Rock liquid nitrogen fracturing monitoring method

Through the combination of sensor and multi-channel data acquisition system, high-precision and real-time monitoring of the liquid nitrogen fracturing process are achieved, solving the problems of low accuracy and slow response of traditional monitoring methods, and significantly improving the monitoring of liquid nitrogen fracturing technology Effect and process optimization capabilities.

CN118933711AInactive Publication Date: 2024-11-12CHINA UNIV OF MINING & TECH (BEIJING)
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202410907608.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-08
Publication Date
2024-11-12
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

During liquid nitrogen fracturing, the temperature, stress and crack expansion inside the rock changes complex and rapidly, and traditional monitoring methods are difficult to monitor accurately in real time, and there are problems of low accuracy and slow response.

Method used

Using sensors, multi-channel data acquisition systems, high-speed signal transmission, real-time data processing algorithms, comprehensive data analysis and display, dynamic parameter adjustment, automatic alarm and recording technologies, the high accuracy of internal changes in rocks during liquid nitrogen fracturing, Real-time monitoring and processing.

Benefits of technology

Through efficient data acquisition and transmission systems, the rapid transmission and processing of real-time monitoring data is guaranteed. Combined with machine learning and adaptive filters, the data processing accuracy and speed are improved, and intuitive monitoring information and dynamic parameter adjustment are provided to timely detect and handle abnormalities. The situation has significantly improved the monitoring effect and process optimization capabilities of liquid nitrogen fracturing technology.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118933711A_ABST
    Figure CN118933711A_ABST
Patent Text Reader

Abstract

The invention discloses a rock liquid nitrogen fracturing monitoring method, and particularly relates to the field of oil and gas exploitation and mineral exploitation, and the method comprises the following steps: S1, arranging temperature, stress and acoustic emission sensors on the surface and in the interior of a rock; s2, designing and installing a multi-channel data acquisition system, and receiving and processing data from a plurality of sensors at the same time; s3, transmitting the sensor data to a data processing center by adopting a signal transmission technology; by applying the technologies of a sensor, a multi-channel data acquisition system, high-speed signal transmission, a real-time data processing algorithm, comprehensive data analysis and display, dynamic parameter adjustment, automatic alarm and recording and the like, the liquid nitrogen fracturing process is optimized through dynamic parameter adjustment, and the fracturing effect is ensured; the automatic alarming and recording system timely discovers and processes abnormal conditions, detailed data support is provided, reliable guarantee is provided for subsequent analysis and process optimization, and the monitoring effect and the process optimization capability of the liquid nitrogen fracturing technology are remarkably improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the fields of oil and gas exploitation and mineral exploitation, and more particularly to a monitoring method for rock liquid nitrogen fracturing. Background Art

[0002] Liquid nitrogen fracturing technology is an emerging rock fracturing method that uses extremely low-temperature liquid nitrogen to induce the expansion of internal cracks in rocks, thereby increasing oil and gas well production and mineral mining efficiency. Traditional hydraulic fracturing methods have problems such as environmental pollution, high water consumption, and poor geological adaptability. Liquid nitrogen fracturing, due to its environmental protection and low-temperature effects, can induce thermal stress cracks and is suitable for special geological environments. However, during the liquid nitrogen fracturing process, the temperature, stress, and crack expansion inside the rock change complexly and rapidly. Traditional monitoring methods are difficult to monitor accurately in real time, and have problems such as low accuracy and slow response. Therefore, a high-precision, real-time monitoring system is urgently needed to overcome these technical difficulties and ensure the efficiency and safety of the liquid nitrogen fracturing process. In order to solve these problems, a monitoring method for liquid nitrogen fracturing of rocks is proposed to solve the above problems. Summary of the invention

