A method for predicting and controlling formation breakdown during a fracturing process

Abstract

The application discloses a method for predicting and controlling formation rupture in a fracturing process, comprising the following steps: S1, arranging a three-component acoustic wave receiver array to continuously receive acoustic emission signals from a formation under a pile shoe; S2, enhancing the acoustic emission signals and converting the acoustic emission signals into digital signals through signal conversion; S3, predicting a rupture state and a rupture point position of a formation at the bottom of the pile shoe according to the digital signals; and S4, adopting a packer, a sealing insert pipe and other tools at the rupture point position to realize water injection in a part of a fracturing fracture and oil extraction in another part of the fracturing fracture. The method and system for predicting and controlling formation rupture in the fracturing process provided by the application can improve prediction accuracy, realize real-time monitoring and automatic adjustment, optimize resource utilization, reduce environmental and operation risks, improve work efficiency and cost benefits, enhance adaptability and sustainability, and bring about a significant technical progress.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of fracture profile control, in particular to a method for predicting and controlling formation rupture in the process of fracturing. BACKGROUND

[0002] Self-elevating drilling platform is the main equipment for offshore and marginal oilfield development. In order to ensure the stability of the platform and the smooth operation, the pile legs need to be inserted into the seabed stratum. In the platform pile insertion operation, the multilayer foundation with hard upper and soft lower layers, and the hard shell stratum (commonly known as "eggshell" stratum) are often encountered. Formation rupture is a major risk hidden danger in the operation process of self-elevating platform. Light damage to the platform structure can cause economic losses of millions of yuan, and heavy can lead to platform overturning and personnel casualties, causing economic losses of hundreds of millions of yuan. Among all the accidents caused by foundation problems, formation rupture accidents account for more than 53%. The geological conditions in China's coastal areas are complex, and there are a large number of hard shell strata. Formation rupture events occur from time to time, which has become a bottleneck problem restricting the further application of self-elevating platforms in complex strata. Therefore, a method for predicting and controlling formation rupture in the process of fracturing is urgently needed.

[0003] In order to solve the above problems, in the prior art, the patent for invention with publication number CN110259442 A discloses a method for identifying the rupture layer of coal measure strata by hydraulic fracturing, which realizes real-time monitoring of the hydraulic fracturing rupture process. Whether the rock stratum is ruptured is judged by the rupture characteristics of the rock stratum and the coal stratum, so as to timely adjust the fracturing process and improve the hydraulic fracturing efficiency. It is suitable for coalbed methane hydraulic fracturing monitoring and evaluation. The patent for invention with publication number CN107939368 A discloses a real-time control method for improving the complexity of hydraulic fractures in the same fracturing section of a horizontal well. This method can significantly increase the complexity of hydraulic fractures without the need for special equipment and without increasing the operation time. The patent for invention with publication number CN107451314 A discloses a method and system for predicting the shear rupture capacity of a formation. The invention can optimize the fracturing construction parameters, reduce the exploration and development cost of shale gas formation, and improve the development efficiency of shale formation. The patent for invention with publication number CN109633747 A discloses a microseismic-fracturing engineering data comprehensive analysis method. This method is based on the comprehensive analysis method combining microseismic, fracturing construction data, seismic data and other data, which deepens the engineering geological understanding and provides a basis for the adjustment of field fracturing construction.

[0004] The aforementioned patented technologies still have many limitations. First, the prediction accuracy is limited: traditional methods rely on experience and intuitive judgment, which may lack accurate prediction capabilities, especially under complex or unfamiliar geological conditions. Second, there is a delay in response time: manual judgment and operational adjustments require time, which may lead to an untimely response to changes in the strata, increasing operational risks. Third, there are efficiency issues: manually adjusting operating parameters may not be precise or timely enough, affecting overall operational efficiency and resource utilization. Fourth, there is a lack of data-driven optimization: traditional methods may fail to fully utilize the collected data for in-depth analysis and continuous optimization. Summary of the Invention

[0005] The purpose of this invention is to provide a method, system, and computer equipment for predicting and controlling formation fracturing during hydraulic fracturing, in order to solve the problems of limited prediction accuracy, delayed response time, low efficiency, and lack of data-driven optimization in the existing technology.

