Three-dimensional stress calculation method for hydraulic fracturing considering borehole inclination angle

By considering the borehole inclination angle and combining it with a neural network model, the method for calculating the three-dimensional geostress of hydraulic fracturing is improved. This solves the problem of inaccurate three-dimensional geostress measurement in inclined boreholes in traditional methods, enabling more accurate hydraulic fracturing design and engineering optimization, and improving the efficiency and safety of oil and gas extraction.

CN120317144BActive Publication Date: 2025-12-26UNIV OF SCI & TECH BEIJING +2
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202510764174.3
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-06-10
Publication Date
2025-12-26
Estimated Expiration
2045-06-10

AI Technical Summary

Technical Problem

Traditional hydraulic fracturing methods cannot accurately measure the three-dimensional geostress state of inclined boreholes, resulting in insufficient prediction accuracy of hydraulic fracturing in complex geological environments. This may lead to inaccurate fracture propagation or hydraulic fracturing failure, especially in unconventional oil and gas extraction.

Method used

A three-dimensional geostress calculation method for hydraulic fracturing that takes into account the borehole inclination angle is adopted. By collecting geological feature data, elastic stiffness, stress ratio and inclination depth index are generated. Combined with a neural network convolutional structure model, the three-dimensional geostress of hydraulic fracturing is predicted, and the borehole inclination angle is adjusted according to the fracturing threshold.

Benefits of technology

It significantly improves the prediction accuracy of three-dimensional geostress caused by hydraulic fracturing, optimizes borehole design, reduces engineering risks, enhances the efficiency of geothermal energy and oil and gas extraction, and improves the efficiency and safety of hydraulic fracturing projects.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120317144B_ABST
    Figure CN120317144B_ABST
Patent Text Reader

Abstract

The present application provides a kind of water pressure fracturing three-dimensional stress calculation method considering borehole inclination angle, it is related to rock mechanics and water pressure fracturing engineering technical field, the present application is by collecting geological feature data, and the elastic stiffness index of rock mass is generated in combination with these data, stress ratio index and inclination depth index, form a comprehensive feature vector, establish water pressure injection model, the feature vector is as input, predict the three-dimensional ground stress when fracture occurs, based on the three-dimensional ground stress of model output, in combination with borehole inclination angle, calculate the vertical stress and horizontal stress of rock mass, judge whether stress is overproof, if it does not exceed threshold value, adjust borehole inclination angle, until stress is overproof and record the real water pressure fracturing three-dimensional ground stress.The present application is by collecting geological feature data, generating rock mass feature vector, and based on water pressure injection model, predict three-dimensional ground stress, realize the accurate calculation of water pressure fracturing three-dimensional ground stress of inclined borehole.
Need to check novelty before this filing date? Find Prior Art

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of rock mechanics and hydraulic fracturing engineering, and particularly to a method for calculating three-dimensional in-situ stress of hydraulic fracturing considering the inclination angle of a borehole. BACKGROUND

[0002] Although hydraulic fracturing is usually performed in vertical boreholes, it is often necessary to test inclined wellbores. For example, in the oil industry, deviated holes are increasingly used to improve production efficiency. In geotechnical engineering site investigation, some inclined exploration holes are usually drilled to intersect with vertical joint sets, which can be missed by vertical boreholes. In addition, rock properties or drilling difficulties can cause unexpected deviated wells.

[0003] With the increasing demand for the exploitation of unconventional resources such as geothermal, shale gas, and shale oil, deep in-situ stress measurement has extremely important practical significance in the safe and efficient development of energy resources. Accurate determination of the three-dimensional in-situ stress state is a necessary prerequisite for studying the development trajectory of hydraulic fractures, analyzing the stability of the borehole wall, optimizing wellbore design and fracturing parameters, and improving resource recovery. The hydraulic fracturing method is the most commonly used method for measuring in-situ stress in vertical deep boreholes at home and abroad, but the traditional hydraulic fracturing method can only measure the two-dimensional in-situ stress state on the vertical borehole cross-section, and the application range is severely limited. In addition, due to factors such as rock properties or drilling difficulties, unexpected deviated wells (with a certain angle to the vertical direction) can occur during drilling, and in the exploitation of unconventional resources, deviated wells are increasingly used to improve production efficiency. However, the traditional hydraulic fracturing in-situ stress solution theory based on the plane strain assumption is invalid for deviated wells, and a true three-dimensional mechanical analysis is needed. Therefore, combined with the inclination angle of the borehole, three-dimensional in-situ stress calculation can more accurately obtain the true three-dimensional in-situ stress distribution in the rock mass, thereby simulating the fracture propagation path, fracture height, optimizing the fracturing design, and improving the production efficiency and safety of oil and gas wells. With the advancement of numerical simulation technology and the development of high-precision measurement technology, the study of hydraulic fracturing three-dimensional in-situ stress through the actual inclination angle of the borehole is gradually becoming one of the key technologies in hydraulic fracturing engineering.

[0004] In the prior art, the borehole is usually assumed to be vertical or in a single direction, without considering the influence of the inclination angle of the borehole on the stress field of the rock mass. This problem leads to insufficient prediction accuracy of hydraulic fracturing in complex geological environments, especially in the exploitation process of unconventional oil and gas, which can cause inaccurate fracture propagation or hydraulic fracturing failure. Secondly, in the traditional technology, the measurement of hydraulic fracturing three-dimensional in-situ stress is usually based on limited empirical formulas or two-dimensional assumptions, which are difficult to fully consider the three-dimensional stress field, the mechanical properties of the rock mass, and the specific geometry of the borehole.