[0003] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a monitoring method for liquid nitrogen fracturing of rocks. By applying sensors, multi-channel data acquisition systems, high-speed signal transmission, real-time data processing algorithms, comprehensive data analysis and display, dynamic parameter adjustment, and automatic alarm and recording technologies, high-precision, real-time monitoring and processing of internal changes in rocks during liquid nitrogen fracturing are achieved, ensuring the comprehensiveness and accuracy of monitoring data; through an efficient data acquisition and transmission system, the rapid transmission and processing of real-time monitoring data are guaranteed; the real-time data processing algorithm combined with machine learning and adaptive filters improves the accuracy and speed of data processing; the comprehensive data analysis and display technology provides intuitive and comprehensive monitoring information, which is convenient for users to understand the changes in real time; dynamic parameter adjustment optimizes the liquid nitrogen fracturing process and ensures the fracturing effect; the automatic alarm and recording system promptly detects and handles abnormal situations, provides detailed data support, and provides reliable guarantees for subsequent analysis and process optimization, significantly improving the monitoring effect and process optimization capabilities of liquid nitrogen fracturing technology.

[0004] To achieve the above object, the present invention provides the following technical solution: a monitoring method for rock liquid nitrogen fracturing, characterized in that: the monitoring method for rock liquid nitrogen fracturing comprises the following steps:

[0005] S1: Arrange temperature, stress and acoustic emission sensors on the surface and inside of the rock;

[0006] S2: Design and install a multi-channel data acquisition system to simultaneously receive and process data from multiple sensors;

[0007] S3: Use signal transmission technology to transmit sensor data to the data processing center;

[0008] S4: Process data using real-time data based on machine learning;

[0009] S5: Integrate and analyze various monitoring data, and display temperature, stress and acoustic emission signals in real time through a graphical user interface;

[0010] S6: Dynamically adjust liquid nitrogen fracturing parameters according to real-time monitoring data;

[0011] S7: Set alarm thresholds for key parameters, automatically alarm when the thresholds are exceeded, and record all monitoring data and analysis results.

[0012] In a preferred embodiment: in step S1, temperature sensors are evenly installed at intervals of 0.5 meters on the rock surface; the temperature sensor measures temperature changes, T=T0+k·ΔT, where T is the measured temperature, T0 is the initial temperature, k is the sensor sensitivity coefficient, and ΔT is the temperature change; a stress sensor is installed at intervals of 1 meter on the rock surface; the stress sensor measures stress changes: σ=E·, where σ is stress, E is the elastic modulus, and is strain; an acoustic emission sensor is arranged at intervals of 1 meter on the rock; the acoustic emission sensor monitors the acoustic wave signal of crack generation and expansion: V(t)=Asin(2πft+ ), where V(t) is the acoustic emission signal, A is the amplitude, f is the frequency, t is the time, and is the initial phase.

[0013] In a preferred embodiment: In step S2, the analog front end amplifies and filters the sensor output analog signal: V out =G·V in ; Among them, V out is the amplified output signal, G is the amplification factor, V in The sensor input signal; the analog-to-digital converter (ADC) converts the analog signal into a digital signal: Where D is the digital output, V ref+ and V ref- are the positive and negative terminals of the reference voltage respectively, and n is the number of ADC bits.

[0014] In a preferred embodiment: in step S3, optical fiber communication or high-speed wireless communication technology is used to transmit the collected data to the data processing center in real time. Optical fiber communication utilizes the high bandwidth and low latency characteristics of optical fiber to quickly transmit data: Among them, C is the communication capacity, B is the bandwidth, S is the signal power, and N is the noise power. Wireless communication uses high-speed wireless communication technologies such as 5G or Wi-Fi6 to ensure the real-time and stability of data transmission: Among them, T is the transmission time, L is the data length, and R is the transmission rate.

