Monitoring and feedback method, device and system for underground hydraulic fracturing crack

Abstract

The invention provides an underground hydraulic fracturing crack monitoring and feedback method, device and system. The method comprises the steps that underground multi-source data in the fracturing process are obtained, and the underground multi-source data comprise fracturing pipeline water pressure data, hydraulic system oil pressure data, fracturing fluid flow data, crack propagation form data, crack inlet temperature and pressure data and proppant concentration data; performing anomaly recognition on the underground multi-source data by adopting a preset judgment threshold value to obtain various anomaly recognition results; and under the condition that any abnormal recognition result represents that the abnormal working condition exists, a feedback control mechanism is triggered, and the feedback control mechanism at least comprises acousto-optic early warning and crack expansion form adjustment. The problem that a hydraulic fracture fracturing monitoring method in the prior art cannot achieve real-time feedback control in the fracturing process is solved.

Description

Technical Field

[0001] This application relates to the field of coal mine fracturing technology, and more specifically, to a method for monitoring and feedback of underground hydraulic fracturing fractures, a device for monitoring and feedback of underground hydraulic fracturing fractures, and a system for monitoring and feedback of underground hydraulic fracturing fractures. Background Technology

[0002] Hydraulic fracturing technology is a key measure in shale oil and gas and coal mining. By injecting high-pressure fluid into the formation, it creates a network of fractures in the rock, which significantly improves reservoir permeability and roof collapse resistance. Fracturing operations require large-volume and high-pump-pressure construction, resulting in high construction pressure and a high risk of accidents, which places higher demands on the real-time monitoring and control of the fracture propagation process.

[0003] Existing hydraulic fracture monitoring methods rely on post-fracturing inversion algorithms and cannot achieve real-time feedback control during the fracturing process. Summary of the Invention

[0004] The main objective of this application is to provide a method, device, and system for monitoring and responding to hydraulic fracturing fractures in wells, so as to at least solve the problem that existing hydraulic fracturing monitoring methods cannot achieve real-time feedback control during the fracturing process.

[0005] To achieve the above objectives, according to one aspect of this application, a method for monitoring and feedback of downhole hydraulic fracturing fractures is provided, comprising: acquiring downhole multi-source data during the fracturing process, wherein the downhole multi-source data includes hydraulic pressure data of the fracturing pipeline, oil pressure data of the hydraulic system, fracturing fluid flow rate data, fracture propagation morphology data, temperature and pressure data at the fracture inlet, and proppant concentration data; identifying anomalies in the downhole multi-source data using a preset evaluation threshold to obtain multiple anomaly identification results; and triggering a feedback control mechanism when any of the anomaly identification results indicates the existence of an abnormal operating condition, wherein the feedback control mechanism includes at least audible and visual early warning and fracture propagation morphology adjustment.

[0006] Optionally, the multiple anomaly identification results include a first anomaly identification result, a second anomaly identification result, and a third anomaly identification result. The preset evaluation threshold includes a static threshold, which includes a preset water pressure threshold, a preset oil pressure threshold, and a preset flow rate threshold. An anomaly identification is performed on the downhole multi-source data using a preset evaluation mechanism to obtain multiple anomaly identification results, including: determining whether the water pressure data of the fracturing pipeline exceeds the preset water pressure threshold to generate the first anomaly identification result; determining whether the oil pressure data of the hydraulic system exceeds the preset oil pressure threshold to generate the second anomaly identification result; and determining whether the fracturing fluid flow rate data exceeds the preset flow rate threshold to generate the third anomaly identification result.