[0006] This invention is implemented as follows:

[0007] According to a first aspect of the present invention, the present invention provides a method for predicting and controlling formation fracturing during hydraulic fracturing, comprising the following steps:

[0008] S100. A three-component acoustic receiver array is arranged in the stratum below the pile shoe to continuously receive acoustic emission signals from the stratum.

[0009] S200: Perform signal enhancement processing on the received acoustic emission signal and convert it into a digital signal;

[0010] S300. The digital signal is analyzed using artificial intelligence algorithms to extract key features in order to predict the fracture state and fracture point location of the pile foundation stratum at the bottom of the pile shoe.

[0011] S400: Based on the prediction results, automatically adjust the operation of the packer and sealing pipe to achieve partial water injection and partial oil production control at the fracture point.

[0012] Furthermore, the application of artificial intelligence algorithms includes the following steps:

[0013] S301. Use machine learning technology to extract features from digital signals and identify frequency, amplitude, and duration;

[0014] S302. Construct a predictive model of the formation fracture state and fracture point location based on the extracted features, and train and optimize it using a neural network algorithm or a support vector machine algorithm.

[0015] S303 integrates an intelligent decision-making system that uses predictive models to monitor and control fracturing operations in real time, automatically adjusting the settings of packers and sealing tubes to ensure optimal operation and safety.

[0016] S304. Enable the system to continuously learn and self-update in order to adapt to constantly changing formation conditions and fracturing process requirements.

[0017] According to a second aspect of the present invention, the present invention provides a method for predicting and controlling formation fracturing during hydraulic fracturing, comprising the following steps:

[0018] S1. Arrange a three-component acoustic receiver array to continuously receive acoustic emission signals from the strata below the pile shoe;

[0019] S2. Amplify the acoustic emission signal and convert it into a digital signal;

[0020] S3. Predict the fracture state and fracture point location of the pile foundation stratum at the bottom of the pile shoe based on the digital signal.

[0021] S4. At the fracture point, use packers, sealing pipes and other tools to achieve partial water injection and partial oil production through hydraulic fracturing.

[0022] Furthermore, the three-component acoustic receiver array is arranged at the bottom of each shoe of the jack-up drilling platform;

[0023] The specific method for enhancing acoustic emission signals is as follows:

[0024] Using the time function of the Hurst exponent, an irregular index for discrete time series is established;

[0025] The parameters of the adaptive filter are calculated iteratively using the cost function, as shown in the following formula:

[0026] J w =C w + λ H w

[0027]

[0028] Where Jw is the cost function, Cw is the convergence index, λ is the Lagrange multiplier, Hw is the irregularity index, n is the time sequence number, w(n) is the parameter matrix of the adaptive filter, μ is the iteration step size, e(n) is the error signal, h(n) is the output signal matrix of the delay module, g(n) is the output signal of the adaptive filter, and i1 and i2 are the interval sequences.

[0029] The adaptive filter outputs the denoised target signal under the adjusted parameters;

[0030] The callback signal data obtained after signal enhancement processing is superimposed and coupled before being output.

[0031] Furthermore, the specific steps for converting the signal into a digital signal are as follows:

[0032] S21. Convert the acoustic emission signal into a serial data packet to be sent;

[0033] S22. Convert the acquired serial data packet into a serial-to-parallel format and send it to the corresponding node;

[0034] S23. Each node performs PSK mapping and frequency hopping processing on the received relevant data;

[0035] S24. Output the digital signal of the relevant data obtained after PSK mapping and frequency hopping through the adaptive filter.

[0036] Furthermore, predicting the fracture state and fracture point location of the pile foundation stratum at the bottom of the pile shoe based on the digital signal specifically includes:

[0037] Predict the fracture state of the pile foundation stratum at the bottom of the pile shoe based on the digital signal;

[0038] When the prediction result indicates that the foundation soil at the bottom of the pile shoe is about to fracture, the location of the fracture point is obtained by inverting the digital signal.

