Experimental method and system for researching hydraulic fracturing crack propagation process

Abstract

The invention provides an experimental method and system for researching the hydraulic fracturing crack propagation process, and the method comprises the steps: employing a true triaxial stress simulation module to load stress in the X, Y and Z directions of a sample to simulate an in-situ stress state; a fluid injection control module is adopted to simulate the fluid injection process of the sample in actual fracturing construction; acquiring pressure data acquired by the pressure sensor array and acoustic emission data acquired by the acoustic emission probe; performing timestamp synchronization on the pressure data and the acoustic emission data, and performing feature extraction and time-space association on the pressure data and the acoustic emission data subjected to timestamp synchronization to obtain pressure dynamic response feature information and acoustic emission feature information meeting time-space association conditions; and based on the pressure dynamic response characteristic information and the acoustic emission characteristic information which meet the space-time correlation condition, performing crack propagation process identification on the sample. According to the method, the problem of synchronous association of pressure fluctuation and crack behaviors under the multi-field coupling condition can be solved.

Description

Technical Field

[0001] The present application relates to the technical field of hydraulic fracturing, and in particular to an experimental method and system for studying the hydraulic fracturing crack expansion process. Background Art

[0002] Hydraulic fracturing is a commonly used method of underground hydrological structural transformation. Its principle is to use high-pressure water to expand rock cracks, use groundwater pressure to expand the cracks and pump water into them. Hydraulic fracturing can expand rock cracks, making originally impermeable formations permeable. Therefore, hydraulic fracturing is widely used in fields such as oil development, coal mining and geothermal energy development. Summary of the invention

[0003] The embodiments of the present application provide an experimental method and system for studying the hydraulic fracturing crack propagation process, which can solve the problem of synchronous correlation between pressure fluctuations and crack behaviors under multi-field coupling conditions.

[0004] According to a first aspect of an embodiment of the present application, an experimental method for studying a hydraulic fracturing crack expansion process is provided, comprising: A true triaxial stress simulation module is used to load stress in the X, Y, and Z directions of the sample to simulate the in-situ stress state; wherein the sample has a built-in pressure sensor array, the pressure sensor array is used to monitor the pressure change of the fluid at the crack mouth, and at least a plurality of acoustic emission probes are arranged on each of the multiple surfaces of the sample, and the acoustic emission probes are used to monitor the acoustic emission data of the crack extension; Using a fluid injection control module to simulate the fluid injection process in actual fracturing construction for the sample; Acquiring pressure data collected by the pressure sensor array and acoustic emission data collected by the acoustic emission probe; The pressure data and the acoustic emission data are time-stamp synchronized, and feature extraction is performed on the pressure data and the acoustic emission data that have been time-stamp synchronized, respectively, to obtain pressure dynamic response feature information and acoustic emission feature information; Performing spatiotemporal correlation on the pressure dynamic response characteristic information and the acoustic emission characteristic information to obtain the pressure dynamic response characteristic information and the acoustic emission characteristic information that satisfy the spatiotemporal correlation conditions; Based on the pressure dynamic response characteristic information and acoustic emission characteristic information that meet the time-space correlation conditions, the crack extension process of the sample is identified.

[0005] According to a second aspect of an embodiment of the present application, an experimental system for studying a hydraulic fracturing crack expansion process is provided, comprising: A true triaxial stress simulation module is used to apply stresses in the X, Y, and Z directions of a specimen to simulate the in-situ stress state. Among them, a pressure sensor array is built in the specimen, and the pressure sensor array is used to monitor the change of fluid pressure at the crack opening. At least a plurality of acoustic emission probes are arranged on each of the multiple surfaces of the specimen, and the acoustic emission probes are used to monitor the acoustic emission data of crack propagation. A fluid injection control module is used to simulate the fluid injection process in actual fracturing construction for the specimen. A data processing module is used to obtain the pressure data collected by the pressure sensor array and the acoustic emission data collected by the acoustic emission probes, synchronize the time stamps of the pressure data and the acoustic emission data, respectively extract features from the pressure data and the acoustic emission data after time stamp synchronization to obtain pressure dynamic response feature information and acoustic emission feature information, perform spatio-temporal correlation on the pressure dynamic response feature information and the acoustic emission feature information to obtain pressure dynamic response feature information and acoustic emission feature information that meet the spatio-temporal correlation conditions, and based on the pressure dynamic response feature information and acoustic emission feature information that meet the spatio-temporal correlation conditions, identify the crack propagation process of the specimen.

[0006] According to the third aspect of the embodiments of the present application, a storage medium is provided. The storage medium stores instructions, and when the instructions are executed by a processor, the processor is caused to execute the method described in the first aspect above.

[0007] According to the technical solution of the present application, the hydraulic fracturing crack propagation process can be simulated with high precision, the dynamic response characteristics of fluid pressure can be monitored in real time. By synchronizing the time stamps of the pressure data and the acoustic emission data, and performing spatio-temporal correlation on the pressure dynamic response feature information and the acoustic emission feature information, the synchronous correlation problem between pressure fluctuations and crack behavior under multi-field coupling conditions can be solved, and the accuracy and reliability of identifying the hydraulic fracturing crack propagation process can be improved. In addition, the modular analysis process can be adapted to different reservoir types and fracturing processes, which can significantly enhance the engineering transformation value of experimental data.