[0007] Optionally, the multiple anomaly identification results also include a fourth anomaly identification result, a fifth anomaly identification result, a sixth anomaly identification result, and a seventh anomaly identification result. The preset evaluation threshold also includes a dynamic threshold, which includes a preset water pressure slope threshold range, a preset amplitude threshold, a preset tolerance value, and a preset propagation rate range. The preset evaluation mechanism is used to identify anomalies in the downhole multi-source data to obtain multiple anomaly identification results, including: determining whether the slope of the water pressure curve of the fracturing pipeline water pressure data is within the preset water pressure slope threshold range to generate the fourth anomaly identification result; determining whether the change amplitude of the slope of the water pressure curve of the fracturing pipeline water pressure data exceeds the preset amplitude threshold after a fracturing section of preset time to generate the fifth anomaly identification result; determining whether the spatial deviation between the fracture propagation morphology data and the expected fracture morphology predicted by the integrated geological engineering model exceeds the preset tolerance value to generate the sixth anomaly identification result, where the integrated geological engineering model is a model for predicting fracture propagation based on geological parameters and fracturing parameters; and determining whether the fracture propagation rate exceeds the preset propagation rate range to generate the seventh anomaly identification result.

[0008] Optionally, the feedback control mechanism further includes an emergency stop operation. When any of the anomaly identification results indicates an abnormal operating condition, the feedback control mechanism is triggered, including: determining the anomaly level of the abnormal operating condition; triggering the audible and visual warning when the anomaly level is a first anomaly level; and triggering the audible and visual warning and performing the emergency stop operation when the anomaly level is a second anomaly level. The emergency stop operation includes disconnecting the power input of the fluid supply pump from the hydraulic system. The urgency of the first anomaly level is less than that of the second anomaly level. Wherein, when the anomaly level is either the first or the second anomaly level, the fracture propagation morphology is adjusted after the audible and visual warning is triggered. The fracture propagation morphology adjustment includes adjusting the fracturing pump displacement, fluid viscosity, or proppant concentration.

[0009] Optionally, before acquiring downhole multi-source data during the fracturing process, the method further includes: acquiring multiple sensor signals during the fracturing process, including water pressure sensor signals, oil pressure sensor signals, flow sensor signals, fracture propagation monitoring sensor signals, temperature and pressure signals at the fracture inlet, and proppant concentration signals; and converting the sensor signals into data formats to obtain the downhole multi-source data.

[0010] Optionally, the fracture propagation monitoring sensor signal includes a fracture propagation morphology signal. Multiple sensor signals are acquired during the fracturing process, including: acquiring the water pressure sensor signal, the oil pressure sensor signal, and the flow sensor signal using a water pressure sensor, an oil pressure sensor, and a flow sensor, respectively; acquiring the fracture propagation morphology signal using a fracture propagation monitoring sensor group, which includes a distributed fiber optic sensor and a downhole camera module; acquiring the temperature and pressure signal at the fracture inlet using a thermobarometer; and acquiring the proppant concentration signal using a proppant concentration sensor.

[0011] Optionally, the feedback control mechanism further includes adaptive optimization control, which is executed after each fracturing operation is completed. The adaptive optimization control includes: obtaining historical fracturing effect data from the historical fracturing database; and updating the preset evaluation threshold and the control parameters used for adjusting the fracture propagation morphology based on the fracture propagation morphology data of the current fracturing operation and the historical fracturing effect data using a machine learning algorithm.

[0012] Optionally, after acquiring downhole multi-source data during the fracturing process, the method further includes at least one of the following fracturing effect evaluation operations: evaluating whether the duration of the current fracturing operation meets a preset process threshold based on the fracturing pipeline water pressure data, the hydraulic system oil pressure data, and the fracturing fluid flow rate data; comparing the water pressure versus time curve and flow rate versus time curve during the current fracturing process with historical successful fracturing curves stored in the database to evaluate whether the current fracturing process conforms to a preset typical fracturing response mode; determining the fracture orientation and propagation radius using a pressure inversion model based on the fracturing pipeline water pressure data; and evaluating the fracture geometry and spatial distribution orientation based on the fracture propagation morphology data, the temperature and pressure data at the fracture inlet, and the proppant concentration data, and calculating the reservoir stimulation volume.

[0013] According to another aspect of this application, a monitoring and feedback device for downhole hydraulic fracturing fractures is provided, comprising: a first acquisition unit for acquiring downhole multi-source data during the fracturing process, the downhole multi-source data including fracturing pipeline water pressure data, hydraulic system oil pressure data, fracturing fluid flow rate data, fracture propagation morphology data, fracture inlet temperature and pressure data, and proppant concentration data; an identification unit for identifying anomalies in the downhole multi-source data using a preset evaluation threshold to obtain multiple anomaly identification results; and a triggering unit for triggering a feedback control mechanism when any of the multiple anomaly identification results indicates the existence of an abnormal operating condition, the feedback control mechanism including at least audible and visual early warning and fracture propagation morphology adjustment.