[0005] Therefore, it is necessary to propose a water pressure cracking three-dimensional stress calculation method considering the inclination angle of the drill hole to solve the problem.

[0006] The above information disclosed in the background section is only for the purpose of enhancing the understanding of the background of the present disclosure and, therefore, it can include information that does not constitute the prior art known to those of ordinary skill in the art. SUMMARY

[0007] The purpose of the present application is to provide a water pressure cracking three-dimensional stress calculation method considering the inclination angle of the drill hole to solve the problem proposed in the background.

[0008] To achieve the above-mentioned purpose, the present application provides the following technical solutions:

[0009] A water pressure cracking three-dimensional stress calculation method considering the inclination angle of the drill hole, the specific steps comprising:

[0010] Step 1: Collect relevant geological feature data, including the density, elastic modulus, Poisson's ratio, initial vertical stress, initial horizontal stress of the rock mass, and the inclination angle and drilling depth of the drill hole relative to the ground level;

[0011] Step 2: Combine the collected density, elastic modulus, and Poisson's ratio of the rock mass to generate the elastic stiffness index of the rock mass, use the obtained initial vertical stress and initial horizontal stress of the rock mass to generate the stress ratio index of the rock mass, and generate the inclination depth index according to the collected inclination angle and drilling depth of the drill hole, and combine the three generated indexes to generate a feature vector related to the rock mass;

[0012] Step 3: Establish a water pressure injection model, with the feature vector of the rock mass as the input and the water pressure cracking three-dimensional stress at the time of crack generation as the output, obtain the feature vector of the rock mass and the water pressure cracking three-dimensional stress in the rock mass drilling history data, input into the water pressure injection model, train the water pressure injection model, input the feature vector of the rock mass obtained in step 2 into the trained model to obtain the current water pressure cracking three-dimensional stress;

[0013] Step 4: Based on the water pressure cracking three-dimensional stress output by the model, combine the inclination angle of the drill hole, the pore water pressure generated by the rock mass, and the unit volume of water to calculate the vertical and horizontal stress on the rock mass, set the fracture threshold of the rock mass in the horizontal and vertical directions, judge whether the vertical and horizontal stress exceeds the corresponding threshold, if not, adjust the inclination angle of the drill hole until it exceeds the corresponding fracture threshold, and record the water pressure cracking three-dimensional stress at this time as the true measured value.

[0014] Further, the elastic stiffness index of the rock mass is generated by the following method:

[0015] The density, elastic modulus and Poisson's ratio of the rock mass are combined to generate an elastic stiffness index, which is used to represent the material condition of the rock mass, including its stiffness, strength and stability, according to the formula:

[0016]

[0017] wherein, represents the elastic stiffness index of the rock mass, is the elastic modulus of the rock mass, is the density of the rock mass, is the Poisson's ratio of the rock mass.

[0018] Further, a stress ratio index of the rock mass is generated according to the method:

[0019] The initial vertical stress and the initial horizontal stress of the rock mass are combined to generate a stress ratio index, which is used to represent the stress state of the rock mass, and further reflects its mechanical properties, according to the formula:

[0020]

[0021] wherein, represents the stress ratio index of the rock mass, are the initial vertical stress and the initial horizontal stress of the rock mass, respectively.

[0022] Further, a tilt depth index is generated according to the method:

[0023] According to the tilt angle and the drilling depth of the collected drill hole, a tilt depth index is generated, which is used to represent the mechanical properties and structural characteristics of the rock mass, and mainly reflects the directionality of the drill hole in the rock mass, the tilt degree of the rock structure, and the physical properties of the rock mass in this direction, according to the formula:

[0024]

[0025] wherein, represents the tilt depth index of the rock mass, is the drilling depth of the drill hole, is the tilt angle of the drill hole.

[0026] Further, a water pressure injection model is established according to the method:

[0027] The elastic stiffness index, the stress ratio index and the tilt depth index are combined to generate a feature vector related to the rock mass, and the feature vector related to the rock mass is used as the input of the model to predict the water pressure fracturing three-dimensional stress as the label.

[0028] ​​​​The water pressure injection model structure adopts a neural network convolution structure, including an input layer, a hidden layer and an output layer. The input layer is used to receive the processed feature vector. The hidden layer is used to process the feature vector. By applying multiple convolution kernels, the hidden layer can identify complex feature patterns. By using a ReLu activation function, a nonlinear relationship is introduced to enable the model to fit complex feature relationships. An independent neuron is arranged in the output layer, which is responsible for converting the local and high-level feature representations extracted by the hidden layer into the final prediction result, i.e., the predicted water pressure fracturing three-dimensional stress .

[0029] Further, based on the water pressure fracturing three-dimensional stress output by the model, the vertical and horizontal stress components on the rock mass are calculated by combining the inclination angle of the borehole, the pore water pressure generated by the rock mass and the unit volume of water. The method is as follows:

[0030] The water pressure fracturing three-dimensional stress obtained by the model output is decomposed into the vertical and horizontal stress components on the rock, and the pore water pressure in two directions is combined. The x-y-z coordinate system is established based on the working surface of the borehole, and the direction cosines l1, m1, n1 on the x-axis and the direction cosines l2, m2, n2 on the y-axis are calculated. The effective depth of the pore water pressure in the vertical and horizontal directions is combined to calculate the vertical and horizontal stress components of the pore water pressure in two directions. The formula is as follows:

[0031]