[0015] In a preferred embodiment: In step S4, a real-time data processing algorithm based on machine learning and an adaptive filter are combined to improve data processing accuracy and response speed, and a support vector machine (SVM) is used for classification and regression analysis to improve signal recognition accuracy: Among them, w is the weight vector, b is the bias, ξ i is a slack variable, C is a penalty parameter; convolutional neural network is used to extract signal features and analyze internal changes in rocks: f(x) = σ(W*x+b), where x is the input signal, W is the convolution kernel, * represents the convolution operation, b is the bias, and σ is the activation function; adaptive filter: Kalman filter is used to dynamically estimate the signal state and filter out noise: in, is the estimated state, K k is the Kalman gain, z k is the measured value, H k is the measurement matrix; the adaptive gradient descent method is used to dynamically adjust the filter parameters and optimize the signal processing effect: Among them, θ t is a parameter, η is the learning rate, is the gradient of the loss function.

[0016] In a preferred embodiment: in step S5, a variety of monitoring data are integrated and analyzed, and temperature, stress and acoustic emission signals are displayed in real time through a graphical user interface; data integration: using a database management system to store and manage data from different sensors: D = {d1, d2, ..., d n},in, is the data set, d i is a single data entry; graphical interface: using data visualization technology, the analysis results are displayed in a graphical manner, graph = f(D), where the graph is the visualization result of the data set D, and f is the visualization function.

[0017] In a preferred embodiment: in step S6, the injection pressure and rate are adjusted using real-time data to achieve the best fracturing effect: Where P is the injection pressure, R is the injection rate, and J is the optimization objective function.

[0018] In a preferred embodiment: in step S7, if any monitoring parameter X of temperature, stress or acoustic emission signal exceeds its set threshold value X th , then trigger the alarm, Among them, X is the monitoring parameter, X this the alarm threshold; automatically records all monitoring data and analysis results: R = {D1, D2, ..., D m}, where R is the record data set, D i For data from a single monitoring cycle; anomaly detection algorithms based on statistics and machine learning are used to identify anomalies in the data and trigger alarms. Statistical method: If the z-score Z of a data point exceeds the set threshold Z th , then the data point is considered abnormal: Among them, Z is z-score, X is data point ′ μ is the mean value of the data, σ is the standard deviation of the data; if the anomaly score of a data point x in the isolation forest algorithm exceeds the set threshold, the data point is considered abnormal: the isolation forest algorithm constructs multiple random trees, and the number of steps to isolate the data point is used as the anomaly score. Data points with high scores are considered to be abnormal points; if the anomaly score S(x) exceeds the set threshold, the data point is considered abnormal: Where E(h(x)) is the average path length of data point x in the random tree, and c(n) is a constant for the size of the data set. All monitoring data and analysis results are stored in the database to support playback and detailed analysis of historical data, helping to optimize fracturing processes and decisions. The data storage is represented by: S = {R1, R2, …, R n},in, To store the data set, R i is the recorded data of different time periods; the data playback formula is as follows: P(t) = {R t}, where P(t) is the data playback result at time t, R t is the recorded data at time t.