[0014] According to another aspect of this application, a monitoring and feedback system for downhole hydraulic fracturing fractures is provided, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including methods for performing any of the described downhole hydraulic fracturing fracture monitoring and feedback methods.

[0015] This application utilizes a technical solution to acquire multi-source downhole data during the fracturing process. This data includes hydraulic pressure data from the fracturing pipeline, oil pressure data from the hydraulic system, fracturing fluid flow rate data, fracture propagation morphology data, temperature and pressure data at the fracture inlet, and proppant concentration data. Preset threshold values ​​are used to identify anomalies in the multi-source data, resulting in various anomaly identification results. When any anomaly identification result indicates an abnormal operating condition, a feedback control mechanism is triggered. This feedback control mechanism includes at least audible and visual warnings and fracture propagation morphology adjustment. The solution achieves the following results: By real-time acquisition of multi-dimensional downhole sensor data (including water pressure, oil pressure, flow rate, fracture morphology, temperature and pressure, and proppant concentration) during fracturing, and synchronous anomaly identification based on preset threshold values, a feedback control mechanism including audible and visual warnings is immediately activated upon triggering any anomaly signal. This enables a rapid anomaly response closed loop in downhole high-pressure hydraulic fracturing operations without relying on post-processing inversion or manual intervention, based on real-time multi-parameter sensing. This solves the problem that existing hydraulic fracture monitoring methods cannot achieve real-time feedback control during the fracturing process. Attached Figure Description

[0016] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0017] Figure 1 A hardware structure block diagram of a mobile terminal for performing a method for monitoring and responding to downhole hydraulic fracturing fractures according to an embodiment of this application is shown.

[0018] Figure 2 A schematic flowchart of a method for monitoring and feedback of downhole hydraulic fracturing fractures according to an embodiment of this application is shown.

[0019] Figure 3 A structural block diagram of a downhole hydraulic fracturing fracture monitoring and feedback device according to an embodiment of this application is shown.

[0020] Figure 4 A schematic diagram of the overall framework of a monitoring and feedback system for downhole hydraulic fracturing fractures provided according to an embodiment of this application is shown.

[0021] Figure 5 A schematic diagram of a data acquisition module for a monitoring and feedback system for downhole hydraulic fracturing fractures according to an embodiment of this application is shown.

[0022] Figure 6 A schematic diagram of a downhole camera module of a downhole hydraulic fracturing fracture monitoring and feedback system according to an embodiment of this application is shown.

[0023] Figure 7 A schematic diagram of anomaly monitoring and feedback control of a downhole hydraulic fracturing fracture monitoring and feedback system provided according to an embodiment of this application is shown.

[0024] Figure 8 The diagram illustrates data analysis and fracture morphology processing of a downhole hydraulic fracturing fracture monitoring and feedback system according to an embodiment of this application.

[0025] The above figures include the following reference numerals:

[0026] 102. Processor; 104. Memory; 106. Transmission device; 108. Input / output device. Detailed Implementation

[0027] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0028] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0029] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this application described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0030] As described in the background section, existing hydraulic fracture monitoring methods rely on post-inversion algorithms and cannot achieve real-time feedback control during the fracturing process. To address the problem that hydraulic fracture monitoring methods cannot achieve real-time feedback control during the fracturing process, embodiments of this application provide a downhole hydraulic fracturing fracture monitoring and feedback method, a downhole hydraulic fracturing fracture monitoring and feedback device, and a downhole hydraulic fracturing fracture monitoring and feedback system.