[0032] wherein x and y represent the direction cosines on the x-axis and the y-axis respectively, l1, m1 and n1 represent the direction cosine components of the x-axis on the x, y and z axes respectively, l2, m2 and n2 represent the direction cosine components of the y-axis on the x, y and z axes respectively, β0 is a reference direction, the angle relative to the x-y-z coordinate system, β1 is the angle of the borehole inclination angle θ relative to the reference direction β0, and α1 is the inclination angle of the pore water pressure on the y-axis;

[0033] Based on the calculated direction cosines on the x-axis and the y-axis, the effective depth of the pore water pressure in the vertical and horizontal directions and the unit volume of water are combined to calculate the vertical and horizontal stress components of the pore water pressure:

[0034] P1=γ*ε*n2=F sw *sinθ+γ*ε*cosα1

[0035] P2=γ*ε*[l2*m1+m2*l1]

[0036] Wherein, P1, P2 are vertical stress and horizontal stress of pore water pressure in two directions respectively; γ is the specific weight of water, ε is the effective depth of pore water pressure in x-y plane, θ is the inclination angle of the borehole.

[0037] The formula for calculating the vertical stress and horizontal stress of the borehole on the rock mass is:

[0038] f1=F sw *sinθ-{P1sin 2 (β0-β1)+P2cos 2 (β0–β1)-P1P2sin[2(β0-β1)]}sin 2 θ

[0039] f2=F sw *cosθ-{P2sin 2 (β0-β1)+P1cos 2 (β0–β1)-P1P2cos[2(β0-β1)]}cos 2 θ

[0040] Wherein, f1, f2 respectively represent the vertical stress and horizontal stress on the rock when the measured borehole is in the vertical direction, F sw is the predicted water pressure fracturing three-dimensional stress.

[0041] Further, the fracture threshold of the rock mass in the horizontal and vertical directions is set, and it is judged whether the vertical stress and horizontal stress exceed the corresponding threshold, if not, the inclination angle of the borehole needs to be adjusted until the corresponding fracture threshold is exceeded, and the logical formula is:

[0042] ;

[0043] Wherein, represents the logical judgment value of whether the vertical stress and horizontal stress exceed the corresponding threshold, 、 respectively represent the fracture threshold of the rock mass in the horizontal and vertical directions, when , it indicates that the vertical stress and horizontal stress do not exceed the corresponding fracture threshold, and the inclination angle of the borehole needs to be continuously adjusted until the corresponding fracture threshold is exceeded; when , it indicates that the vertical stress and horizontal stress exceed the corresponding fracture threshold, and the water pressure fracturing three-dimensional stress output by the model at this time is recorded as the measured value.

[0044] Compared with the prior art, the beneficial effects of the present application are:

[0045] The present application significantly improves the prediction accuracy of hydraulic fracturing three-dimensional ground stress by introducing geological feature data such as drilling inclination angle and drilling depth. Traditional hydraulic fracturing calculation methods often ignore the influence of the geometric shape of the borehole on stress distribution, while the present application comprehensively considers the physical properties of the rock mass and the spatial structure of the borehole by generating elastic stiffness index, stress ratio index and inclination depth index. This method can more accurately simulate the stress state and crack propagation of the rock mass, providing more reliable support for hydraulic fracturing in complex geological environments, thereby reducing engineering risks and improving geothermal energy and oil and gas extraction efficiency.

[0046] In addition, the present application uses a water pressure injection model based on a neural network convolution structure, combined with multi-dimensional geological feature data, so that the model can automatically identify and fit complex rock mass mechanical characteristics. This innovation enables the model to accurately predict hydraulic fracturing three-dimensional ground stress and dynamically adjust according to the prediction results and the fracture threshold to ensure that the stress of the rock mass in the horizontal and vertical directions reaches the fracture condition. Through this method, the drilling inclination angle can be optimized to improve the fracturing effect, ultimately providing a more accurate design scheme for hydraulic fracturing engineering, thereby improving engineering efficiency and safety.

[0047] The present application accurately predicts hydraulic fracturing three-dimensional ground stress using a neural network model by combining the physical properties of the rock mass and the geometric information of the borehole, thereby optimizing borehole design and improving the efficiency and safety of hydraulic fracturing engineering. BRIEF DESCRIPTION OF DRAWINGS

[0048] Figure 1 The present application is a schematic diagram of the overall method. DETAILED DESCRIPTION

[0049] To make the purpose, technical solutions and advantages of the present application clearer, the present application is further described in detail below with specific examples.

[0050] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present application should be understood as their usual meanings by those skilled in the art. The terms "first", "second" and similar words used in the present application do not represent any order, quantity or importance, but are used to distinguish different components. The terms "include" or "contain" and similar words mean that the elements or objects before the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. The terms "connect" or "connected" and similar words are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. The terms "up", "down", "left", "right" and the like are only used to represent relative positional relationships, which may change accordingly when the absolute position of the described object changes.