[0039] Furthermore, predicting the fracture state of the pile foundation stratum at the bottom of the pile shoe based on the digital signal includes:

[0040] Predict effective events characterizing the fatigue state of hard-shell formations based on the feature parameters of the digital signal;

[0041] Predict whether the stratum at the bottom of the pile shoe is about to fracture based on the cumulative number of valid events.

[0042] Furthermore, the method of predicting whether the foundation stratum at the bottom of the pile shoe is about to fracture based on the cumulative number of valid events includes:

[0043] Obtain the cumulative number curve of valid events during the piling process;

[0044] Monitor the slope of the cumulative curve in real time;

[0045] When the slope of the cumulative number curve reaches its maximum value, an early warning message is sent indicating that the foundation stratum at the bottom of the pile shoe is about to fracture.

[0046] Furthermore, the characteristic parameters include: energy, similarity, and / or amplitude-frequency relationship.

[0047] According to a third aspect of the present invention, the present invention provides a formation fracturing prediction and control system for implementing the above-described method for predicting and controlling formation fracturing during hydraulic fracturing, the system comprising:

[0048] The signal receiving module is used to continuously receive acoustic emission signals from the strata below the pile shoe using a three-component acoustic receiver array;

[0049] The signal enhancement module, connected to the signal receiving module, is used to enhance the acoustic emission signal and convert it into a digital signal.

[0050] The prediction module, connected to the signal enhancement module, predicts the fracture state and fracture point location of the pile foundation stratum at the bottom of the pile shoe based on the digital signal.

[0051] The control module, connected to the prediction module, uses tools such as packers and sealing pipes at the fracture point to achieve partial water injection and partial oil production through hydraulic fracturing.

[0052] According to a fourth aspect of the present invention, the present invention provides a computer device, the computer device including a memory and a processor, the memory storing a computer program, which, when executed by the processor, causes the processor to perform the steps of the above-described method for predicting and controlling formation fracturing during hydraulic fracturing.

[0053] Compared with the prior art, the present invention has the following beneficial effects:

[0054] 1. This invention brings about significant technological progress by improving prediction accuracy, enabling real-time monitoring and automatic adjustment, optimizing resource utilization, reducing environmental and operational risks, improving work efficiency and cost-effectiveness, and enhancing adaptability and sustainability.

[0055] 2. By utilizing artificial intelligence algorithms to analyze acoustic emission signals, this method can more accurately predict the fracture state and location of fracture points in strata. This high-precision prediction is difficult to achieve with traditional methods, especially under complex underground conditions.

[0056] 3. By integrating an intelligent decision-making system, this method can monitor the fracturing process in real time and automatically adjust the operation of the packer and sealing tube based on prediction results. This not only improves operational efficiency but also reduces the risks caused by human error.

[0057] 4. By implementing a strategy of partial water injection and partial oil recovery through fracturing at the fracture point, this method can utilize resources more effectively and improve the oil and gas recovery rate.

[0058] 5. Precise formation fracturing control reduces unnecessary fracturing operations and lowers potential environmental impacts. Simultaneously, intelligent control reduces safety risks during operations.

[0059] 6. Automated and intelligent operation reduces reliance on human labor and improves the efficiency of the entire fracturing process. In the long run, this method can significantly reduce operating costs and time.

[0060] 7. The intelligent learning and self-updating capabilities of this method enable it to adapt to different geological conditions and changes, thereby improving the sustainability and future applicability of the entire system. Attached Figure Description

[0061] Figure 1 This is a flowchart of the formation fracturing prediction and control method provided in Embodiment 1 of the present invention;

[0062] Figure 2 This is a flowchart of the formation fracturing prediction and control method provided in Embodiment 2 of the present invention;

[0063] Figure 3 This is a flowchart of the method for converting a signal into a digital signal provided in Embodiment 2 of the present invention;

[0064] Figure 4 This is a structural diagram of the formation fracturing prediction and control system provided in Embodiment 3 of the present invention. Detailed Implementation

[0065] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0066] Example 1

[0067] like Figure 1 As shown, a method for predicting and controlling formation fracturing during hydraulic fracturing includes the following steps:

[0068] S100. A three-component acoustic receiver array is arranged in the stratum below the pile shoe to continuously receive acoustic emission signals from the stratum.