[0031] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0032] The methods and embodiments provided in this application can be executed on a mobile terminal, computer terminal, or similar computing device. Taking running on a mobile terminal as an example, Figure 1 This is a hardware structure block diagram of a mobile terminal for a method of monitoring and providing feedback on hydraulic fracturing fractures in wells, according to an embodiment of the present invention. Figure 1 As shown, a mobile terminal may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data are also shown. The mobile terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the mobile terminal described above. For example, the mobile terminal may also include components that are more... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0033] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the downhole hydraulic fracturing fracture monitoring and feedback method in this embodiment of the invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thereby implementing the above-described method. The memory 104 may include high-speed random access memory and non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the aforementioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof. The transmission device 106 is used to receive or send data via a network. Specific examples of the aforementioned networks may include wireless networks provided by the mobile terminal's communication provider. In one example, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0034] This embodiment provides a method for monitoring and feedback of downhole hydraulic fracturing fractures that runs on a mobile terminal, computer terminal, or similar computing device. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Also, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0035] Figure 2 This is a schematic flowchart illustrating the monitoring and feedback method for downhole hydraulic fracturing fractures according to an embodiment of this application. Figure 2 As shown, the method includes the following steps:

[0036] Step S201: Obtain downhole multi-source data during the fracturing process. The downhole multi-source data includes fracturing pipeline water pressure data, hydraulic system oil pressure data, fracturing fluid flow rate data, fracture propagation morphology data, fracture inlet temperature and pressure data, and proppant concentration data.

[0037] Specifically, during fracturing operations, multi-source downhole data is acquired. Among these, hydraulic pressure data in the fracturing pipeline reflects the operational pressure status, hydraulic system oil pressure data reflects the operational health of the equipment, fracturing fluid flow data reflects the injection efficiency, fracture propagation morphology data is obtained by capturing the geometric evolution of fractures in real time through distributed optical fibers and downhole cameras, temperature and pressure data at the fracture inlet can determine whether the fracture connects to the formation and whether there is thermal channeling or fluid anomalies, and proppant concentration data can assess the proppant addition effect and the effectiveness of fracture support.

[0038] Step S202: Anomaly identification is performed on the above downhole multi-source data using a preset evaluation threshold to obtain various anomaly identification results;

[0039] Specifically, based on preset evaluation thresholds, such as pressure, flow rate limit, water pressure slope change, and fracture morphology deviation, the acquired downhole multi-source data is compared and analyzed to generate various anomaly identification results (such as overpressure, sand blockage, fracture displacement, and uncontrolled propagation). This process does not rely on manual interpretation or post-processing inversion, and quickly achieves anomaly determination from data acquisition.

[0040] Step S203: If any of the above-mentioned anomaly identification results indicate the existence of an abnormal working condition, a feedback control mechanism is triggered. The above-mentioned feedback control mechanism includes at least audible and visual early warning and crack propagation morphology adjustment.

[0041] Specifically, once any anomaly identification result indicates an abnormal operating condition (such as a sudden drop in water pressure, fracture deviation from the model, etc.), a feedback control mechanism is immediately triggered. This mechanism includes at least audible and visual early warning and fracture propagation morphology adjustment. The audible and visual early warning triggers an on-site audible and visual alarm to alert operators; the fracture propagation morphology adjustment can automatically adjust the fracturing pump discharge rate, liquid viscosity, or proppant concentration to actively intervene in the direction and morphology of fracture propagation (such as reducing the discharge rate to suppress high fracture cross-linking and increasing viscosity to enhance distal fracture branching).

[0042] This embodiment acquires multi-dimensional downhole sensor data (including water pressure, oil pressure, flow rate, fracture morphology, temperature and pressure, and proppant concentration) in real time during the fracturing process. Based on preset evaluation thresholds, it synchronously identifies anomalies in the above-mentioned multi-source data. When any abnormal signal is triggered, a feedback control mechanism including audible and visual warnings is immediately activated. This achieves a rapid anomaly response closed loop in downhole high-pressure hydraulic fracturing operations without relying on post-inversion or manual intervention, based on real-time perception of multiple parameters. This solves the problem that existing hydraulic fracture monitoring methods cannot achieve real-time feedback control during the fracturing process.