[0051] Embodiment:

[0052] Please refer to Figure 1 A water pressure fracturing three-dimensional stress calculation method considering the inclination angle of the borehole, the specific steps of which include:

[0053] Step 1: Collect relevant geological feature data, including the density, elastic modulus, Poisson's ratio, initial vertical stress, initial horizontal stress of the rock mass, and the inclination angle and drilling depth of the borehole relative to the ground level;

[0054] Step 2: Combine the collected density, elastic modulus, and Poisson's ratio of the rock mass to generate the elastic stiffness index of the rock mass, use the obtained initial vertical stress and initial horizontal stress of the rock mass to generate the stress ratio index of the rock mass, and generate the inclination depth index according to the collected inclination angle and drilling depth of the borehole, and combine the three generated indexes to generate a feature vector related to the rock mass;

[0055] Step 3: Establish a water pressure injection model, taking the feature vector of the rock mass as input and the water pressure fracturing three-dimensional stress at the time of crack generation as output, obtain the feature vector of the rock mass and the water pressure fracturing three-dimensional stress in the rock mass drilling history data, input into the water pressure injection model, train the water pressure injection model, input the feature vector of the rock mass obtained in step 2 into the trained model to obtain the current water pressure fracturing three-dimensional stress;

[0056] Step 4: Based on the water pressure fracturing three-dimensional stress output by the model, combine the inclination angle of the borehole, the pore water pressure generated by the rock mass, and the unit volume of water to calculate the vertical and horizontal stress on the rock mass, set the rock mass fracture threshold in the horizontal and vertical directions, and judge whether the vertical and horizontal stress exceeds the corresponding threshold, if not, adjust the inclination angle of the borehole until the corresponding fracture threshold is exceeded, and record the water pressure fracturing three-dimensional stress at this time as the true measured value.

[0057] It should be noted that by generating the elastic stiffness index of the rock mass, the stiffness, strength, and stability of the rock mass can be effectively represented, providing key parameters for the prediction of ground stress during hydraulic fracturing. By combining the density, elastic modulus, and Poisson's ratio of the rock mass, the mechanical properties of the rock mass can be more accurately reflected, providing a scientific basis for subsequent water pressure fracturing simulation and borehole design. The setting of this index helps to optimize the engineering application of the rock mass and ensures the safety and efficiency of hydraulic fracturing.

[0058] The method for obtaining each feature data is described here, including:

[0059] The density of the rock mass can be obtained by core sampling and laboratory analysis. First, core samples are obtained by drilling, and then the volume and mass of the samples are measured using precise weighing methods or the Archimedes principle to calculate the density of the rock mass;

[0060] The elastic modulus is usually obtained by seismic wave method or compression test in the laboratory. In the seismic wave method, the elastic modulus is calculated by measuring the seismic wave velocity using the formula. For the laboratory method, the stress-strain relationship of the rock sample can be determined by uniaxial or triaxial compression test, and then the elastic modulus is obtained;

[0061] The Poisson's ratio is obtained by experimentally measuring the ratio of lateral strain to longitudinal strain of the rock sample under compression. It is usually obtained by compression test, such as uniaxial compression test or triaxial compression test, to obtain the stress-strain curve, and then the Poisson's ratio is calculated by measuring the longitudinal and lateral strains;

[0062] The initial vertical stress is usually obtained by formation pressure test, such as pressure test in the borehole, using the formation pressure corresponding to the depth during drilling, combined with the density of the formation and the theory of gravity field, such as the mass distribution underground obtained by gravity measurement, to estimate the initial vertical stress;

[0063] The initial horizontal stress can be obtained by seismic reflection method, borehole test, such as stress release test, usually by directly measuring the stress in the borehole, or by microseismic monitoring and analysis in the rock formation, combined with existing geological structure analysis, to estimate the initial horizontal stress;

[0064] The inclination angle of the borehole relative to the ground level is usually measured by angle sensors on the drilling instrument or total station. During the drilling process, the inclination angle of the drill bit can be monitored in real time. The drilling depth can be determined by depth gauge or drill rod length, usually with automatic recording system to monitor the drilling depth in real time.

[0065] Therefore, it is necessary to generate the elastic stiffness index of the rock mass, and the method is as follows:

[0066] The density, elastic modulus and Poisson's ratio of the rock mass are combined to generate the elastic stiffness index, which is used to represent the material condition of the rock mass, including its stiffness, strength and stability, and the formula is as follows:

[0067] ;

[0068] wherein, E represents the elastic stiffness index of the rock mass, E represents the elastic modulus of the rock mass, D represents the density of the rock mass, The Poisson's ratio of the rock mass is given by the formula above. This index integrates the effects of the rock mass's elastic modulus, density, and Poisson's ratio, characterizing its mechanical properties. This index reflects the rock mass's stiffness, strength, and stability, and is therefore of great significance in geotechnical engineering, especially in analyzing the rock mass's response to external forces. The elastic stiffness index of the rock mass is also mentioned. With elastic modulus Proportional The larger, A higher elastic modulus generally indicates higher strength in rock masses. This means that the rock mass is better able to maintain its structural integrity and reduce the occurrence of cracks or failure when facing high pressure and high stress environments; the density of the rock mass... With elastic stiffness index Inversely proportional, The larger, A smaller Poisson's ratio indicates that a high-density rock mass may contain more heavy minerals or a dense granular structure. These materials may be relatively brittle and prone to fracture. High-density rock masses typically have a strong mass-sensing ability, meaning they can withstand greater stress and energy. However, higher density may also mean limited deformation capacity; their response to external forces may be biased towards fracturing or cracking rather than elastic deformation. When it increases, It will decrease because Poisson's ratio is related to the lateral deformation of the rock mass. The larger the Poisson's ratio, the easier it is for the rock mass to undergo greater lateral compression after being subjected to force, resulting in a smaller elastic modulus and thus a decrease in the overall stiffness of the rock mass.