[0069] S200 performs signal enhancement processing on the received acoustic emission signal and converts it into a digital signal.

[0070] S300: Artificial intelligence algorithms are applied to analyze digital signals and extract key features to predict the fracture state and location of fracture points in the foundation strata at the bottom of the pile shoe. The application of artificial intelligence algorithms includes the following steps:

[0071] S301. Use machine learning technology to extract features from digital signals and identify frequency, amplitude, and duration;

[0072] S302. Construct a predictive model of the formation fracture state and fracture point location based on the extracted features, and train and optimize it using a neural network algorithm or a support vector machine algorithm.

[0073] S303 integrates an intelligent decision-making system that uses predictive models to monitor and control fracturing operations in real time, automatically adjusting the settings of packers and sealing tubes to ensure optimal operation and safety.

[0074] S304. Enable the system to continuously learn and self-update in order to adapt to constantly changing formation conditions and fracturing process requirements.

[0075] S400: Based on the prediction results, automatically adjust the operation of the packer and sealing pipe to achieve partial water injection and partial oil production control at the fracture point.

[0076] Example 2

[0077] like Figure 2 As shown, a method for predicting and controlling formation fracturing during hydraulic fracturing includes the following steps:

[0078] S1. Arrange a three-component acoustic receiver array. The three-component acoustic receiver array is arranged at the bottom of each pile shoe of the jack-up drilling platform. The acoustic emission signals from the strata below the pile shoe are continuously received by the three-component acoustic receiver array.

[0079] S2. The acoustic emission signal is amplified and then converted into a digital signal. The specific method for amplifying the acoustic emission signal is as follows:

[0080] Using the time function of the Hurst exponent, an irregular index for discrete time series is established;

[0081] The parameters of the adaptive filter are calculated iteratively using the cost function, as shown in the following formula:

[0082] J w =C w + λ H w

[0083]

[0084] Where Jw is the cost function, Cw is the convergence index, λ is the Lagrange multiplier, Hw is the irregularity index, n is the time sequence number, w(n) is the parameter matrix of the adaptive filter, μ is the iteration step size, e(n) is the error signal, h(n) is the output signal matrix of the delay module, g(n) is the output signal of the adaptive filter, and i1 and i2 are the interval sequences. Under the adjusted parameters, the adaptive filter outputs the denoised target signal, and the callback signal data obtained after signal enhancement processing is superimposed and coupled before being output.

[0085] like Figure 3 As shown, the specific steps for converting a signal into a digital signal are as follows:

[0086] S21. Convert the acoustic emission signal into a serial data packet to be sent.

[0087] S22. Convert the acquired serial data packets into parallel data and send them to the corresponding node.

[0088] S23. Each node performs PSK mapping and frequency hopping processing on the received relevant data.

[0089] S24. Output the digital signal of the relevant data obtained after PSK mapping and frequency hopping through the adaptive filter.

[0090] S3. Predict the fracture state and fracture point location of the pile foundation stratum at the bottom of the pile shoe based on digital signals, as detailed below:

[0091] Predicting the fracture state of the pile foundation strata at the bottom of the pile shoe based on digital signals: Effective events characterizing the fatigue state of the hard crust strata are predicted based on the characteristic parameters of the digital signals, including energy, similarity, and / or amplitude-frequency relationship. The cumulative number of effective events is then used to predict whether the pile foundation strata at the bottom of the pile shoe is about to fracture.