[0043] In the specific implementation process, the above-mentioned anomaly identification results include a first anomaly identification result, a second anomaly identification result, and a third anomaly identification result. The above-mentioned preset evaluation thresholds include static thresholds, which include preset water pressure thresholds, preset oil pressure thresholds, and preset flow rate thresholds. The preset evaluation mechanism is used to identify anomalies in the above-mentioned downhole multi-source data, resulting in multiple anomaly identification results, including: determining whether the water pressure data of the above-mentioned fracturing pipeline exceeds the above-mentioned preset water pressure threshold, generating the above-mentioned first anomaly identification result; determining whether the oil pressure data of the above-mentioned hydraulic system exceeds the above-mentioned preset oil pressure threshold, generating the above-mentioned second anomaly identification result; and determining whether the fracturing fluid flow rate data exceeds the above-mentioned preset flow rate threshold, generating the above-mentioned third anomaly identification result.

[0044] Specifically, determining whether the hydraulic pressure data in the fracturing pipeline exceeds the preset hydraulic pressure threshold is to prevent rupture, leakage, or blowout accidents caused by pressure overload in the fracturing pipeline, wellhead equipment, packers, etc. The preset hydraulic pressure threshold can be set based on the rated operating pressure, the wellhead safety rating, and the formation fracturing pressure safety margin. If the hydraulic pressure continues to exceed the threshold, it indicates that the fracture has not effectively expanded, the formation's pressure-bearing capacity is insufficient, or the pipeline is blocked (such as by sand blockage), and continued construction will lead to a catastrophic accident. The generated first anomaly identification result serves as the triggering basis for subsequent feedback control mechanisms.

[0045] Determining whether the hydraulic system oil pressure data exceeds the preset oil pressure threshold is to protect the hydraulic power system of the fracturing truck (such as the pump truck motor, servo valve, and accumulator) and prevent equipment damage or fire due to excessive load, valve core jamming, or oil circuit blockage. The preset oil pressure threshold can be set according to the rated output pressure of the hydraulic pump. An abnormal increase in oil pressure is often a sign of mechanical failure in the pump truck, abnormal hydraulic oil viscosity, or servo system malfunction, which may lead to shutdown or even equipment damage. The generated second anomaly identification result serves as the triggering basis for subsequent feedback control mechanisms.

[0046] Determining whether fracturing fluid flow rate exceeds a preset flow threshold is crucial to prevent over-injection of fracturing fluid due to control failure, which could lead to a sudden increase in wellbore fluid column pressure, uncontrolled formation fracturing, or overflow of the mixing tank. The preset flow threshold can be set based on a combination of factors, including the pump truck's maximum safe discharge capacity, the upper limit of formation absorption capacity, and the pressure-bearing capacity of the on-site pipelines. An abnormally high flow rate could indicate a flow meter malfunction, accidental valve opening, or control system failure. It could also suggest that the fracture is rapidly connecting to natural fractures or adjacent wells, requiring immediate intervention. The generated third anomaly identification result serves as the trigger for subsequent feedback control mechanisms.

[0047] By setting static thresholds for three key safety parameters in fracturing operations—fracturing pipeline water pressure, hydraulic system oil pressure, and fracturing fluid flow rate—the system achieves millisecond-level precise identification of the most direct and urgent safety risks, such as equipment overload, pipeline rupture, and flow control failure, generating three traceable anomaly identification results. Without relying on complex algorithms, it offers rapid response, clear logic, and strong anti-interference capabilities, effectively preventing equipment damage or blowout accidents caused by exceeding the limits of a single parameter. This significantly improves the safety of downhole high-pressure operations and provides a stable and reliable underlying triggering foundation for subsequent feedback control.

[0048] In some embodiments of this application, the various anomaly identification results further include a fourth anomaly identification result, a fifth anomaly identification result, a sixth anomaly identification result, and a seventh anomaly identification result. The preset evaluation threshold also includes a dynamic threshold, which includes a preset water pressure slope threshold range, a preset amplitude threshold, a preset tolerance value, and a preset propagation rate range. The preset evaluation mechanism is used to identify anomalies in the downhole multi-source data to obtain various anomaly identification results, including: determining whether the slope of the water pressure curve of the fracturing pipeline water pressure data is within the preset water pressure slope threshold range, generating the fourth anomaly identification result; determining whether the change amplitude of the water pressure curve slope of the fracturing pipeline water pressure data exceeds the preset amplitude threshold after a fracturing section of preset time, generating the fifth anomaly identification result; determining whether the spatial deviation between the fracture propagation morphology data and the expected fracture morphology predicted by the integrated geological engineering model exceeds the preset tolerance value, generating the sixth anomaly identification result, where the integrated geological engineering model is a model for predicting fracture propagation based on geological parameters and fracturing parameters; and determining whether the fracture propagation rate exceeds the preset propagation rate range, generating the seventh anomaly identification result.