[0019] The technical effects and advantages of the present invention are as follows: by applying sensors, multi-channel data acquisition systems, high-speed signal transmission, real-time data processing algorithms, comprehensive data analysis and display, dynamic parameter adjustment, and automatic alarm and recording technologies, high-precision, real-time monitoring and processing of internal changes in rocks during liquid nitrogen fracturing are achieved, ensuring the comprehensiveness and accuracy of monitoring data; through an efficient data acquisition and transmission system, rapid transmission and processing of real-time monitoring data are guaranteed; a real-time data processing algorithm combining machine learning and adaptive filters improves the accuracy and speed of data processing; comprehensive data analysis and display technology provides intuitive and comprehensive monitoring information, making it easy for users to understand changes in real time; dynamic parameter adjustment optimizes the liquid nitrogen fracturing process and ensures the fracturing effect; the automatic alarm and recording system promptly detects and handles abnormal situations, provides detailed data support, and provides reliable guarantees for subsequent analysis and process optimization, significantly improving the monitoring effect and process optimization capability of liquid nitrogen fracturing technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 It is a schematic diagram of the working steps of the present invention. DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0022] An exemplary embodiment will now be described more fully with reference to the accompanying drawings, a monitoring method for rock liquid nitrogen fracturing, the monitoring method for rock liquid nitrogen fracturing comprising the following steps: S1: arranging temperature, stress and acoustic emission sensors on the surface and inside of the rock; S2: designing and installing a multi-channel data acquisition system to simultaneously receive and process data from multiple sensors; S3: using signal transmission technology to transmit sensor data to a data processing center; S4: using real-time data processing based on machine learning; S5: integrating and analyzing a variety of monitoring data, and displaying temperature, stress and acoustic emission signals in real time through a graphical user interface ; S6: Dynamically adjust liquid nitrogen fracturing parameters according to real-time monitoring data; S7: Set the alarm threshold of key parameters, automatically alarm when exceeding the threshold, and record all monitoring data and analysis results; In step S1, temperature sensors are evenly installed at intervals of 0.5 meters on the rock surface; the temperature sensor measures temperature changes, T = T0 + k·ΔT, where T is the measured temperature, T0 is the initial temperature, k is the sensor sensitivity coefficient, and ΔT is the temperature change; a stress sensor is installed at intervals of 1 meter on the rock surface; the stress sensor measures stress changes: σ = E·, where σ is stress, E is the elastic modulus, and is strain; an acoustic emission sensor is arranged at intervals of 1 meter on the rock; the acoustic emission sensor monitors the acoustic wave signal of crack generation and expansion: V(t) = Asin(2πft+ ), where V(t) is the acoustic emission signal, A is the amplitude, f is the frequency, t is the time, and is the initial phase; the temperature sensor monitors the temperature distribution inside the rock by measuring temperature changes. The measurement principle of the temperature sensor is based on its sensitivity coefficient. When the temperature changes, the sensor will generate corresponding electrical signal changes. Stress sensors calculate stress changes by measuring strain, and the relationship between stress and strain is determined by the elastic modulus of the rock. Acoustic emission sensors determine the formation and expansion of cracks by monitoring the sound wave signals emitted when cracks are generated and expanded. The amplitude and frequency changes of the sound wave signals can reflect the activity of the cracks.

[0023] Next, in step S2, the analog front end amplifies and filters the sensor output analog signal: V out =GV in ; Among them, Vout is the amplified output signal, G is the amplification factor, V in The sensor input signal; the analog-to-digital converter (ADC) converts the analog signal into a digital signal: Where D is the digital output, V ref+ and V ref- are the positive and negative terminals of the reference voltage, and n is the number of ADC bits. In order to achieve the synchronous acquisition and processing of multiple sensor data, a multi-channel data acquisition system needs to be designed and installed. The system includes an analog front end, an analog-to-digital converter, a data buffer, and a microcontroller. The analog front end amplifies and filters the analog signal output by the sensor to improve the quality and reliability of the signal. The analog-to-digital converter converts the amplified analog signal into a digital signal. The working principle of the analog-to-digital converter is to convert the input signal into a corresponding digital value within a set range through the change of the reference voltage. The data buffer is used to temporarily store the converted digital signal to prevent data loss or transmission delay. The microcontroller is responsible for processing and managing the data in the buffer, including data transmission and storage. The amplification factor of the analog front end determines the gain of the signal, and the design of the filter ensures the purity of the signal and eliminates the influence of environmental noise on the measurement results. The resolution and sampling rate of the analog-to-digital converter determine the accuracy and real-time performance of the digital signal, and the capacity of the buffer and the processing power of the microcontroller ensure the stability and reliability of the system under high data flow.