[0069] The Poisson's ratio of the rock mass is mostly in the range of Between, when the Poisson ratio of the rock mass is large, that is, close to When the longitudinal deformation of the rock mass is relatively significant, the transverse deformation weakens its resistance to deformation when subjected to external forces, resulting in a lower elastic stiffness index. When the Poisson's ratio of the rock mass is small, it approaches a lower value. When the rock mass exhibits relatively small lateral deformation, it indicates that the rock mass can maintain a higher elastic modulus when subjected to tension or compression, meaning that the rock mass has high stiffness and therefore a large elastic stiffness index.

[0070] It should be noted that the calculation method of stress ratio index combines the initial vertical stress and initial horizontal stress of rock mass, and is used to describe the stress state of rock mass in different directions. The vertical stress is usually directly related to the weight of the stratum and external loading, while the horizontal stress reflects the geological structure, tectonic stress field and deformation characteristics of rock mass. The stress ratio index can effectively reflect the stress distribution of rock mass, and then affect its mechanical properties such as strength, deformation capacity and failure mode. By setting a reasonable stress ratio index, engineers can predict the behavior of rock mass under different stress environments, optimize the design, and avoid adverse deformation or failure, which has important practical significance, especially in underground engineering, geotechnical mechanics and earthquake engineering.

[0071] Therefore, it is necessary to generate the stress ratio index of rock mass, and the method is:

[0072] The stress ratio index is generated by combining the initial vertical stress and the initial horizontal stress of rock mass, and this index is used to characterize the stress state of rock mass, and then reflect its mechanical properties, and the formula is:

[0073] ;

[0074] Among them, represents the stress ratio index of rock mass, , are the initial vertical stress and the initial horizontal stress of rock mass respectively; in the above formula, the stress ratio index reflects the stress difference of rock mass in the vertical direction and the horizontal direction, and can reveal the mechanical behavior and stability of rock mass through different values.

[0075] When , it means that the stress of rock mass in the vertical direction and the horizontal direction is balanced, that is, the stress of rock mass in the two directions is equal. At this time, the failure mode of rock mass may be complex, because it is subjected to both vertical compression and horizontal tension or compression, which will produce complex stress concentration, such as some balanced tectonic state or in the case of surrounding rock stress close to uniform, the rock mass in this state may show uniform deformation cracking;

[0076] When , that is, the vertical stress of rock mass is greater than the horizontal stress, which means that the vertical compressive stress of rock mass is much greater than the horizontal stress. In this case, the deformation of rock mass is mainly dominated by vertical stress, which may lead to compressive failure of rock mass. In places with large vertical stress such as underground mining and tunnel engineering, this situation usually occurs. Under this stress condition, rock mass may easily appear vertical cracking or compression deformation, and special attention should be paid to the stability of surrounding rock;

[0077] When When the horizontal stress is greater than the vertical stress, it usually occurs in certain geological environments, such as in areas with strong tectonic stress or in areas with high groundwater pressure. The rock mass is subjected to stronger compressive stress in the horizontal direction, which may lead to horizontal damage or expansion. This state usually occurs in areas affected by tectonic deformation, fault activity or strong horizontal stress. The horizontal fracture or sliding of the rock mass may become the main form of damage, and special attention should be paid to the control of horizontal cracks and slip zones in engineering design.

[0078] It should be noted that the inclination depth index reflects the structural characteristics, inclination degree and physical properties of the rock mass by combining the drilling depth and inclination angle. This index not only quantitatively describes the inclination of the rock stratum, but also indirectly reveals the mechanical properties of the rock mass, such as strength and stability. It has important significance in geological exploration, mining and geotechnical engineering construction, and can optimize drilling programs, improve exploration accuracy and evaluate rock mass stability, thereby providing a scientific basis for engineering design and decision-making.

[0079] Therefore, it is necessary to generate an inclination depth index based on the following method:

[0080] According to the inclination angle and drilling depth of the collected borehole, an inclination depth index is generated to characterize the mechanical properties and structural characteristics of the rock mass. This index mainly reflects the directionality of the borehole in the rock mass, the inclination degree of the rock stratum structure, and the physical properties of the rock mass in that direction. The formula is:

[0081] ;

[0082] wherein, represents the inclination depth index of the rock mass, is the drilling depth of the borehole, is the inclination angle of the borehole; in the above formula, the inclination angle of the borehole reflects the angle between the borehole and the vertical direction, indicating that the borehole is inclined in a certain direction into the rock mass. When the borehole is drilled along the inclination direction of the rock stratum, the projection of the borehole depth on the horizontal plane will change with the increase of the angle. In the formula, the actual projection depth of the borehole depth in the rock mass is represented by , which accurately reflects the actual length of the borehole penetrating the rock mass; the inclination degree of the rock stratum directly affects the depth of the borehole penetrating the rock mass and its physical properties. In the case of large inclination, the actual vertical penetration depth of the borehole is shallow, , thereby reducing the calculated inclination depth index , indicating that the inclination degree of the rock mass is large and the penetration depth is small. Conversely, in the case of small, for example, close to vertical, The larger the index is, the deeper the vertical penetration of the borehole into the rock mass is, and the larger the inclination depth index is; the formula is The actual drilling depth of the borehole is represented, which directly reflects the degree of drilling into the rock mass. With the increase of the drilling depth, the number of penetrated rock layers increases, and the overall structural characteristics and mechanical properties of the rock mass can be more comprehensively reflected.