[0008] The additional aspects and advantages of the present application will be partially given in the following description, partially become obvious from the following description, or be understood through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] The above and / or additional aspects and advantages of the present application will become obvious and easy to understand from the following description of the embodiments in conjunction with the drawings, where: Figure 1 is a schematic diagram of an experimental system for studying the hydraulic fracturing crack propagation process provided by an embodiment of the present application; Figure 2An exemplary diagram of pressure monitoring and acoustic emission monitoring provided by an embodiment of the present application; Figure 3 A schematic flow chart of an experimental method for studying the process of hydraulic fracture propagation provided by an embodiment of the present application. Detailed implementation manners

[0010] The embodiments of the present application will be described in detail below. The examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals represent the same or similar elements or elements with the same or similar functions from beginning to end. The embodiments described below by referring to the accompanying drawings are exemplary and are intended to explain the present application, and should not be construed as a limitation to the present application.

[0011] An experimental method and system for studying the process of hydraulic fracture propagation according to an embodiment of the present application will be described below with reference to the accompanying drawings.

[0012] Figure 1 A schematic diagram of an experimental system for studying the process of hydraulic fracture propagation provided by an embodiment of the present application. As Figure 1 shown, the experimental system for studying the process of hydraulic fracture propagation may include, but is not limited to: a true triaxial stress simulation module 101, a fluid injection control module 102, and a data processing module 103.

[0013] Among them, the true triaxial stress simulation module 101 is used to apply stresses in the X, Y, and Z directions of the specimen (for example, the value range of the stress can be 0-100 MPa, but is not limited thereto) to simulate the in-situ stress state. Among them, a pressure sensor array may be built in the specimen A, and the pressure sensor array can be used to monitor the change of fluid pressure at the crack mouth. At least a plurality of acoustic emission probes may be arranged on each of the multiple surfaces of the specimen A, and the acoustic emission probes can be used to monitor the acoustic emission data of crack propagation. The fluid injection control module 102 can be used to simulate the fluid injection process in actual fracturing construction for the specimen. A hydraulic fracturing experiment is carried out on the specimen through the true triaxial stress simulation module 101 and the fluid injection control module 102.

[0014] In some embodiments, the specimen may be a rock specimen. For example, it may be a coal mine rock specimen. The experimental system of the embodiment of the present application can be applied to the field of coal mine mining, but is not limited thereto. Exemplarily, the size of the specimen may be 400 mm × 400 mm × 400 mm, but is not limited thereto. In some embodiments, as Figure 1 shown, an experimental pressure pillow B may be arranged between the true triaxial stress simulation module 101 and the surface of the specimen A. The experimental pressure pillow B may be a variable device filled with gas inside, and the experimental pressure pillow B can be used to ensure that the stress applied to the surface of the specimen A is a uniform stress, avoiding stress loading errors caused by the non-absolutely flat surface of the specimen.

[0015] In some embodiments, as Figure 2 shown, a perforation channel can be preset at the center of specimen A, and a micro pressure sensor array C (for example, the sampling frequency is greater than or equal to 1000 Hz) can be built-in to monitor the change of fluid pressure at the crack opening in real time. The built-in micro pressure sensor array can ensure that the monitored fluid pressure is the pressure at the crack opening, avoiding errors such as pipeline friction in the fluid pressure data monitored by external sensors.

[0016] Exemplarily, the pressure sensor array can adopt a micro high-frequency piezoresistive or fiber optic pressure sensor, with a range of 0 - 100 MPa, a sampling frequency ≥ 1000 Hz, a resolution ≤ 0.1 MPa, and a size ≤ 1 mm × 1 mm × 0.5 mm (miniaturized design). The specimen can be processed into a 400×400×400 mm cube, and a perforation channel with a diameter of 2 mm is pre-drilled at the center to simulate the actual wellbore perforation structure. The pressure sensor array can be arranged in the specimen based on a preset radial arrangement and layered distribution; among them, the design of the radial arrangement is as follows: centered on the perforation channel, arranged along the preset crack propagation direction, with a spacing of the first length, covering the first area; the design of the layered distribution is as follows: buried in layers around the perforation channel, with a spacing of the second length between each layer; the pressure sensor array is embedded inside the specimen through precision drilling and epoxy resin encapsulation technology.

[0017] For example, the array arrangement of the pressure sensor array can be as follows: (1) Radial arrangement: Centered on the perforation channel, arranged along the preset crack propagation direction (usually the minimum horizontal principal stress direction), with a spacing of 2 mm, covering an area with a radius of 10 mm. (2) Layered distribution: Buried in layers around the perforation channel (such as 3 layers × 5 columns), with a spacing of 3 mm between each layer to achieve three-dimensional pressure monitoring. Through precision drilling and epoxy resin encapsulation technology, the pressure sensor is embedded inside the specimen to ensure that the surface of the sensor is flush with the inner wall of the specimen, which can avoid stress concentration interference.

[0018] In some embodiments, the monitoring data of the pressure sensor array can be collected synchronously through multiple channels. Exemplarily, a high-speed data acquisition card is adopted, which supports 32-channel parallel acquisition, and the sampling rate synchronization accuracy ≤ 1 μs. The original signal can be processed by a low-noise amplifier and an anti-aliasing filter (such as a cut-off frequency of 500 Hz) to eliminate high-frequency noise.

[0019] In some embodiments, the acoustic emission probe can be a broadband acoustic emission sensor, with a frequency response range of 50 kHz - 1 MHz, a sensitivity greater than or equal to 80 dB, and supporting three-dimensional positioning; the acoustic emission probe can be fixed on the surface of the specimen by magnetic attraction or adhesives, and a coupling agent is applied to the contact surface with the specimen.