[0049] Specifically, this embodiment introduces a dynamic threshold on the basis of the static threshold, realizing the shift from judging whether the limit is exceeded to judging whether there is abnormal evolution. By analyzing the evolution trend, rate of change and deviation of parameters over time and spatial morphology, it can identify complex abnormal working conditions that are highly concealed, highly dangerous and difficult to capture by traditional methods.

[0050] Determining whether the slope of the water pressure curve in the fracturing pipeline falls within the preset water pressure slope threshold range is crucial for assessing whether fracturing is in the normal rupture and propagation phase. An excessively high slope may indicate difficulty in fracturing the formation, wasted pump pressure, and wellbore pressure risks; an excessively low slope may suggest incomplete fracturing, failure to initiate fractures, or ineffective injection. During fracturing, after rupture, the formation should enter a stable propagation phase, with the water pressure exhibiting a gradual upward trend (moderate slope). Sudden changes in the slope or a sustained deviation from the design range indicate that fracturing has not started as expected. The preset water pressure slope threshold range is set based on the lithological and mechanical parameters of the target reservoir (such as the brittleness index and geostress gradient) and the measured dynamic water pressure data from the fracturing rupture-propagation phase in the field, combined with the stable fracture propagation slope range predicted by theoretical models (such as KGD and PKN). This determines a reasonable dynamic range that reflects effective fracture propagation while avoiding fracturing initiation failure or excessive pressurization. The generated fourth anomaly identification result serves as the trigger for subsequent feedback control mechanisms.

[0051] Determining whether the change in the slope of the hydraulic pressure curve in the fracturing pipeline exceeds a preset threshold after a pre-defined fracturing period is crucial for identifying abrupt changes during fracturing. Examples include: sand plugging (sharp increase in slope, continuous pressure rise, constant flow); connecting natural fractures or adjacent wells (sharp drop in slope, fluid leakage); fracture turning / bidding (intensified slope fluctuations). The preset threshold is a quantitative assessment of trend stability; even if the current hydraulic pressure is within limits, an abnormal rate of change still indicates significant risk. For example, if the initial fracturing slope is 0.8 MPa / s, and then suddenly rises to 3.0 MPa / s after entering the stabilization phase, sand plugging is highly suspected. The preset threshold is set based on statistical analysis of historical changes in the slope of the hydraulic pressure curve under typical fracturing conditions (such as normal propagation, sand plugging, and connecting natural fractures), combined with formation response dynamics, to determine the critical change range that distinguishes normal evolution from abrupt changes, ensuring sensitive identification of key anomalies such as sand plugging and fracture connection without false alarms. The generated fifth anomaly identification result serves as the triggering basis for subsequent feedback control mechanisms.

[0052] Determining whether the spatial deviation between the fracture propagation morphology data and the expected fracture morphology predicted by the integrated geological engineering model exceeds a preset tolerance value is crucial for achieving three-dimensional visual closed-loop control of fracture propagation. Geological parameters include in-situ stress, lithology, and natural fracture distribution, while fracturing parameters include displacement, viscosity, proppant dosage, and pump shutdown time. The fracture length is located using distributed optical fibers, and the fracture orientation and morphology are identified using downhole camera units. Temperature and pressure data are fused and input into a finite element / discrete element / machine learning prediction model (integrated geological engineering model), outputting the expected fracture morphology. If the actual fracture propagates in a non-designed direction (e.g., into an aquifer or breaking through an interlayer), even with normal water pressure, it constitutes a significant geological risk. The preset tolerance value is set based on the prediction accuracy error range of the integrated geological engineering model, the measurement uncertainty of downhole multimodal monitoring data (e.g., optical fiber positioning error ±1~2m, camera recognition error ±3%), and engineering safety redundancy requirements. This comprehensive determination of the maximum permissible spatial deviation threshold between the actual and predicted fracture morphologies ensures controllable fracture propagation, preventing breaches of the target modification area or the initiation of geological risks. The generated sixth anomaly identification result serves as the trigger for subsequent feedback control mechanisms.

