micro-annular gap of the entire wellbore; the three-dimensional visualized wellbore trajectory is established based on wellbore trajectory parameters using three-dimensional visualization technology.

[0085] In one embodiment, the finite element model establishment module 702 is specifically used for:

[0086] The load conditions corresponding to the fracturing engineering parameters are input into the finite element model for response calculation, and the plastic strain data of the cement sheath are output; where the load conditions are the preset parameter variation range of the fracturing engineering parameters.

[0087] In one embodiment, the plastic strain prediction model training module 703 is specifically used for:

[0088] Using a combination of fracturing parameters as input and the plastic strain of the cement sheath as output, a BP neural network model is trained to obtain a trained plastic strain prediction model. The combination of fracturing parameters includes: maximum horizontal stress, minimum horizontal stress, vertical stress, casing internal pressure, cement sheath elastic modulus, cement sheath Poisson's ratio, formation elastic modulus, formation Poisson's ratio, and casing wall thickness, or any combination thereof.

[0089] In one embodiment, the micro-annular gap width calculation module 704 is specifically used for:

[0090] The micro-annular gap width is calculated based on the plastic strain prediction results and the cement ring thickness.

[0091] In one embodiment, the micro-annular gap width calculation module 704 is specifically used for:

[0092] Based on the predicted plastic strain and the thickness of the cement ring, the width of the micro-ring gap is calculated using the following formula, including:

[0093] L = H·ε;

[0094] Where L is the width of the micro-annulus, H is the thickness of the cement annulus, and ε is the predicted result of plastic strain.

[0095] In one embodiment, the micro-annular gap width calculation module 704 is specifically used for:

[0096] The combination of fracturing parameters corresponding to each well depth in the target well is input into the plastic strain prediction model. For each well depth, the plastic strain prediction model outputs the corresponding plastic strain prediction result of the cement sheath.

[0097] Based on the predicted plastic strain at each well depth, the corresponding micro-annulus width is calculated.

[0098] In one embodiment, the gas leakage path characterization module 705 is specifically used for:

[0099] Based on the well depth, inclination angle, and azimuth angle in the well trajectory parameters, the three-dimensional spatial coordinates of the well trajectory are generated using three-dimensional visualization technology;

[0100] Map the width of the micro-annulus at each well depth to the three-dimensional spatial coordinates of the wellbore trajectory;

[0101] Risk levels are classified based on a preset micro-annular gap width threshold. Different color codes are used to mark the risk levels on the wellbore trajectory to generate a gas leakage risk distribution map. The gas leakage risk distribution map is used to characterize the leakage path of gas in the micro-annular gaps of the entire wellbore.

[0102] This invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the above-described method for characterizing the gas leakage path in the micro-annulus of the entire wellbore.

[0103] This invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for characterizing the gas leakage path in the micro-annulus of the entire wellbore.

[0104] This invention also provides a computer program product, which includes a computer program that, when executed by a processor, implements the above-described method.

[0105] In this embodiment of the invention, fracturing engineering parameters and geological parameters are extracted from the analyzed well fracturing design documents to obtain a combination of fracturing parameters. Based on the geological parameters and fracturing engineering parameters, a finite element model is established, and the plastic strain of the cement sheath is calculated using the finite element model. The finite element model is a combination of casing, cement sheath, and formation. The neural network model is trained using the combination of fracturing parameters as input and the plastic strain of the cement sheath as output to obtain a trained plastic strain prediction model. The fracturing parameter combination of the target well is input into the plastic strain prediction model, and the plastic strain prediction result of the cement sheath is output. The micro-annular gap width is calculated based on the plastic strain prediction result. The micro-annular gap width is combined with the established three-dimensional visualized wellbore trajectory to characterize the leakage path of gas in the micro-annular gap of the entire wellbore. The three-dimensional visualized wellbore trajectory is established using three-dimensional visualization technology based on the wellbore trajectory parameters. In the above process, the embodiments of the present invention accurately calculate the plastic strain of the cement sheath based on the established finite element model of the casing-cement sheath-formation assembly, and train a neural network model with parameter combination as input and plastic strain as output to form a plastic strain prediction model, thereby achieving accurate prediction of the plastic strain of the cement sheath in the entire wellbore of the target well, significantly improving the accuracy of micro-annular leakage risk prediction; then, based on the prediction results of the cement sheath plastic strain, the micro-annular width is calculated, and the micro-annular width is dynamically combined with the wellbore trajectory to characterize the leakage path of gas in the micro-annular space of the entire wellbore, intuitively displaying the gas leakage path, and providing data support for fracturing parameter optimization and wellbore integrity protection.