[0024] Next, in step S3, optical fiber communication or high-speed wireless communication technology is used to transmit the collected data to the data processing center in real time. Optical fiber communication uses the high bandwidth and low latency characteristics of optical fiber to quickly transmit data: Among them, C is the communication capacity, B is the bandwidth, S is the signal power, and N is the noise power. Wireless communication uses high-speed wireless communication technologies such as 5G or Wi-Fi6 to ensure the real-time and stability of data transmission: Among them, T is the transmission time, L is the data length, and R is the transmission rate; in the process of liquid nitrogen fracturing, in order to ensure the real-time transmission and processing of monitoring data, high-speed signal transmission technology is required. Optical fiber communication and high-speed wireless communication technology are two main options. Optical fiber communication uses the high bandwidth and low latency characteristics of optical fiber to achieve rapid data transmission. The working principle of optical fiber communication is the transmission of optical signals. The transmission speed of optical signals is close to the speed of light, with large bandwidth, large data transmission, and low latency, which is suitable for real-time data transmission. High-speed wireless communication technologies such as 5G or Wi-Fi6 transmit data through radio waves, with high transmission rate and low latency. The working principle of high-speed wireless communication is to send and receive radio signals through antennas, use frequency modulation and demodulation technology to convert digital signals into radio signals for transmission, and then convert them back to digital signals. The rate of signal transmission determines the efficiency of data transmission, while the transmission distance and environmental conditions affect the quality and stability of the signal. In liquid nitrogen fracturing monitoring, the use of high-speed signal transmission technology can ensure that sensor data can be transmitted to the data processing center in real time to meet the needs of real-time monitoring and analysis.

[0025] Then, in step S4, a real-time data processing algorithm based on machine learning and an adaptive filter are combined to improve data processing accuracy and response speed, and a support vector machine (SVM) is used for classification and regression analysis to improve signal recognition accuracy: Among them, w is the weight vector, b is the bias, ξ i is a slack variable, C is a penalty parameter; convolutional neural network is used to extract signal features and analyze internal changes in rocks: f(x) = σ(W*x+b), where x is the input signal, W is the convolution kernel, * represents the convolution operation, b is the bias, and σ is the activation function; adaptive filter: Kalman filter is used to dynamically estimate the signal state and filter out noise: in, is the estimated state, K k is the Kalman gain, z k is the measured value, H k is the measurement matrix; the adaptive gradient descent method is used to dynamically adjust the filter parameters and optimize the signal processing effect: Among them, θ t is a parameter, η is the learning rate, is the gradient of the loss function; in order to improve the processing accuracy and response speed of monitoring data, it is necessary to combine real-time data processing algorithms based on machine learning and adaptive filters. The application of machine learning algorithms such as support vector machines and convolutional neural networks in data processing can improve the recognition accuracy and feature extraction capabilities of signals. Support vector machines are an algorithm used for classification and regression analysis. By constructing hyperplanes to classify data, support vector machines can accurately identify normal data and abnormal data when processing rock internal change data. Convolutional neural networks are used to extract signal features. Through multi-layer convolution and pooling operations, convolutional neural networks can extract multiple features of rock internal changes and improve the accuracy of data analysis. The application of adaptive filters such as Kalman filters and adaptive gradient descent methods in signal processing can dynamically adjust filter parameters and optimize signal processing effects. Kalman filters can filter out noise and improve signal accuracy by recursively estimating system states. The adaptive gradient descent rule adjusts filter parameters so that the filter can adaptively process different signals and improve processing speed and accuracy. By combining machine learning algorithms and adaptive filters, real-time processing of monitoring data can be achieved, data accuracy and response speed can be improved, and the needs of liquid nitrogen fracturing monitoring can be met.

[0026] Continuing, in step S5, the various monitoring data are integrated and analyzed, and the temperature, stress and acoustic emission signals are displayed in real time through a graphical user interface; Data integration: Using a database management system, the data of different sensors are stored and managed: D = {d1, d2, ..., d n},in, is the data set, d iis a single data entry; Graphical interface: Using data visualization technology, the analysis results are displayed in a graphical way, graph = f(D), where the graph is the visualization result of the data set D, and f is the visualization function; In order to fully understand the changes in the process of rock liquid nitrogen fracturing, it is necessary to integrate and analyze various monitoring data and display them in real time through a graphical user interface. Data integration refers to the storage and management of data collected by different sensors. The use of a database management system can achieve efficient storage and fast query of data. The database management system can quickly locate and extract the required data in the case of large amounts of data through indexing and query optimization technology. The graphical user interface uses data visualization technology to display the analysis results in a graphical way, such as temperature change curves, stress distribution diagrams, and acoustic emission signal diagrams. Data visualization technology uses charts, curves, and color maps to intuitively display complex data results, which is convenient for users to understand and analyze. The graphical user interface also supports interactive operations. Users can view detailed data and analysis results through operations such as clicking, zooming, and dragging. The role of comprehensive data analysis and display is to provide comprehensive and intuitive monitoring results, help operators understand the changes in the rock liquid nitrogen fracturing process in real time, and provide a basis for process adjustment and optimization.