[0020] Exemplarily, as Figure 2As shown, acoustic emission probes D can be arranged on the six surfaces of the specimen, with at least two acoustic emission probes set on each surface to form a three-dimensional monitoring network. Based on the time difference of the acoustic emission signals reaching each acoustic emission probe and combined with the geometric parameters of the specimen, the coordinates of the crack event can be calculated (accuracy ±1 mm).

[0021] It should be noted that in the embodiments of the present application, the fluid injection control module 102 is a core component of the experimental system for studying the process of hydraulic fracture propagation. It can be used to accurately simulate the fluid injection process in actual fracturing construction, support various injection modes (such as constant rate, pulse, stepped pressure increase, etc.) and real-time regulation of fluid viscosity to study the dynamic response of fluid pressure during fracture propagation under different working conditions. Exemplarily, the core functions of the fluid injection control module 102 may include: ① Multi-mode fluid injection: accurately control the flow rate, pressure and injection timing sequence.

[0022] ② Dynamic viscosity adjustment: adjust the rheological properties of the fracturing fluid in real time according to experimental requirements.

[0023] ③ Data synchronization and feedback: cooperate with the pressure sensor and the acoustic emission system to achieve closed-loop control.

[0024] In some embodiments, the fluid injection control module 102 can adopt a constant rate injection mode to simulate the fluid injection process in actual fracturing construction for the specimen. Among them, the control logic of this constant rate injection mode can be: set the target flow rate (such as 10 mL / min), and the servo motor adjusts the plunger displacement speed through closed-loop feedback to compensate for the pressure fluctuation caused by fracture propagation in real time. Combine the feedback of the flow meter with this target flow rate to adjust the motor speed to correct the flow error.

[0025] In the embodiments of the present application, the data processing module 103 can be used to: obtain the pressure data collected by the pressure sensor array and the acoustic emission data collected by the acoustic emission probes; synchronize the time stamps of the pressure data and the acoustic emission data, and respectively extract the features of the pressure data and the acoustic emission data after time stamp synchronization to obtain the pressure dynamic response feature information and the acoustic emission feature information; perform spatio-temporal correlation on the pressure dynamic response feature information and the acoustic emission feature information to obtain the pressure dynamic response feature information and the acoustic emission feature information that meet the spatio-temporal correlation conditions; based on the pressure dynamic response feature information and the acoustic emission feature information that meet the spatio-temporal correlation conditions, identify the process of crack propagation in the specimen.

[0026] That is to say, a hydraulic fracturing experiment can be performed on the specimen through the true triaxial stress simulation module and the fluid injection control module. During this hydraulic fracturing experiment, the data processing module 103 can acquire the pressure data collected by the pressure sensor array in the specimen and the acoustic emission data collected by the acoustic emission probe, and perform data preprocessing and time synchronization on the pressure data and the acoustic emission data. Then, feature extraction and spatio-temporal correlation are respectively performed on the pressure data and the acoustic emission data. The pressure dynamic response feature information and the acoustic emission feature information that meet the spatio-temporal correlation conditions can be obtained. Furthermore, based on the pressure dynamic response feature information and the acoustic emission feature information that meet the spatio-temporal correlation conditions, the crack propagation process and the behavior pattern of the crack propagation process of the specimen in the future time can be predicted.

[0027] In some embodiments, an optional implementation manner for data preprocessing of the pressure data is as follows: denoising processing and baseline correction are performed on the pressure data. Exemplarily, wavelet transform (such as Daubechies 5) can be used to perform denoising processing on the pressure data to filter out high-frequency noise and retain the effective pressure fluctuation signal. The purpose of performing baseline correction on the pressure data can be to eliminate the pressure baseline offset caused by temperature drift or system error and ensure the accuracy of the absolute pressure value.

[0028] In some embodiments, an optional implementation manner for data preprocessing of the acoustic emission data is as follows: event screening is performed on the acoustic emission data based on the energy threshold, duration, and frequency characteristics, and positioning calibration is performed on the acoustic emission data. Exemplarily, the acoustic emission data with energy greater than or equal to the energy threshold (such as 40 dB), duration within the preset time range (such as 10 μs to 1 ms), and frequency characteristics within the preset frequency range (such as the main frequency being 50 to 500 kHz) can be retained, so as to eliminate the interference of ambient noise. Exemplarily, the optional implementation manner for performing positioning calibration on the acoustic emission data is as follows: the positioning accuracy of the acoustic emission event can be verified through an artificial lead break test at a known position (error ≤ ±1 mm).

[0029] In some embodiments, the optional implementation manner for synchronizing the timestamps of the pressure data and the acoustic emission data is as follows: GPS or IEEE 1588 protocol (PTP) can be used to perform global clock synchronization on the pressure data and the acoustic emission data to ensure that the time error between the pressure sensor and the acoustic emission system is ≤1 ms. Based on the fluid injection start signal as a reference, the start times of all data acquisition devices are synchronized to achieve the purpose of trigger alignment.

[0030] In some embodiments, the above-mentioned pressure dynamic response characteristic information may include the sudden drop amplitude of the pressure sudden drop point, the peak pressure gradient, and the fluctuation frequency. Among them, the pressure sudden drop point may refer to a pressure drop ≥ 5 MPa within a continuous time window (the time window Δt ≤ 10 ms), which can be defined as a crack tip breakthrough or bifurcation event. The peak pressure gradient may refer to the maximum value of the pressure difference between adjacent sensors (such as ΔP / Δx ≥ 10 MPa / mm, where ΔP is the pressure difference and Δx is the displacement), which can be defined as the crack propagation direction and rate. The fluctuation frequency can be determined based on the periodic fluctuation data in the pressure data. By analyzing the main frequency (such as 1 - 10 Hz) and the amplitude spectrum energy distribution through FFT, the periodic fluctuation can be identified, and this periodic fluctuation can be defined as the response of pulse injection or intermittent crack propagation.