[0106] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0107] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0108] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0109] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0110] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for characterizing the gas leakage path in the micro-annulus of the entire wellbore, characterized in that, include: Extract fracturing engineering parameters and geological parameters from the analyzed well fracturing design documents to obtain fracturing parameter combinations; Based on geological parameters and fracturing engineering parameters, a finite element model was established, and the plastic strain of the cement sheath was calculated using the finite element model; the finite element model is a combination of casing, cement sheath and formation. Using the combination of fracturing parameters as input and the plastic strain of the cement sheath as output, the neural network model is trained to obtain the trained plastic strain prediction model. The fracturing parameters of the target well are input into the plastic strain prediction model, and the plastic strain prediction results of the cement sheath are output. The micro-annulus width is calculated based on the plastic strain prediction results. The micro-annular gap width is combined with the established three-dimensional visualized wellbore trajectory to characterize the leakage path of gas in the micro-annular gap throughout the wellbore; The three-dimensional visualized wellbore trajectory is established using three-dimensional visualization technology based on wellbore trajectory parameters.

2. The method as described in claim 1, characterized in that, Based on geological parameters and fracturing engineering parameters, a finite element model was established. The plastic strain of the cement sheath was calculated using the finite element model, including: The load conditions corresponding to the fracturing engineering parameters are input into the finite element model for response calculation, and the plastic strain data of the cement sheath are output; where the load conditions are the preset parameter variation range of the fracturing engineering parameters.

3. The method as described in claim 1, characterized in that, Using a combination of fracturing parameters as input and the plastic strain of the cement sheath as output, a neural network model is trained to obtain a trained plastic strain prediction model, including: Using a combination of fracturing parameters as input and the plastic strain of the cement sheath as output, a BP neural network model is trained to obtain a trained plastic strain prediction model. The combination of fracturing parameters includes: maximum horizontal stress, minimum horizontal stress, vertical stress, casing internal pressure, cement sheath elastic modulus, cement sheath Poisson's ratio, formation elastic modulus, formation Poisson's ratio, and casing wall thickness, or any combination thereof.

4. The method as described in claim 1, characterized in that, The micro-annular gap width is calculated based on the plastic strain prediction results, including: The micro-annular gap width is calculated based on the plastic strain prediction results and the cement ring thickness.

5. The method as described in claim 4, characterized in that, Based on the predicted plastic strain and the thickness of the cement ring, the width of the micro-ring gap is calculated, including: The width of the micro-annulus gap is calculated using the following formula: L = H·ε; Where L is the width of the micro-annulus, H is the thickness of the cement annulus, and ε is the predicted result of plastic strain.

6. The method as described in claim 1, characterized in that, The fracturing parameters of the target well are input into the plastic strain prediction model, which outputs the plastic strain prediction results of the cement sheath. The micro-annulus width is then calculated based on these results, including: The combination of fracturing parameters corresponding to each well depth in the target well is input into the plastic strain prediction model. For each well depth, the plastic strain prediction model outputs the corresponding plastic strain prediction result of the cement sheath. Based on the predicted plastic strain at each well depth, the corresponding micro-annulus width is calculated.

7. The method as described in claim 6, characterized in that, The micro-annular gap width is combined with the established 3D visualized wellbore trajectory to characterize the leakage path of gas in the micro-annular gap throughout the wellbore, including: Based on the well depth, inclination angle, and azimuth angle in the well trajectory parameters, the three-dimensional spatial coordinates of the well trajectory are generated using three-dimensional visualization technology; Map the width of the micro-annulus at each well depth to the three-dimensional spatial coordinates of the wellbore trajectory; Risk levels are classified based on a preset micro-annular gap width threshold. Different color codes are used to mark the risk levels on the wellbore trajectory to generate a gas leakage risk distribution map. The gas leakage risk distribution map is used to characterize the leakage path of gas in the micro-annular gaps of the entire wellbore.