[0027] At this time, in step S6, the injection pressure and rate are adjusted using real-time data to achieve the best fracturing effect: Among them, P is the injection pressure, R is the injection rate, and J is the optimization objective function; in the process of liquid nitrogen fracturing, in order to optimize the fracturing effect, it is necessary to dynamically adjust the parameters of liquid nitrogen injection, such as injection pressure and injection rate, according to real-time monitoring data. The principle of parameter adjustment is to determine the best combination of injection parameters through the analysis results of monitoring data. The real-time data processing algorithm can provide accurate monitoring data and analysis results. Based on these data, operators can adjust the injection pressure and injection rate to achieve the best fracturing effect. The adjustment of injection pressure and injection rate needs to consider the mechanical properties of rock and the physical properties of liquid nitrogen. Too high injection pressure may cause uneven rock fracture, while too low injection rate may affect the fracturing effect. By dynamically adjusting the injection parameters, the process of liquid nitrogen fracturing can be optimized and the uniformity and effect of fracturing can be improved. The role of dynamic parameter adjustment is to adjust the fracturing process parameters in time according to real-time monitoring data, optimize the fracturing effect, improve the uniformity and effect of rock fracture, and provide data support and optimization basis for the liquid nitrogen fracturing process.

[0028] It should be noted that in step S7, if any monitoring parameter X in temperature, stress or acoustic emission signal exceeds its set threshold value X th , then trigger the alarm, Among them, X is the monitoring parameter, X this the alarm threshold; automatically records all monitoring data and analysis results: R = {D1, D2, ..., D m}, where R is the record data set, D i For data from a single monitoring cycle; anomaly detection algorithms based on statistics and machine learning are used to identify anomalies in the data and trigger alarms. Statistical method: If the z-score Z of a data point exceeds the set threshold Z th , then the data point is considered abnormal: Among them, Z is z-score, X is data point ′ μ is the mean value of the data, σ is the standard deviation of the data; if the anomaly score of a data point x in the isolation forest algorithm exceeds the set threshold, the data point is considered abnormal: the isolation forest algorithm constructs multiple random trees, and the number of steps to isolate the data point is used as the anomaly score. Data points with high scores are considered to be abnormal points; if the anomaly score S(x) exceeds the set threshold, the data point is considered abnormal: Where E(h(x)) is the average path length of data point x in the random tree, and c(n) is a constant for the size of the data set. All monitoring data and analysis results are stored in the database to support playback and detailed analysis of historical data, helping to optimize fracturing processes and decisions. The data storage is represented by: S = {R1, R2, …, R n}, where S is the storage data set, R i is the recorded data of different time periods; the data playback formula is as follows: P(t) = {R t}, where P(t) is the data playback result at time t, R tis the recorded data at time t; in the process of liquid nitrogen fracturing, in order to detect abnormal conditions in time and record monitoring data, it is necessary to set the alarm threshold of key parameters, automatically trigger the alarm when the threshold is exceeded, and record all monitoring data and analysis results. The working principle of the alarm system is to set the thresholds of temperature, stress and acoustic emission signals. When the monitoring parameters exceed the set thresholds, the system automatically triggers the alarm to prompt the operator to take corresponding measures. The application of anomaly detection algorithms in alarm systems can improve the accuracy of anomaly detection. Statistical anomaly detection methods such as the z-score algorithm determine whether it is abnormal by calculating the z-score value of each data point. The z-score value reflects the degree of deviation of the data point from the average value. When the deviation exceeds the set threshold, the data point is considered abnormal. Machine learning-based anomaly detection methods such as the isolation forest algorithm construct multiple random trees and use the number of steps to isolate the data point as the anomaly score. Data points with high scores are considered to be abnormal points. The automatic recording system stores all monitoring data and analysis results in the database for subsequent analysis and process optimization. The data storage system can efficiently store large amounts of data through indexing and compression technology, and supports fast query and playback. The data playback function can playback historical data when needed, analyze the changes in the liquid nitrogen fracturing process in detail, and help optimize the fracturing process and decision-making. The role of automatic alarm and recording is to timely discover and handle abnormal situations, ensure the safety and effectiveness of the liquid nitrogen fracturing process, and provide detailed data records to provide data support for subsequent analysis and process optimization.