[0092] Predicting whether the stratum at the bottom of the pile shoe is about to fracture based on the cumulative number of valid events includes:

[0093] The system acquires the cumulative number curve of valid events during the pile driving process; monitors the slope of the cumulative number curve in real time; and sends an early warning message that the stratum at the bottom of the pile shoe is about to fracture when the slope of the cumulative number curve reaches its maximum value. When the prediction result indicates that the stratum at the bottom of the pile shoe is about to fracture, the location of the fracture point is obtained by inverting the digital signal.

[0094] S4. At the fracture point, use packers, sealing pipes and other tools to achieve partial water injection and partial oil production through hydraulic fracturing.

[0095] Example 3

[0096] like Figure 4 As shown, a formation fracturing prediction and control system during hydraulic fracturing includes a signal receiving module, a signal enhancement module, a prediction module, and a control module. The signal receiving module continuously receives acoustic emission signals from the formation beneath the pile shoe using a three-component acoustic receiver array. The signal enhancement module, connected to the signal receiving module, amplifies the acoustic emission signals and converts them into digital signals. The prediction module, also connected to the signal enhancement module, predicts the fracturing state and location of the fracture points in the pile foundation formation at the bottom of the pile shoe based on the digital signals. The control module, connected to the prediction module, uses packers, sealing pipes, and other tools at the fracture points to achieve partial hydraulic fracturing for water injection and partial hydraulic fracturing for oil recovery.

[0097] Example 4

[0098] A computer device includes a memory and a processor. The memory stores a computer program. When the computer program is executed by the processor, it causes the processor to perform the steps of the formation fracturing prediction and control method provided in Embodiment 1 or Embodiment 2.

[0099] It should be noted that embodiments of the present invention can be implemented in hardware, software, or a combination of both. The hardware portion can be implemented using dedicated logic; the software portion can be stored in memory and executed by a suitable instruction execution system, such as a microprocessor or dedicated-design hardware. Those skilled in the art will understand that the above-described devices and methods can be implemented using computer-executable instructions and / or included in processor control code, for example, such code provided on a carrier medium such as a disk, CD, or DVD-ROM, a programmable memory such as read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The devices and modules of the present invention can be implemented by hardware circuitry such as very large-scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field-programmable gate arrays, programmable logic devices, etc., or by software executed by various types of processors, or by a combination of the above-described hardware circuitry and software, such as firmware.

[0100] The following are two specific implementation examples and their solutions:

[0101] Application Solution 1: Optimization of Oilfield Fracturing Operations

[0102] 1) Arrangement of acoustic receivers: A high-precision three-component acoustic receiver array is arranged below the predetermined fracturing area of ​​the oilfield to continuously monitor the acoustic emission signals of the formation.

[0103] 2) Signal processing and conversion: The acoustic emission signals received from the formation are enhanced by advanced signal enhancement techniques, such as adaptive filters, and these signals are converted into digital form using high-precision analog-to-digital converters.

[0104] 3) AI Analysis and Prediction: Utilize deep learning models (such as convolutional neural networks) to analyze digital signals, extract features of geological faults, and predict the location of fault points.

[0105] 4) Real-time control of fracturing operations: Based on AI model predictions, the operation of fracturing equipment, such as the configuration of packers and sealing tubing, is automatically adjusted to optimize the fracturing water injection and oil production process.

[0106] Through real-time monitoring and intelligent prediction, this solution can significantly improve the efficiency and safety of oilfield fracturing operations while maximizing oil and gas recovery.

[0107] Application Scheme 2: Crack Control in Geothermal Energy Development

[0108] 1) Equipment layout: Deploy a three-component acoustic receiver array at key points in the geothermal energy development area to monitor acoustic emission signals from underground rock strata.

[0109] 2) Data acquisition and conversion: Acquire acoustic emission signals, enhance the signals using advanced signal processing technology, and then convert them into digital signals.

[0110] 3) Machine learning prediction models: Using machine learning algorithms, such as random forests or gradient boosters, to analyze digital signals and predict formation fracturing modes and locations.