8. A characterization device for gas leakage paths in micro-annular gaps throughout a wellbore, characterized in that, include: The fracturing parameter combination acquisition module is used to extract fracturing engineering parameters and geological parameters from the parsed well fracturing design file to obtain fracturing parameter combinations. The finite element model building module is used to build a finite element model based on geological parameters and fracturing engineering parameters, and to calculate the plastic strain of the cement sheath through the finite element model; the finite element model is a combination of casing, cement sheath and formation; The plastic strain prediction model training module is used to train the neural network model with fracturing parameter combinations as input and the plastic strain of the cement sheath as output, so as to obtain the trained plastic strain prediction model. The micro-annular gap width calculation module is used to input the combination of fracturing parameters of the target well into the plastic strain prediction model, output the plastic strain prediction results of the cement sheath, and calculate the micro-annular gap width based on the plastic strain prediction results; The gas leakage path characterization module is used to combine the micro-annulus width with the established three-dimensional visualized wellbore trajectory to characterize the leakage path of gas in the micro-annulus throughout the wellbore. The three-dimensional visualized wellbore trajectory is established using three-dimensional visualization technology based on wellbore trajectory parameters.

9. The apparatus as claimed in claim 8, characterized in that, The finite element model building module is specifically used for: The load conditions corresponding to the fracturing engineering parameters are input into the finite element model for response calculation, and the plastic strain data of the cement sheath are output; where the load conditions are the preset parameter variation range of the fracturing engineering parameters.

10. The apparatus as claimed in claim 8, characterized in that, The plastic strain prediction model training module is specifically used for: Using a combination of fracturing parameters as input and the plastic strain of the cement sheath as output, a BP neural network model is trained to obtain a trained plastic strain prediction model. The combination of fracturing parameters includes: maximum horizontal stress, minimum horizontal stress, vertical stress, casing internal pressure, cement sheath elastic modulus, cement sheath Poisson's ratio, formation elastic modulus, formation Poisson's ratio, and casing wall thickness, or any combination thereof.

11. The apparatus as claimed in claim 8, characterized in that, The micro-annular gap width calculation module is specifically used for: The micro-annular gap width is calculated based on the plastic strain prediction results and the cement ring thickness.

12. The apparatus as claimed in claim 11, characterized in that, The micro-annular gap width calculation module is specifically used for: Based on the predicted plastic strain and the thickness of the cement ring, the width of the micro-ring gap is calculated using the following formula, including: L = H·ε; Where L is the width of the micro-annulus, H is the thickness of the cement annulus, and ε is the predicted result of plastic strain.

13. The apparatus as claimed in claim 8, characterized in that, The micro-annular gap width calculation module is specifically used for: The combination of fracturing parameters corresponding to each well depth in the target well is input into the plastic strain prediction model. For each well depth, the plastic strain prediction model outputs the corresponding plastic strain prediction result of the cement sheath. Based on the predicted plastic strain at each well depth, the corresponding micro-annulus width is calculated.

14. The apparatus as claimed in claim 13, characterized in that, The gas leak path characterization module is specifically used for: Based on the well depth, inclination angle, and azimuth angle in the well trajectory parameters, the three-dimensional spatial coordinates of the well trajectory are generated using three-dimensional visualization technology; Map the width of the micro-annulus at each well depth to the three-dimensional spatial coordinates of the wellbore trajectory; Risk levels are classified based on a preset micro-annular gap width threshold. Different color codes are used to mark the risk levels on the wellbore trajectory to generate a gas leakage risk distribution map. The gas leakage risk distribution map is used to characterize the leakage path of gas in the micro-annular gaps of the entire wellbore.

15. 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 computer program, it implements the method of any one of claims 1 to 7.

16. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method of any one of claims 1 to 7.

17. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the method of any one of claims 1 to 7.

Images