[0031] In some embodiments, the above-mentioned acoustic emission characteristic information may include the event density, the energy accumulation rate, and the main frequency distribution. Among them, the event density can be determined based on the event coordinates (X, Y, Z) and the occurrence time in the acoustic emission data. Exemplarily, the acoustic emission data of each acoustic emission event may include the event coordinates, the occurrence time (t), the energy (E), and the main frequency (f). The acoustic emission events can be clustered based on the DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithm to identify micro-crack clusters. The DBSCAN algorithm can define a cluster as the largest set of density-connected points, capable of dividing regions with sufficient high density into clusters, and can discover clusters of any shape in a spatial database with noise, thereby distinguishing between main crack events and branch crack events. That is to say, the event density can represent the event coordinates, the occurrence time, and the specific crack event (such as the main crack event or the branch crack event). The energy accumulation rate can be determined based on the occurrence time and energy of the acoustic emission events in the acoustic emission data. The main frequency distribution can be determined based on the main frequency of the acoustic emission events in the acoustic emission data.

[0032] In the embodiments of the present application, the optional implementation manner of performing spatio-temporal association on the pressure dynamic response characteristic information and the acoustic emission characteristic information to obtain the pressure dynamic response characteristic information and the acoustic emission characteristic information that meet the spatio-temporal association conditions is as follows: Set a sliding time window, associate the pressure sudden drop point with the acoustic emission events within the sliding time window, and calculate the correlation coefficient between the pressure dynamic response characteristic information and the acoustic emission characteristic information; Project the acoustic emission event coordinates to the peak pressure gradient region to verify the spatial consistency of the crack propagation path; Based on the correlation coefficient and the verification result of the spatial consistency, obtain the pressure dynamic response characteristic information and the acoustic emission characteristic information that meet the spatio-temporal association conditions; Among them, meeting the spatio-temporal association conditions includes that the correlation coefficient is greater than or equal to a preset value, and the verification result of the spatial consistency is consistent.

[0033] Exemplarily, a sliding time window can be set (e.g., the sliding time window Δt = 20 ms), the pressure sudden drop point is associated with the acoustic emission events within the window, the correlation coefficient between the pressure dynamic response characteristic information and the acoustic emission characteristic information is calculated through the Pearson correlation coefficient, and the acoustic emission event coordinates are projected onto the pressure gradient peak region to verify the spatial consistency of the crack propagation path, thereby realizing the spatio-temporal correlation of pressure-acoustic emission and breaking through the limitations of a single data source. The pressure dynamic response characteristic information and the acoustic emission characteristic information with a correlation coefficient greater than or equal to a preset value (e.g., 0.7, determined as a strong correlation) and a consistent verification result of spatial consistency are determined as the pressure dynamic response characteristic information and the acoustic emission characteristic information that meet the spatio-temporal correlation conditions, that is, they can be used for the identification of the crack propagation process.

[0034] In some embodiments, an intelligent dynamic criterion can be performed based on a machine learning-based crack propagation prediction model to provide real-time decision support for the fracturing construction. Exemplarily, the pressure dynamic response characteristic information and the acoustic emission characteristic information that meet the spatio-temporal correlation conditions can be input into a pre-trained crack propagation prediction model to obtain the crack propagation process (such as a main crack event or a branch crack event) within a future time and the behavior pattern of the crack propagation process (such as crack branching, turning, or stable propagation mode, etc.). Among them, the crack propagation prediction model can be a joint model based on an LSTM network and a random forest classifier, and the classification accuracy of the random forest classifier can be greater than or equal to 88%. Optionally, when training the crack propagation prediction model, 100 sets of experimental data can be used (70% for training and 30% for testing), and cross-validation is performed to prevent overfitting. The crack propagation prediction model can be verified based on the energy release rate and combined with the acoustic emission cumulative energy (ΣE). The calculation formula of the energy release rate can be as follows: , where is the crack volume, with the unit of mm 3 ; is the crack area, with the unit of mm 2 ; is the pressure change value, with the unit of MPa. For example, the energy release rate can be calculated based on the pressure change value, the crack volume, and the crack area at the previous moment, and the crack propagation process at the next moment (whether it is a main crack or a branch crack) can be calculated based on the energy release rate combined with the acoustic emission cumulative energy, and the result is compared with the prediction result of the crack propagation prediction model to verify the accuracy of the crack propagation prediction model.

[0035] In the above embodiments, the process of hydraulic fracturing crack propagation can be simulated with high precision, and the dynamic response characteristics of fluid pressure can be monitored in real time. By synchronizing the pressure data and acoustic emission data with timestamps and correlating the pressure dynamic response characteristic information and acoustic emission characteristic information in space and time, the problem of synchronous correlation between pressure fluctuations and crack behavior under multi-field coupling conditions can be solved, and the accuracy and reliability of identifying the process of hydraulic fracturing crack propagation can be improved. In addition, the modular analysis process can be adapted to different reservoir types and fracturing processes, which can significantly enhance the engineering conversion value of experimental data.

[0036] Figure 3 FIG. is a schematic flow chart of an experimental method for studying the process of hydraulic fracturing crack propagation provided by an embodiment of the present application. It should be noted that the execution subject of the experimental method in the embodiment of the present application can be the data processing module in the experimental system involved in any of the above embodiments. As Figure 3 shown, the experimental method for studying the process of hydraulic fracturing crack propagation may include, but is not limited to, the following steps.