[0111] 4) Geothermal energy extraction control: Based on the prediction results of the machine learning model, the parameters of geothermal energy extraction, such as water injection volume and pressure, are automatically adjusted to control the development of formation fractures.

[0112] Application effects: This solution can effectively control geological fissures during geothermal energy development, improve energy extraction efficiency, and reduce environmental impact.

[0113] These two solutions demonstrate how the proposed methods can be applied to different industrial scenarios, leveraging AI technology to achieve real-time monitoring and intelligent control of ground fracturing, thereby optimizing operational effectiveness and resource utilization.

[0114] Example 5

[0115] A method for predicting and controlling formation fracturing during hydraulic fracturing, as provided in Example 2, can be combined with mathematical algorithms and models of artificial intelligence (AI) to achieve its intelligentization. This can be carried out according to the following steps:

[0116] S1000, Data Collection and Preprocessing

[0117] Acoustic receiver array arrangement: A high-precision three-component acoustic receiver array is arranged in the strata below the pile shoe to continuously receive acoustic emission signals from the strata. These signals contain key information about strata fracturing.

[0118] Data preprocessing: The collected acoustic emission signals are initially cleaned and preprocessed, such as denoising and normalization, to facilitate more accurate subsequent analysis.

[0119] S2000, Signal Enhancement and Digitization

[0120] Signal enhancement: Using signal processing techniques (such as filters, amplifiers, etc.) to enhance sound wave signals, ensuring signal clarity and recognizability.

[0121] Analog-to-digital conversion: An analog-to-digital converter (ADC) is used to convert the enhanced analog signal into a digital signal, preparing it for AI analysis.

[0122] S3000, AI-driven fracture prediction

[0123] Feature extraction: Using machine learning techniques to extract key features from digital signals, such as frequency, amplitude, and duration.

[0124] Establish a predictive model: Based on the extracted features, use artificial intelligence algorithms (such as neural networks, support vector machines, etc.) to establish a predictive model of the formation fracture state and fracture point location.

[0125] Model training and optimization: The model is trained using historical and field data, and its accuracy is continuously optimized through feedback loops.

[0126] S4000, Intelligent Control Fracturing Operation

[0127] Intelligent Decision System: Integrates the prediction results of AI models into an intelligent decision system for real-time monitoring and control of the fracturing process.

[0128] Real-time feedback and adjustment: The system automatically adjusts the operation of packers and sealing pipes based on real-time data and prediction results to achieve the optimization of partial water injection and partial oil production in fractured systems.

[0129] Safety monitoring: The system should also include a safety monitoring module to ensure that the entire process complies with safety standards.

[0130] The technical implementation is as follows:

[0131] Algorithm and model selection: Select AI algorithms and models suitable for acoustic wave data analysis, such as convolutional neural networks (CNN) for feature recognition and recurrent neural networks (RNN) for processing time series data.

[0132] System Integration: Integrate the AI ​​module with existing fracturing equipment and control systems to ensure seamless data transmission and real-time response.

[0133] Continuous learning and updating: Ensure the system can continuously learn and optimize itself based on new data.

[0134] In summary, by applying artificial intelligence mathematical algorithms and models to the prediction and control of formation fracturing during fracturing, the accuracy and efficiency of operations can be significantly improved, while reducing human error and risk, thus achieving safer and more sustainable fracturing operations.

[0135] Based on the above technical solutions and the technical problems solved, the advantages and positive effects of the technical solution to be protected by this invention are as follows:

[0136] First, the present invention provides tools such as packers and sealing pipes at the fracture point to achieve partial water injection and partial oil production through fracturing. This can reduce the distance between the injection end and the production end, reduce the impact of formation fracturing events, and improve economic efficiency.