[0029] The above embodiments are implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments are implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer is a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions are stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions are transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.) mode. The computer-readable storage medium is any available medium that a computer can access or a data storage device such as a server or data center containing one or more available media sets. The available medium is a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium is a solid-state hard disk.

[0030] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0031] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0032] The units described as separate components are or are not physically separated, and the components shown as units are or are not physical units, that is, located in one place or distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0033] In addition, each functional unit in each embodiment of the present application is integrated into one processing unit, each unit exists physically separately, or two or more units are integrated into one unit.

[0034] If the functions are implemented in the form of software functional units and sold or used as independent products, they are stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or partly in other words, the part that contributes to the prior art or part of the technical solution is embodied in the form of a software product, and the computer software product is stored in a storage medium, including several instructions for enabling a computer device (such as a personal computer, a server, or a network device) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media for storing program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0035] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A monitoring method for rock liquid nitrogen fracturing, characterized in that: The monitoring method for rock liquid nitrogen fracturing comprises the following steps: S1: Arrange temperature, stress and acoustic emission sensors on the surface and inside of the rock; S2: Design and install a multi-channel data acquisition system to simultaneously receive and process data from multiple sensors; S3: Use signal transmission technology to transmit sensor data to the data processing center; S4: Process data using real-time data based on machine learning; S5: Integrate and analyze various monitoring data, and display temperature, stress and acoustic emission signals in real time through a graphical user interface; S6: Dynamically adjust liquid nitrogen fracturing parameters according to real-time monitoring data; S7: Set alarm thresholds for key parameters, automatically alarm when the thresholds are exceeded, and record all monitoring data and analysis results.

2. The monitoring method for rock liquid nitrogen fracturing according to claim 1, characterized in that: In step S1, temperature sensors are evenly installed at intervals of 0.5 meters on the rock surface; the temperature sensors measure temperature changes, T=T0+k·ΔT, where T is the measured temperature, T0 is the initial temperature, k is the sensor sensitivity coefficient, and ΔT is the temperature change; a stress sensor is installed at intervals of 1 meter on the rock surface; the stress sensor measures stress changes: σ=E·, where σ is stress, E is the elastic modulus, and is strain; an acoustic emission sensor is arranged at intervals of 1 meter on the rock; the acoustic emission sensor monitors the acoustic wave signals of crack generation and expansion: V(t)=Asin(2πft+ ), where V(t) is the acoustic emission signal, A is the amplitude, f is the frequency, t is the time, and is the initial phase.

3. The monitoring method for rock liquid nitrogen fracturing according to claim 1, characterized in that: In step S2, the analog front end amplifies and filters the sensor output analog signal: V out =G·V in ; Among them, V out is the amplified output signal, G is the amplification factor, V in The sensor input signal; the analog-to-digital converter (ADC) converts the analog signal into a digital signal: Where D is the digital output, V ref+ and V ref- are the positive and negative terminals of the reference voltage respectively, and n is the number of ADC bits.