[0037] In step 301, a true triaxial stress simulation module is used to apply stresses in the X, Y, and Z directions of the specimen to simulate the in-situ stress state.

[0038] Among them, in the embodiments of the present application, a pressure sensor array is built in the specimen, and the pressure sensor array is used to monitor the change of fluid pressure at the crack mouth. At least a plurality of acoustic emission probes are arranged on each of the multiple surfaces of the specimen, and the acoustic emission probes are used to monitor the acoustic emission data of crack propagation.

[0039] In some embodiments, the specimen may be a rock specimen. Exemplarily, the size of the specimen may be 400 mm × 400 mm × 400 mm, but is not limited thereto. In some embodiments, as Figure 1 shown, an experimental pressure pillow B may be arranged in the middle of the surface of the true triaxial stress simulation module 101 and the specimen A. The experimental pressure pillow B may be a variable device filled with gas inside, and the experimental pressure pillow B may be used to ensure that the stress applied to the surface of the specimen A is a uniform stress, avoiding stress loading errors caused by the non-absolutely flat surface of the specimen.

[0040] In some embodiments, as Figure 2 shown, a perforation channel may be preset in the center of the specimen A, and a micro pressure sensor array C (for example, the sampling frequency is greater than or equal to 1000 Hz) is built in to monitor the change of fluid pressure at the crack mouth in real time. The built-in micro pressure sensor array can ensure that the monitored fluid pressure is the pressure at the crack mouth, avoiding errors such as pipeline friction in the fluid pressure data monitored by external sensors.

[0041] Exemplarily, the pressure sensor array can adopt a micro high-frequency piezoresistive or fiber optic pressure sensor, with a measurement range of 0 to 100 MPa, a sampling frequency ≥ 1000 Hz, a resolution ≤ 0.1 MPa, and a size ≤ 1 mm × 1 mm × 0.5 mm (miniaturized design). The specimen can be processed into a 400×400×400 mm cube, with a pre-drilled perforation channel with a diameter of 2 mm in the center to simulate the actual wellbore perforation structure. The pressure sensor array can be arranged in the specimen based on a preset radial arrangement and layered distribution; among them, the radial arrangement is designed as follows: centered on the perforation channel, arranged along the preset crack propagation direction, with a spacing of the first length, covering the first area; the layered distribution is designed as follows: buried in layers around the perforation channel, with a spacing of the second length between each layer; the pressure sensor array is embedded inside the specimen through precision drilling and epoxy resin encapsulation technology.

[0042] For example, the array arrangement of the pressure sensor array can be as follows: (1) Radial arrangement: Centered on the perforation channel, arranged along the preset crack propagation direction (usually the minimum horizontal principal stress direction), with a spacing of 2 mm, covering an area with a radius of 10 mm. (2) Layered distribution: Buried in layers around the perforation channel (such as 3 layers × 5 columns), with a spacing of 3 mm between each layer to achieve three-dimensional pressure monitoring. Through precision drilling and epoxy resin encapsulation technology, the pressure sensor is embedded inside the specimen to ensure that the surface of the sensor is flush with the inner wall of the specimen, which can avoid stress concentration interference.

[0043] In some embodiments, a multi-channel synchronous acquisition can be used to collect the monitoring data of the pressure sensor array. Exemplarily, a high-speed data acquisition card is adopted, which supports 32-channel parallel acquisition, and the sampling rate synchronization accuracy ≤ 1 μs. The original signal can be processed through a low-noise amplifier and an anti-aliasing filter (such as a cut-off frequency of 500 Hz) to eliminate high-frequency noise.

[0044] In some embodiments, the acoustic emission probe can be a broadband acoustic emission sensor, with a frequency response range of 50 kHz to 1 MHz, a sensitivity greater than or equal to 80 dB, and supports three-dimensional positioning; the acoustic emission probe can be fixed on the surface of the specimen by magnetic attraction or adhesives, and a coupling agent is applied to the contact surface with the specimen.

[0045] Exemplarily, as Figure 2 shown, acoustic emission probes can be arranged on 6 surfaces of the specimen, with at least 2 acoustic emission probes arranged on each surface to form a spatial three-dimensional monitoring network. The coordinates of the crack event can be calculated (accuracy ± 1 mm) based on the time difference of the acoustic emission signals reaching each acoustic emission probe, combined with the geometric parameters of the specimen.

[0046] In step 302, a fluid injection control module is used to simulate the fluid injection process in actual fracturing construction for the specimen.

[0047] It should be noted that in the embodiments of the present application, the fluid injection control module is the core component of the experimental system for studying the process of hydraulic fracturing crack propagation. It can be used to accurately simulate the fluid injection process in actual fracturing construction, support various injection modes (such as constant rate, pulse, stepped pressurization, etc.) and real-time regulation of fluid viscosity to study the dynamic response of fluid pressure during crack propagation under different working conditions. Exemplarily, the core functions of the fluid injection control module may include: ① Multi-mode fluid injection: precisely control the flow rate, pressure, and injection timing.

[0048] ② Dynamic viscosity adjustment: adjust the rheological properties of the fracturing fluid in real time according to experimental requirements.

[0049] ③ Data synchronization and feedback: cooperate with the pressure sensor and acoustic emission system to achieve closed-loop control.

[0050] In some embodiments, the fluid injection control module can adopt a constant rate injection mode to simulate the fluid injection process in actual fracturing construction for the specimen. Among them, the control logic of this constant rate injection mode can be: set the target flow rate (such as 10 mL / min), and the servo motor adjusts the plunger displacement speed through closed-loop feedback, compensating for the pressure fluctuations caused by crack propagation in real time. Combining the feedback of the flow meter with this target flow rate, the motor speed is adjusted to correct the flow error.