[0137] This invention involves arranging a three-component acoustic receiver array at the bottom of each pile shoe on a jack-up drilling platform. During pile insertion, the array continuously receives acoustic emission signals from the underlying strata of the pile shoe. Based on these acoustic emission signals, the fracture state and location of the pile foundation strata at the bottom of the pile shoe are predicted. Specifically, during the drilling platform insertion process, by arranging three-component acoustic receivers at the bottom of the pile shoe, acoustic emission signals emitted during the fatigue process of the hard-shell strata are collected, serving as the data basis for predicting the fracture state and location of the fracture point. This allows for the determination of the time and location of strata fracture, thereby preventing strata fracturing events.

[0138] Second, the significant technological advancements brought about by the formation fracturing prediction and control method proposed in this invention include:

[0139] 1) Improved prediction accuracy: By utilizing artificial intelligence algorithms to analyze acoustic emission signals, this method can more accurately predict the fracture state and location of fracture points in strata. This high-precision prediction is difficult to achieve with traditional methods, especially under complex underground conditions.

[0140] 2) Real-time monitoring and automatic adjustment: Combined with an intelligent decision-making system, this method can monitor the fracturing process in real time and automatically adjust the operation of the packer and sealing tube based on the prediction results. This not only improves operational efficiency but also reduces the risks caused by human error.

[0141] 3) Optimize resource utilization and improve oil and gas recovery rate: By implementing a strategy of partial water injection and partial oil production through fracturing at the fracture point, this method can utilize resources more effectively and improve the oil and gas recovery rate.

[0142] 4) Reduced environmental impact and operational risks: Precise formation fracturing control reduces unnecessary fracturing operations and lowers potential environmental impacts. Simultaneously, intelligent control reduces safety risks during operations.

[0143] 5) Improved work efficiency and cost-effectiveness: Automated and intelligent operation reduces reliance on human labor and improves the overall efficiency of the fracturing process. In the long run, this method can significantly reduce operating costs and time.

[0144] 6) Adaptability and sustainability: The intelligent learning and self-updating capabilities of this method enable it to adapt to different geological conditions and changes, improving the sustainability and future applicability of the entire system.

[0145] In summary, the formation fracturing prediction and control method provided by this invention brings significant technological progress by improving prediction accuracy, enabling real-time monitoring and automatic adjustment, optimizing resource utilization, reducing environmental and operational risks, improving work efficiency and cost-effectiveness, and enhancing adaptability and sustainability.

[0146] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention can have various modifications and variations. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for predicting and controlling formation fracturing during hydraulic fracturing, characterized in that, Includes the following steps: S100. A three-component acoustic receiver array is arranged in the stratum below the pile shoe to continuously receive acoustic emission signals from the stratum. S200: Perform signal enhancement processing on the received acoustic emission signal and convert it into a digital signal; S300. The digital signal is analyzed using artificial intelligence algorithms to extract key features in order to predict the fracture state and fracture point location of the pile foundation stratum at the bottom of the pile shoe. S400: Based on the prediction results, automatically adjust the operation of the packer and sealing pipe to achieve partial water injection and partial oil production control at the fracture point.

2. The method for predicting and controlling formation fracturing during hydraulic fracturing according to claim 1, characterized in that, The application of artificial intelligence algorithms includes the following steps: S301. Use machine learning technology to extract features from digital signals and identify frequency, amplitude, and duration; S302. Construct a predictive model of the formation fracture state and fracture point location based on the extracted features, and train and optimize it using a neural network algorithm or a support vector machine algorithm. S303 integrates an intelligent decision-making system that uses predictive models to monitor and control fracturing operations in real time, automatically adjusting the settings of packers and sealing tubes to ensure optimal operation and safety. S304. Enable the system to continuously learn and self-update in order to adapt to constantly changing formation conditions and fracturing process requirements.

3. A method for predicting and controlling formation fracturing during hydraulic fracturing, characterized in that, Includes the following steps: S1. Arrange a three-component acoustic receiver array to continuously receive acoustic emission signals from the strata below the pile shoe; S2. Amplify the acoustic emission signal and convert it into a digital signal; S3. Predict the fracture state and fracture point location of the pile foundation stratum at the bottom of the pile shoe based on the digital signal. S4. At the fracture point, use packers, sealing pipes and other tools to achieve partial water injection and partial oil production through hydraulic fracturing.