[0053] Determining whether the fracture propagation rate exceeds the preset range is crucial to prevent uncontrolled fracture height (e.g., reaching the surface or connecting to aquifers) or excessive lateral propagation (leading to resource waste). The fracture's length or height growth rate per second is calculated using the acoustic emission positioning time difference of distributed optical fibers or the characteristic displacement between downhole camera frames. If the propagation rate exceeds the preset range, it indicates abnormal formation stress or insufficient fracturing fluid viscosity, potentially leading to ineffective fracturing, inter-well interference, or environmental risks. The preset propagation rate range is set based on the target reservoir's rock mechanics parameters (e.g., stress difference, Young's modulus, fracture toughness), historical fracturing data, and geological engineering model simulation results. This comprehensive assessment determines the maximum and minimum propagation rate range under safe and controllable conditions to prevent uncontrolled fracture height migration or insufficient propagation resulting in a lower-than-expected stimulation volume. The generated seventh anomaly identification result serves as the trigger for subsequent feedback control mechanisms.

[0054] By introducing a dynamic threshold mechanism, a four-dimensional real-time anomaly identification system based on the slope of the water pressure curve, the amplitude of slope change, fracture morphology deviation, and propagation rate was constructed, which significantly improved the accuracy and adaptability of anomaly identification in the fracturing process. By linking with the integrated geological engineering model, quantitative closed-loop control of fracture evolution behavior was achieved, enabling intelligent identification of key anomalies such as sand plugging, natural fracture communication, and fracture height loss of control within seconds. The anomaly response time was shortened from minutes to seconds, greatly enhancing the safety, stability, and accuracy of fracturing operations and reservoir stimulation.

[0055] In some embodiments of this application, the feedback control mechanism further includes an emergency stop operation. When any of the above-mentioned anomaly identification results indicates an abnormal operating condition, the feedback control mechanism is triggered, including: determining the anomaly level of the abnormal operating condition; triggering the audible and visual warning when the anomaly level is a first anomaly level; and triggering the audible and visual warning and performing the emergency stop operation when the anomaly level is a second anomaly level. The emergency stop operation includes disconnecting the power input of the fluid supply pump from the hydraulic system. The urgency of the first anomaly level is less than that of the second anomaly level. Wherein, in both the first and second anomaly levels, the fracture propagation morphology is adjusted after the audible and visual warning is triggered. The fracture propagation morphology adjustment includes adjusting the fracturing pump displacement, fluid viscosity, or proppant concentration.

[0056] Specifically, the core of this embodiment lies in implementing differentiated control strategies based on the severity of the anomaly identification results. When any anomaly (such as excessive water pressure, abnormal fracture propagation, etc.) is detected, its anomaly level is first assessed. If it is a minor anomaly (Level 1), only an audible and visual warning is activated, and fracturing parameters (such as displacement, viscosity, and proppant concentration) are adjusted simultaneously to actively correct the fracture morphology and prevent deterioration. If it is a severe anomaly (Level 2), an emergency stop operation is immediately executed upon triggering the audible and visual warning, cutting off the power input to the fluid supply pump and hydraulic system to eliminate major risks such as equipment overload or wellbore rupture from the source. Regardless of the anomaly level, fracture morphology adjustment is performed simultaneously.

[0057] By constructing a feedback control mechanism of "anomaly classification - layered response - synchronous regulation," the safety and efficiency of fracturing operations are optimized simultaneously. Mild anomalies (Level 1) trigger only audible and visual warnings and automatically fine-tune the flow rate, viscosity, or proppant concentration to proactively correct fracture morphology. Severe anomalies (Level 2) immediately trigger an emergency shutdown based on the warning, completely cutting off the fluid supply and hydraulic system to effectively prevent major accidents such as wellbore rupture. Regardless of the anomaly level, fracture morphology adjustment is performed synchronously after the alarm, breaking through the limitations of traditional "stop without adjustment" or "loss of control after shutdown," ensuring that while guaranteeing inherent safety, the continuity and precision of fracturing operations are maintained to the greatest extent possible.