[0051] In step 303, the pressure data collected by the pressure sensor array and the acoustic emission data collected by the acoustic emission probe are obtained.

[0052] In step 304, the pressure data and the acoustic emission data are time-stamped synchronized, and feature extraction is respectively performed on the pressure data and the acoustic emission data that have been time-stamped synchronized to obtain the pressure dynamic response feature information and the acoustic emission feature information.

[0053] In some embodiments, before time-stamping synchronization of the pressure data and the acoustic emission data, data preprocessing can be performed on the pressure data and the acoustic emission data. In some embodiments, the optional implementation methods for data preprocessing of the pressure data are as follows: denoising processing and baseline correction are performed on the pressure data. Exemplarily, wavelet transform (such as Daubechies 5) can be used to perform denoising processing on the pressure data to filter out high-frequency noise and retain the effective pressure fluctuation signal. The purpose of performing baseline correction on the pressure data can be to eliminate the pressure baseline offset caused by temperature drift or system error to ensure the accuracy of the absolute pressure value.

[0054] In some embodiments, an alternative implementation of data preprocessing for acoustic emission data is as follows: Event screening is performed on the acoustic emission data based on energy threshold, duration, and frequency characteristics, and positioning calibration is performed on the acoustic emission data. Exemplarily, acoustic emission data with energy greater than or equal to the energy threshold (e.g., 40 dB), duration within a preset time range (e.g., 10 μs to 1 ms), and frequency characteristics within a preset frequency range (e.g., main frequency of 50 to 500 kHz) can be retained, thereby eliminating environmental noise interference. Exemplarily, the alternative implementation of the above positioning calibration for acoustic emission data is as follows: The positioning accuracy of acoustic emission events (error ≤ ±1 mm) can be verified through an artificial lead break test at a known location.

[0055] In some embodiments, the alternative implementation of the above timestamp synchronization of pressure data and acoustic emission data is as follows: GPS or IEEE 1588 protocol (PTP) can be used to perform global clock synchronization on the pressure data and acoustic emission data to ensure that the time error between the pressure sensor and the acoustic emission system is ≤1 ms. Based on the fluid injection start signal as a reference, the start time of all data acquisition devices is synchronized to achieve the purpose of trigger alignment.

[0056] In some embodiments, the above pressure dynamic response characteristic information may include the drop amplitude at the pressure drop point, the peak pressure gradient, and the fluctuation frequency. Among them, the pressure drop point may refer to a pressure drop of ≥5 MPa within a continuous time window (time window Δt ≤ 10 ms), which can be defined as a crack tip breakthrough or bifurcation event. The peak pressure gradient may refer to the maximum value of the pressure difference between adjacent sensors (e.g., ΔP / Δx ≥ 10 MPa / mm, ΔP is the pressure difference, and Δx is the displacement), which can be defined as the crack propagation direction and rate. The fluctuation frequency can be determined based on the periodic fluctuation data in the pressure data. By analyzing the main frequency (e.g., 1 - 10 Hz) and the amplitude spectrum energy distribution through FFT, periodic fluctuations can be identified, and this periodic fluctuation can be defined as the response to pulse injection or crack intermittent propagation.

[0057] In some embodiments, the above acoustic emission characteristic information may include event density, energy accumulation rate, and dominant frequency distribution. Among them, the event density may be determined based on the event coordinates (X, Y, Z) and occurrence time in the acoustic emission data. Exemplarily, the acoustic emission data of each acoustic emission event may include event coordinates, occurrence time (t), energy (E), and dominant frequency (f). The acoustic emission events may be clustered based on the DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithm to identify micro-fracture clusters. The DBSCAN algorithm can define a cluster as the largest set of density-connected points, capable of dividing regions with sufficient high density into clusters and discovering clusters of arbitrary shapes in a spatial database with noise, thereby distinguishing between main crack events and branch crack events. That is to say, the event density can represent the event coordinates, occurrence time, and specific crack events (such as main crack events or branch crack events). The energy accumulation rate may be determined based on the occurrence time and energy of the events in the acoustic emission data. The dominant frequency distribution may be determined based on the dominant frequency of the acoustic emission events in the acoustic emission data.

[0058] In step 305, the pressure dynamic response characteristic information and the acoustic emission characteristic information are spatio-temporally correlated to obtain the pressure dynamic response characteristic information and the acoustic emission characteristic information that meet the spatio-temporal correlation conditions.

[0059] In some embodiments, a sliding time window is set, the pressure drop points are associated with the acoustic emission events within the sliding time window, and the correlation coefficient between the pressure dynamic response characteristic information and the acoustic emission characteristic information is calculated; the acoustic emission event coordinates are projected onto the pressure gradient peak region to verify the spatial consistency of the crack propagation path; based on the correlation coefficient and the verification result of the spatial consistency, the pressure dynamic response characteristic information and the acoustic emission characteristic information that meet the spatio-temporal correlation conditions are obtained; among them, meeting the spatio-temporal correlation conditions includes that the correlation coefficient is greater than or equal to a preset value, and the verification result of the spatial consistency is consistent.