4. The method for predicting and controlling formation fracturing during hydraulic fracturing according to claim 3, characterized in that, The three-component acoustic receiver array is arranged at the bottom of each shoe of the jack-up drilling platform; The specific method for enhancing acoustic emission signals is as follows: Using the time function of the Hurst exponent, an irregular index for discrete time series is established; The parameters of the adaptive filter are calculated iteratively using the cost function, as shown in the following formula: J w =C w + λ H w Where Jw is the cost function, Cw is the convergence index, λ is the Lagrange multiplier, Hw is the irregularity index, n is the time sequence number, w(n) is the parameter matrix of the adaptive filter, μ is the iteration step size, e(n) is the error signal, h(n) is the output signal matrix of the delay module, g(n) is the output signal of the adaptive filter, and i1 and i2 are the interval sequences. The adaptive filter outputs the denoised target signal under the adjusted parameters; The callback signal data obtained after signal enhancement processing is superimposed and coupled before being output.

5. The method for predicting and controlling formation fracturing during hydraulic fracturing as described in claim 3, characterized in that, The specific steps for converting a signal into a digital signal are as follows: S21. Convert the acoustic emission signal into a serial data packet to be sent; S22. Convert the acquired serial data packet into a serial-to-parallel format and send it to the corresponding node; S23. Each node performs PSK mapping and frequency hopping processing on the received relevant data; S24. Output the digital signal of the relevant data obtained after PSK mapping and frequency hopping through an adaptive filter.

6. The method for predicting and controlling formation fracturing during hydraulic fracturing as described in claim 3, characterized in that, Predicting the fracture state and fracture point location of the pile foundation stratum at the bottom of the pile shoe based on the digital signal specifically includes: Predict the fracture state of the pile foundation stratum at the bottom of the pile shoe based on the digital signal; When the prediction result indicates that the foundation soil at the bottom of the pile shoe is about to fracture, the location of the fracture point is obtained by inverting the digital signal.

7. The method for predicting and controlling formation fracturing during hydraulic fracturing as described in claim 6, characterized in that, Predicting the fracture state of the pile foundation stratum at the bottom of the pile shoe based on the digital signal includes: Predict effective events characterizing the fatigue state of hard-shell formations based on the feature parameters of the digital signal; Predict whether the stratum at the bottom of the pile shoe is about to fracture based on the cumulative number of valid events.

8. The method for predicting and controlling formation fracturing during hydraulic fracturing according to claim 7, characterized in that, The method of predicting whether the stratum at the bottom of the pile shoe is about to fracture based on the cumulative number of valid events includes: Obtain the cumulative number curve of valid events during the piling process; Monitor the slope of the cumulative curve in real time; When the slope of the cumulative number curve reaches its maximum value, an early warning message is sent indicating that the foundation stratum at the bottom of the pile shoe is about to fracture.

9. The method for predicting and controlling formation fracturing during hydraulic fracturing according to claim 7, characterized in that, The characteristic parameters include: energy, similarity, and / or amplitude-frequency relationship.

10. A formation fracturing prediction and control system for implementing the formation fracturing prediction and control method as described in any one of claims 1-9, characterized in that, The system includes: The signal receiving module is used to continuously receive acoustic emission signals from the strata below the pile shoe using a three-component acoustic wave receiver array; The signal enhancement module, connected to the signal receiving module, is used to enhance the acoustic emission signal and convert it into a digital signal. The prediction module, connected to the signal enhancement module, predicts the fracture state and fracture point location of the pile foundation stratum at the bottom of the pile shoe based on the digital signal. The control module, connected to the prediction module, uses tools such as packers and sealing pipes at the fracture point to achieve partial water injection and partial oil production through hydraulic fracturing.

11. A computer device, characterized in that, The computer device includes a memory and a processor. The memory stores a computer program, which, when executed by the processor, causes the processor to perform the steps of the formation fracturing prediction and control method as described in any one of claims 1-8.

Images