4. The monitoring method for rock liquid nitrogen fracturing according to claim 1, characterized in that: In step S3, optical fiber communication or high-speed wireless communication technology is used to transmit the collected data to the data processing center in real time. Optical fiber communication uses the high bandwidth and low latency characteristics of optical fiber to quickly transmit data: Among them, C is the communication capacity, B is the bandwidth, S is the signal power, and N is the noise power. Wireless communication uses high-speed wireless communication technologies such as 5G or Wi-Fi6 to ensure the real-time and stability of data transmission: Among them, T is the transmission time, L is the data length, and R is the transmission rate.

5. The method for monitoring rock liquid nitrogen fracturing according to claim 1, characterized in that: In step S4, a real-time data processing algorithm based on machine learning and an adaptive filter are combined to improve data processing accuracy and response speed, and a support vector machine (SVM) is used for classification and regression analysis to improve signal recognition accuracy: Among them, w is the weight vector, b is the bias, ξ i is a slack variable, C is a penalty parameter; convolutional neural network is used to extract signal features and analyze internal changes in rocks: f(x) = σ(W*x+b), where x is the input signal, W is the convolution kernel, * represents the convolution operation, b is the bias, and σ is the activation function; adaptive filter: Kalman filter is used to dynamically estimate the signal state and filter out noise: in, is the estimated state, K k is the Kalman gain, z k is the measured value, H k is the measurement matrix; the adaptive gradient descent method is used to dynamically adjust the filter parameters and optimize the signal processing effect: Among them, θ t is a parameter, η is the learning rate, is the gradient of the loss function.

6. The method for monitoring rock liquid nitrogen fracturing according to claim 1, characterized in that: In step S5, a variety of monitoring data are integrated and analyzed, and temperature, stress and acoustic emission signals are displayed in real time through a graphical user interface; Data integration: Using a database management system, the data of different sensors are stored and managed: D = {d1, d2, ..., d n },in, is the data set, d i is a single data entry; graphical interface: using data visualization technology, the analysis results are displayed in a graphical manner, graph = f(D), where the graph is the visualization result of the data set D, and f is the visualization function.

7. The method for monitoring rock liquid nitrogen fracturing according to claim 1, characterized in that: In step S6, the injection pressure and rate are adjusted to achieve the best fracturing effect using real-time data: Where P is the injection pressure, R is the injection rate, and J is the optimization objective function.

8. The method for monitoring rock liquid nitrogen fracturing according to claim 1, characterized in that: In step S7, if any monitoring parameter X among temperature, stress or acoustic emission signal exceeds its set threshold value X th , then trigger the alarm, Among them, X is the monitoring parameter, X th is the alarm threshold; automatically records all monitoring data and analysis results: R = {D1, D2, ..., D m }, where R is the record data set, D i For data from a single monitoring cycle; anomaly detection algorithms based on statistics and machine learning are used to identify anomalies in the data and trigger alarms. Statistical method: If the z-score Z of a data point exceeds the set threshold Z th , then the data point is considered abnormal: Among them, Z is z-score, X is data point ′ μ is the mean value of the data, σ is the standard deviation of the data; if the anomaly score of a data point x in the isolation forest algorithm exceeds the set threshold, the data point is considered abnormal: the isolation forest algorithm constructs multiple random trees, and the number of steps to isolate the data point is used as the anomaly score. Data points with high scores are considered to be abnormal points; if the anomaly score S(x) exceeds the set threshold, the data point is considered abnormal: Where E(h(x)) is the average path length of data point x in the random tree, and c(n) is a constant for the size of the data set. All monitoring data and analysis results are stored in the database to support playback and detailed analysis of historical data, helping to optimize fracturing processes and decisions. The data storage is represented by: S = {R1, R2, …, R n },in, To store the data set, R i is the recorded data of different time periods; the data playback formula is as follows: P(t) = {R t }, where P(t) is the data playback result at time t, R t is the recorded data at time t.

Citation Information

Patent Citations

  • Method and device for monitoring liquid nitrogen fracturing of rock

    CN109187177A

  • Intelligent early warning optimization method for complex events in fracturing process based on machine learning

    CN117408165A

  • Shale gas horizontal well fracturing intelligent monitoring method

    CN117588197A