[0060] Exemplarily, a sliding time window may be set (such as the sliding time window Δt = 20 ms), the pressure drop points are associated with the acoustic emission events within the window, the correlation coefficient between the pressure dynamic response characteristic information and the acoustic emission characteristic information is calculated through the Pearson correlation coefficient, and the acoustic emission event coordinates are projected onto the pressure gradient peak region to verify the spatial consistency of the crack propagation path, thereby realizing the spatio-temporal correlation of pressure-acoustic emission and breaking through the limitations of a single data source. The pressure dynamic response characteristic information and the acoustic emission characteristic information with a correlation coefficient greater than or equal to a preset value (such as 0.7, determined as a strong correlation) and a consistent verification result of the spatial consistency are determined as the pressure dynamic response characteristic information and the acoustic emission characteristic information that meet the spatio-temporal correlation conditions, that is, they can be used for the identification of the crack propagation process.

[0061] In step 306, based on the pressure dynamic response feature information and acoustic emission feature information that meet the spatio-temporal correlation conditions, the crack propagation process of the specimen is identified.

[0062] In some embodiments, an intelligent dynamic criterion can be performed based on a machine learning-based crack propagation prediction model to provide real-time decision support for the fracturing construction. Exemplarily, the pressure dynamic response feature information and acoustic emission feature information that meet the spatio-temporal correlation conditions can be input into a pre-trained crack propagation prediction model to obtain the crack propagation process (such as main crack events or branch crack events) within a future time and the behavior pattern of the crack propagation process (such as crack branching, turning, or stable propagation mode, etc.). Among them, the crack propagation prediction model can be a joint model based on an LSTM network and a random forest classifier, and the classification accuracy of the random forest classifier can be greater than or equal to 88%. Optionally, when training the crack propagation prediction model, 100 sets of experimental data can be used (70% for training and 30% for testing), and cross-validation can be performed to prevent overfitting. The crack propagation prediction model can be verified based on the energy release rate and combined with the acoustic emission cumulative energy (ΣE). The calculation formula of the energy release rate can be as follows: , where is the crack volume, with the unit of mm 3 ; is the crack area, with the unit of mm 2 ; is the pressure change value, with the unit of MPa. For example, the energy release rate can be calculated based on the pressure change value, crack volume, and crack area at the previous moment, and the crack propagation process at the next moment (whether it is a main crack or a branch crack) can be calculated based on the energy release rate combined with the acoustic emission cumulative energy, and the result can be compared with the prediction result of the crack propagation prediction model to verify the accuracy of the crack propagation prediction model.

[0063] According to the experimental method of the embodiments of the present application, the hydraulic fracturing crack propagation process can be simulated with high precision, the dynamic response characteristics of the fluid pressure can be monitored in real time, and by synchronizing the pressure data and acoustic emission data with timestamps and correlating the pressure dynamic response feature information and acoustic emission feature information spatio-temporally, the synchronous correlation problem between pressure fluctuations and crack behavior under multi-field coupling conditions can be solved, and the accuracy and reliability of the identification of the hydraulic fracturing crack propagation process can be improved. In addition, different reservoir types and fracturing processes can be adapted through a modular analysis process, which can significantly enhance the engineering conversion value of experimental data.

[0064] To implement the above embodiments, the present application further provides a storage medium, which can store instructions. When the instructions are executed by a processor (such as the processor in the data processing module), the processor is caused to execute the experimental method provided by the present application for studying the process of hydraulic fracture propagation. The non-transitory computer-readable storage medium of the present application stores computer instructions, and the computer instructions are used to cause a computer to execute the experimental method provided by the present application for studying the process of hydraulic fracture propagation.

[0065] In the description of this specification, the descriptions referring to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples" mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, without conflict, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0066] In the description of the present application, the meaning of "a plurality" is at least two, such as two, three, etc., unless otherwise specifically and clearly defined.

[0067] Any process or method description in the flowchart or described in other ways herein can be understood to represent a module, segment, or part of code including one or more executable instructions for implementing a customized logic function or process. The scope of the preferred embodiments of the present application includes additional implementations, where the functions can be executed in a manner that is not shown or discussed in the order, including in a substantially simultaneous manner according to the functions involved or in the reverse order, which should be understood by those skilled in the art to which the embodiments of the present application belong.

[0068] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a definite sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or used in combination with these instruction execution systems, apparatus, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection portion with one or more wirings (electronic device), a portable computer diskette (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or other suitable processing as necessary, and then stored in a computer memory.

[0069] It should be understood that various parts of the present application can be implemented by hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application-specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), and the like.

[0070] Those of ordinary skill in the art of this technology can understand that all or part of the steps carried by the method of implementing the above embodiments can be completed by instructing relevant hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiments.

[0071] In addition, each functional unit in various embodiments of the present application may be integrated into one processing module, or each unit may exist physically alone, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. When the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0072] The above-mentioned storage medium may be a read-only memory, a magnetic disk, an optical disc, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present application. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. An experimental method for studying the hydraulic fracturing crack propagation process, characterized in that: include: A true triaxial stress simulation module is used to load stress in the X, Y, and Z directions of the sample to simulate the in-situ stress state; wherein the sample has a built-in pressure sensor array, the pressure sensor array is used to monitor the pressure change of the fluid at the crack mouth, and at least a plurality of acoustic emission probes are arranged on each of the multiple surfaces of the sample, and the acoustic emission probes are used to monitor the acoustic emission data of the crack extension; Using a fluid injection control module to simulate the fluid injection process in actual fracturing construction for the sample; Acquiring pressure data collected by the pressure sensor array and acoustic emission data collected by the acoustic emission probe; The pressure data and the acoustic emission data are time-stamp synchronized, and feature extraction is performed on the pressure data and the acoustic emission data that have been time-stamp synchronized, respectively, to obtain pressure dynamic response feature information and acoustic emission feature information; Performing spatiotemporal correlation on the pressure dynamic response characteristic information and the acoustic emission characteristic information to obtain the pressure dynamic response characteristic information and the acoustic emission characteristic information that satisfy the spatiotemporal correlation conditions; Based on the pressure dynamic response characteristic information and acoustic emission characteristic information that meet the time-space correlation conditions, the crack extension process of the sample is identified.