[0083] It should be noted that the structure of the water pressure injection model adopts a neural network convolution structure, mainly because convolutional neural networks perform well in processing data with spatial or structural characteristics, and can effectively extract local and high-level features from the input feature vectors. The input layer is responsible for receiving the processed feature vectors such as the elastic stiffness index, stress ratio index and inclination depth index, which reflect the mechanical properties and structural characteristics of the rock mass. The hidden layer can identify and capture complex feature patterns through convolution operations and the application of ReLu activation functions, and further establish a nonlinear relationship between the rock mass characteristics and the water pressure fracturing three-dimensional stress. The output layer converts the extracted features into the final prediction result, i.e. the water pressure fracturing three-dimensional stress, through an independent neuron. The design of this structure enables the model to have efficient feature extraction capability and strong prediction capability, thereby providing a reliable basis for stress prediction during water pressure injection.

[0084] Therefore, it is necessary to establish a water pressure injection model, and the method is:

[0085] The generated elastic stiffness index, stress ratio index and inclination depth index are combined to generate a feature vector related to the rock mass, and the feature vector related to the rock mass is used as the input of the model, and the predicted water pressure fracturing three-dimensional stress is used as the label.

[0086] The structure of the water pressure injection model adopts a neural network convolution structure, including an input layer, a hidden layer and an output layer, the input layer is responsible for receiving the processed feature vectors; the hidden layer is used for data processing of the feature vectors, and through the application of multiple convolution kernels, the hidden layer can identify complex feature patterns.

[0087] The feature vectors of the rock mass in the past drilling operations are obtained, and the water pressure fracturing three-dimensional stress is calculated based on the expert scoring of the inclination angle of the borehole and the related rock mass data. The feature vectors of the rock mass formed by the drilling operations in the history are used as the input, and the water pressure fracturing three-dimensional stress is used as the label to train the model. During the training process, the mean square error function is selected as the loss function, the loss function value is calculated according to the output result and the real label, and the gradient is calculated through the back propagation algorithm to update the weights and biases of the neural network. The above operation is repeated until the model reaches the predetermined training number of rounds.

[0088] The ReLu activation function is used during training to introduce nonlinearity, enabling the model to fit complex feature relationships. An independent neuron is added to the output layer to convert the local and high-level feature representations extracted by the hidden layers into the final prediction, which is the predicted hydraulic fracturing three-dimensional stress .

[0089] It is important to note that by decomposing the model output of the hydraulic fracturing three-dimensional stress into vertical and horizontal stresses on the rock mass, combined with the pore water pressure and the inclination angle of the borehole, an effective calculation framework is established. This framework uses direction cosines to quantify stresses and pressures in different directions, providing important theoretical basis for rock mass stability analysis, tunnel and shaft design, and groundwater resource management. The accuracy and scientific nature of this calculation method help engineers better assess the behavior of underground rock mass under water pressure and stress, improve engineering safety and construction efficiency, and ensure the successful implementation of underground engineering.

[0090] Therefore, based on the model output of the hydraulic fracturing three-dimensional stress, combined with the inclination angle of the borehole, the pore water pressure generated by the rock mass, and the unit volume of water, the vertical and horizontal stresses on the rock mass are calculated, and the method is as follows:

[0091] The hydraulic fracturing three-dimensional stress output by the model is decomposed into vertical and horizontal stresses on the rock, and combined with the pore water pressure in two directions, the x-y-z coordinate system is established based on the working surface of the borehole, the direction cosines l1, m1, n1 on the x-axis and l2, m2, n2 on the y-axis are calculated, and the effective depth of the pore water pressure in the vertical and horizontal directions is calculated to calculate the vertical and horizontal stresses of the pore water pressure in two directions. The formula is:

[0092]

[0093] where x and y represent the direction cosines on the x-axis and y-axis, respectively, l1, m1, n1 represent the direction cosine components of the x-axis on the x, y, z axes, respectively, l2, m2, n2 represent the direction cosine components of the y-axis on the x, y, z axes, respectively, β0 is a reference direction relative to the x-y-z coordinate system, β1 is the angle of the borehole inclination angle θ relative to the reference direction β0, and α1 is the inclination angle of the pore water pressure on the y-axis;

[0094] Based on the calculated direction cosines on the x-axis and y-axis, combined with the effective depth of the pore water pressure in the vertical and horizontal directions and the unit volume of water, the vertical and horizontal stresses of the pore water pressure are calculated:

[0095] P1 = γ * ε * n2 = F sw *sinθ+γ*ε*cosα1

[0096] P2 = γ * ε *[l2*m1+m2*l1]

[0097] Wherein, P1, P2 are the vertical stress and horizontal stress of pore water pressure in two directions respectively; γ is the specific weight of water, ε is the effective depth of pore water pressure in the x-y plane direction, θ is the inclination angle of the borehole; In the above formula, the direction cosines (l1, m1, n1) and (l2, m2, n2) can effectively decompose the force or stress in any direction to three coordinate axes, and this decomposition method can accurately calculate the stress and pressure in different directions, so as to reflect the real rock mass stress state; And the angle of the inclination angle θ of the borehole relative to the reference direction β0 is expressed by the direction cosine, which can capture the actual state of the borehole in different working surfaces, because the inclination of the borehole will directly affect the distribution of pore water pressure and the stress state of rock mass.