2. The method according to claim 1, characterized in that The fluid injection control module is used to simulate the fluid injection process in actual fracturing construction on the sample, including: The fluid injection control module is controlled to adopt a constant speed injection mode to simulate the fluid injection process in actual fracturing construction for the sample; wherein the control logic of the constant speed injection mode includes: a servo motor adjusts the plunger displacement speed through closed-loop feedback, compensates for pressure fluctuations caused by crack expansion in real time, and adjusts the motor speed through flow meter feedback combined with a set target flow to correct the flow error.

3. The method according to claim 1, characterized in that Before synchronizing the pressure data and the acoustic emission data with timestamps, the method further includes: performing denoising and baseline correction on the pressure data; and / or, Event screening is performed on the acoustic emission data based on energy threshold, duration and frequency characteristics, and positioning calibration is performed on the acoustic emission data.

4. The method according to claim 1, characterized in that: The pressure dynamic response characteristic information includes the sudden drop amplitude, pressure gradient peak value and fluctuation frequency at the pressure sudden drop point, and the acoustic emission characteristic information includes event density, energy accumulation rate and main frequency distribution; The step of performing spatiotemporal correlation on the pressure dynamic response characteristic information and the acoustic emission characteristic information to obtain the pressure dynamic response characteristic information and the acoustic emission characteristic information satisfying the spatiotemporal correlation condition includes: Setting a sliding time window, associating the pressure drop point with the acoustic emission event within the sliding time window, and calculating a correlation coefficient between the pressure dynamic response characteristic information and the acoustic emission characteristic information; The coordinates of the acoustic emission events were projected onto the pressure gradient peak area to verify the spatial consistency of the crack propagation path; Based on the verification results of the correlation coefficient and spatial consistency, pressure dynamic response characteristic information and acoustic emission characteristic information that meet the time-space correlation conditions are obtained; wherein, the time-space correlation conditions are met including that the correlation coefficient is greater than or equal to a preset value, and the verification result of the spatial consistency is consistent.

5. The method according to any one of claims 1 to 4, characterized in that The method of identifying the crack extension process of the sample based on the pressure dynamic response characteristic information and the acoustic emission characteristic information that satisfy the time-space correlation condition includes: Inputting the pressure dynamic response characteristic information and acoustic emission characteristic information satisfying the time-space correlation conditions into a pre-trained crack extension prediction model to obtain the crack extension process in the future and the behavior pattern of the crack extension process; Among them, the crack extension prediction model is a joint model based on LSTM network and random forest classifier.

6. An experimental system for studying the hydraulic fracturing crack expansion process, characterized in that: include: A true triaxial stress simulation module is used to apply stress in the X, Y, and Z directions of the sample to simulate the in-situ stress state; wherein the sample has a built-in pressure sensor array, the pressure sensor array is used to monitor the pressure change of the fluid at the crack mouth, and at least a plurality of acoustic emission probes are arranged on each of the multiple surfaces of the sample, and the acoustic emission probes are used to monitor the acoustic emission data of the crack extension; A fluid injection control module, used to simulate the fluid injection process in actual fracturing construction for the sample; A data processing module is used to obtain the pressure data collected by the pressure sensor array and the acoustic emission data collected by the acoustic emission probe, and synchronize the pressure data and the acoustic emission data with timestamps, and respectively extract features from the pressure data and the acoustic emission data that have been synchronized with timestamps to obtain pressure dynamic response characteristic information and acoustic emission characteristic information, perform spatiotemporal correlation on the pressure dynamic response characteristic information and the acoustic emission characteristic information to obtain pressure dynamic response characteristic information and acoustic emission characteristic information that meet spatiotemporal correlation conditions, and identify the crack extension process of the sample based on the pressure dynamic response characteristic information and the acoustic emission characteristic information that meet the spatiotemporal correlation conditions.

7. The system according to claim 6, characterized in that An experimental pressure pillow is arranged between the true triaxial stress simulation module and the surface of the sample. The experimental pressure pillow is a variable device filled with gas. The experimental pressure pillow is used to ensure that the stress loaded on the surface of the sample is uniform stress.

8. The system according to claim 6, characterized in that A perforation channel is preset in the center of the sample, and the pressure sensor array is arranged in the sample based on a preset radial arrangement and a layered distribution array; wherein the radial arrangement is designed as follows: with the perforation channel as the center, the pressure sensors are arranged along a preset crack extension direction, with a first length of spacing, and covering a first area; the layered distribution is designed as follows: the pressure sensors are buried in layers around the perforation channel, with a second length of spacing between each layer; The pressure sensor array is embedded in the sample through precision drilling and epoxy resin packaging technology.

9. The system according to claim 6, characterized in that The acoustic emission probe is a wide-band acoustic emission sensor with a frequency response range of 50 kHz to 1 MHz, a sensitivity greater than or equal to 80 dB, and supports three-dimensional positioning; the acoustic emission probe is fixed to the surface of the sample by magnetism or adhesive, and a coupling agent is applied to the contact surface with the sample.

10. A storage medium storing instructions, characterized in that: When the instructions are executed by a processor, the processor is caused to perform the method according to any one of claims 1 to 5.

Images