[0098] The formula for calculating the vertical stress and horizontal stress of the borehole on the rock mass is:

[0099] f1 = F sw *sinθ+γ*ε*cosα1 2 (β0-β1)+P2cos 2 (β0-β1)-P1P2sin[2(β0-β1)]}sin 2 θ

[0100] f2 = F sw *cosθ-{P2sin 2 (β0-β1)+P1cos 2 (β0-β1)-P1P2cos[2(β0-β1)]}cos 2 θ

[0101] Wherein, f1, f2 respectively represent the vertical stress and horizontal stress on the rock when the measured borehole is in the vertical direction, F swThis is the predicted three-dimensional geostress caused by hydraulic fracturing. It's important to note that setting the logical formula is crucial for determining whether the rock mass has reached the fracturing condition. By establishing fracturing thresholds F1 and F2 in the horizontal and vertical directions, it's possible to accurately determine whether the vertical and horizontal stress components exceed these thresholds during hydraulic fracturing. When Q = 0, it indicates that the stress has not exceeded the fracturing threshold, and the borehole inclination angle needs to be adjusted to optimize injection conditions until the threshold is exceeded. When Q = 1, it indicates that the stress exceeds the threshold, and the three-dimensional geostress caused by hydraulic fracturing at this point can be recorded as a measurement of rock mass fracturing. This logical judgment ensures precise control of the rock mass fracturing process, avoiding excessive or ineffective fracturing.

[0102] Therefore, it is necessary to establish fracture thresholds for the rock mass in the horizontal and vertical directions, and to determine whether the vertical and horizontal stress components exceed the corresponding thresholds. If they do not exceed the thresholds, the borehole inclination angle needs to be adjusted until the corresponding fracture threshold is exceeded. The underlying logic formula is as follows:

[0103] ;

[0104] in, This represents the logical judgment value used to determine whether the vertical and horizontal stress components exceed their corresponding thresholds. , These represent the fracture thresholds of the rock mass in the horizontal and vertical directions, respectively. When the vertical and horizontal stress components do not exceed the corresponding fracture thresholds, the borehole inclination needs to be adjusted further until it exceeds the corresponding fracture thresholds; when When the vertical and horizontal stress components exceed the corresponding fracturing thresholds, the hydraulic fracturing three-dimensional geostress output by the model at this time is recorded as the measured value; in the above logical formula, If any one of the fracture conditions is not met, the rock mass is considered not to have reached the fracture threshold. This is because, in practice, rock mass fracture is influenced by multiple stresses. When either the vertical or horizontal stress component fails to reach the fracture threshold, the rock mass as a whole may still remain in a relatively stable state. If the stress in only one direction fails to reach the fracture threshold, it indicates that the fracture conditions are not fully met. Therefore, it can be assumed that the borehole inclination angle should continue to be adjusted to optimize stress distribution until the stress in both directions reaches the fracture threshold. The stresses in both vertical and horizontal directions must be simultaneously satisfied, that is, the stresses in both vertical and horizontal directions exceed the respective breaking thresholds, to consider that the rock mass has been broken. This setting is because the rock mass breaking does not depend on the stress in a single direction, and the combined action of the vertical and horizontal stresses will lead to the breaking of the rock mass. When the stresses in both directions reach or exceed the breaking thresholds, it indicates that the rock mass is in a critical state of breaking, and the breaking has occurred. Therefore, only when the two stress conditions are satisfied at the same time, can it be considered that the rock mass has effectively broken, and then the three-dimensional in-situ stress caused by water pressure fracturing can be recorded.

[0105] The above formulas are dimensionless values calculated, and the formulas are obtained by software simulation of a large amount of data to obtain a formula closest to the actual situation. The preset parameters in the formula are set by a person skilled in the art according to the actual situation.

[0106] The above embodiments can be realized wholly or partially by software, hardware, firmware or any combination thereof. When realized by software, the above embodiments can be realized wholly or partially in the form of a computer program product. Those skilled in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized by hardware or software methods depends on the specific application and design constraints of the technical solutions.

[0107] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, which can be located in one place or distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiments.

[0108] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application.

Claims

1. A hydraulic fracturing three-dimensional stress calculation method considering a borehole inclination angle, characterized by, The specific steps include: Step 1: Collect relevant geological feature data, including the density, elastic modulus, Poisson's ratio, initial vertical stress, initial horizontal stress of the rock mass, and the inclination angle and drilling depth of the borehole relative to the ground level; Step 2: Combine the collected density, elastic modulus, and Poisson's ratio of the rock mass to generate an elastic stiffness index of the rock mass, use the obtained initial vertical stress and initial horizontal stress of the rock mass to generate a stress ratio index of the rock mass, and generate an inclination-depth index according to the collected inclination angle and drilling depth of the borehole, and combine the three generated indexes to generate a feature vector related to the rock mass; Step 3: Establish a water pressure injection model, with the feature vector of the rock mass as the input and the water pressure fracturing three-dimensional ground stress at the time of crack generation as the output, obtain the feature vector of the rock mass and the water pressure fracturing three-dimensional ground stress in the rock mass drilling history data, input them into the water pressure injection model, train the water pressure injection model, and input the feature vector of the rock mass obtained in step 2 into the trained model to obtain the current water pressure fracturing three-dimensional ground stress; Step 4: Based on the water pressure fracturing three-dimensional ground stress output by the model, combine the inclination angle of the borehole, the pore water pressure generated by the rock mass, and the unit volume of water to calculate the vertical and horizontal stress on the rock mass, set the rock mass fracture threshold in the horizontal and vertical directions, and judge whether the vertical and horizontal stress exceeds the corresponding threshold, if not, adjust the inclination angle of the borehole until it exceeds the corresponding fracture threshold, and record the water pressure fracturing three-dimensional ground stress at this time as the true measured value.

2. The water pressure cracking three-dimensional stress calculation method considering the drilling inclination angle according to claim 1, characterized in that, The method for generating the elastic stiffness index of the rock mass is: The elastic stiffness index is generated by combining the density, elastic modulus, and Poisson's ratio of the rock mass, which is used to represent the material condition of the rock mass, including its stiffness, strength, and stability, and the formula is: ; wherein, represents the elastic stiffness index of the rock mass, is the elastic modulus of the rock mass, is the density of the rock mass, is the Poisson's ratio of the rock mass.

3. The water pressure cracking three-dimensional stress calculation method considering the drilling inclination angle according to claim 1, characterized in that, The method for generating the stress ratio index of the rock mass is: The stress ratio index is generated by combining the initial vertical stress and initial horizontal stress of the rock mass, which is used to represent the stress state of the rock mass and reflect its mechanical properties, and the formula is: ; wherein, represents the stress ratio index of the rock mass, , are the initial vertical stress and the initial horizontal stress of the rock mass, respectively.

4. The water pressure cracking three-dimensional stress calculation method considering the drilling inclination angle according to claim 1, characterized in that, The method for generating the inclination-depth index is: According to the collected inclination angle and drilling depth of the borehole, an inclination-depth index is generated to represent the mechanical properties and structural characteristics of the rock mass, which mainly reflects the directionality of the borehole in the rock mass, the inclination degree of the rock layer structure, and the physical properties of the rock mass in that direction, and the formula is: ; wherein, represents the inclination depth index of the rock mass, is the drilling depth of the borehole, is the inclination angle of the borehole.

5. The water pressure cracking three-dimensional stress calculation method considering the drilling inclination angle according to claim 1, characterized in that, The method for establishing the water pressure injection model is: The generated elastic stiffness index, stress ratio index, and inclination-depth index are combined to generate a feature vector related to the rock mass, and the feature vector related to the rock mass is used as the input of the model, and the predicted water pressure fracturing three-dimensional ground stress is used as the label; The water pressure injection model structure adopts a neural network convolution structure, including an input layer, a hidden layer and an output layer. The input layer is used to receive the processed feature vector. The hidden layer is used to process the feature vector. By applying multiple convolution kernels, the hidden layer can identify complex feature patterns. By using a ReLu activation function, a non-linear relationship is introduced to enable the model to fit complex feature relationships. An independent neuron is set in the output layer, which is responsible for converting the local and high-level feature representations extracted by the hidden layer into the final prediction result, i.e., the predicted water pressure fracturing three-dimensional stress .

6. The water pressure cracking three-dimensional stress calculation method considering the drilling inclination angle according to claim 1, characterized in that The method for calculating the vertical and horizontal stress on the rock mass based on the water pressure fracturing three-dimensional ground stress output by the model, the inclination angle of the borehole, the pore water pressure generated by the rock mass, and the unit volume of water is: The water pressure fracturing three-dimensional stress obtained by model output is decomposed into vertical and horizontal stress on the rock, and the pore water pressure in two directions is combined to establish the formula for calculating the vertical and horizontal stress of pore water pressure in two directions, which is based on the drilling operation surface as the reference surface. The axial coordinate system is calculated The direction cosine on the axis With The direction cosine on the axis , combined with the effective depth of pore water pressure in the vertical and horizontal directions, to calculate the vertical and horizontal stress of pore water pressure in two directions, the formula is as follows: ; wherein, respectively represent the direction cosine of the axis respectively represent the direction cosine of the axis respectively represent the direction cosine of the axis , , respectively represent the direction cosine of the axis respectively represent the direction cosine of the axis respectively represent the direction cosine of the axis , , respectively represent the direction cosine of the axis respectively represent the direction cosine of the axis respectively represent the direction cosine of the axis is a reference direction, the angle of the axis coordinate system relative to the reference direction, is the angle of the borehole inclination relative to the reference direction , is the angle of the pore water pressure inclination relative to the reference direction Based on the calculated direction cosines on the axes, the direction cosines on the axes, and the effective depths of the pore water pressure in the vertical and horizontal directions and the specific weight of water per unit volume, the vertical and horizontal components of the pore water pressure are calculated: ; wherein, , are the vertical and horizontal principal stresses of the pore water pressure in two directions, respectively; is the unit weight of water, is the effective depth of the pore water pressure in the plane direction of , is the inclination angle of the borehole; The formula for calculating the vertical and horizontal stress of the borehole on the rock mass is: ; wherein, , respectively represent the vertical and horizontal components of stress on the rock when the measured borehole is vertical, is the predicted hydraulic fracturing 3D stress.

7. The water pressure cracking three-dimensional stress calculation method considering the drilling inclination angle according to claim 6, characterized in that, The rock mass is set up in horizontal and vertical direction of the breaking threshold, the vertical stress, the horizontal stress is judged whether to exceed the corresponding threshold, if not, the drilling angle needs to be adjusted until the corresponding breaking threshold is exceeded, the logical formula is: ; wherein, represents a logical judgment value of judging whether the vertical and horizontal principal stresses exceed the corresponding threshold values, , respectively represent the rock mass rupture threshold values in the horizontal and vertical directions, when , it indicates that the vertical and horizontal principal stresses do not exceed the corresponding rupture threshold values, and the drilling inclination angle needs to be continuously adjusted until the corresponding rupture threshold values are exceeded; when , it indicates that the vertical and horizontal principal stresses exceed the corresponding rupture threshold values, and the water pressure cracking three-dimensional stress output by the model at this time is recorded as the measured value.

Citation Information

Patent Citations

  • Oblique three-hole combined hydraulic fracturing ground stress testing method

    CN117432396A

  • Calculation method for measuring geostress through hydraulic fracturing

    CN117540134A