[0058] In some embodiments of this application, before acquiring downhole multi-source data during the fracturing process, the method further includes: acquiring multiple sensor signals during the fracturing process, including water pressure sensor signals, oil pressure sensor signals, flow sensor signals, fracture propagation monitoring sensor signals, temperature and pressure signals at the fracture inlet, and proppant concentration signals; and converting the sensor signals into data formats to obtain the downhole multi-source data.

[0059] Specifically, before fracturing operations begin, signals from water pressure sensors, oil pressure sensors, flow sensors, fracture propagation monitoring sensors, temperature and pressure signals at the fracture inlet, and proppant concentration signals are simultaneously and in real-time acquired. Subsequently, these raw signals from different sensors, with varying ranges, protocols, and sampling frequencies, undergo unified signal conditioning, filtering, amplification, and analog-to-digital conversion (ADC) to standardize them into digital data packets with consistent structure, uniform units, and synchronized time—i.e., downhole multi-source data. This step lays a high-quality, highly consistent data foundation for subsequent real-time display, anomaly detection, morphological analysis, and control decisions, resolving engineering bottlenecks such as the difficulty in fusing heterogeneous multi-source data, time asynchrony, and accuracy mismatch.

[0060] By collecting multi-dimensional raw sensor signals such as water pressure, oil pressure, flow rate, fracture propagation, fracture inlet temperature and pressure, and proppant concentration before fracturing operations, and uniformly conditioning and converting the signals, high-precision, high-synchronization, and standardized fusion of heterogeneous sensor data was achieved. This provides a reliable, consistent, and traceable data foundation for subsequent real-time monitoring and intelligent control, effectively solving the problems of monitoring distortion and response lag caused by inconsistent signal protocols, asynchronous sampling, and large noise interference.

[0061] Furthermore, the aforementioned fracture propagation monitoring sensor signals include fracture propagation morphology signals. Multiple sensor signals are acquired during the fracturing process, including: acquiring the water pressure sensor signal, the oil pressure sensor signal, and the flow sensor signal using a water pressure sensor, an oil pressure sensor, and a flow sensor, respectively; acquiring the fracture propagation morphology signal using a fracture propagation monitoring sensor group, which includes a distributed fiber optic sensor and a downhole camera module; acquiring the temperature and pressure signal at the fracture inlet using a thermobarometer; and acquiring the proppant concentration signal using a proppant concentration sensor.

[0062] Specifically, multiple types of sensors deployed at key downhole locations, including hydraulic pressure sensors, oil pressure sensors, and flow sensors for monitoring pipeline pressure; distributed fiber optic or camera units for detecting fracture propagation; thermobarometers installed near the perforation clusters (to acquire temperature and pressure changes at the fracture inlet); and proppant concentration sensors based on ultrasonic attenuation principles, synchronously and in real-time acquire raw analog / digital signals. The hydraulic pressure, oil pressure, and flow sensors are used to acquire engineering control parameters of the fracturing fluid; fracture propagation morphology signals are jointly acquired by a distributed fiber optic sensor (DAS / DTS) and a downhole camera module. The former accurately locates the fracture initiation point, extension length, and development trend through acoustic vibration and temperature field changes, while the latter directly visualizes the fracture morphology and spatial orientation through high-definition images. This complementary integration overcomes the limitations of single sensors in qualitative and quantitative analysis. Simultaneously, the thermobarometer monitors real-time temperature and pressure changes at the fracture inlet, reflecting the interaction between fluid and rock, while the proppant concentration sensor dynamically provides feedback on proppant loading efficiency.

[0063] By constructing a multimodal collaborative sensing system based on pressure, morphology, temperature and pressure, and concentration, a distributed optical fiber sensor (DAS / DTS) and a downhole camera module are used as the core combination to acquire fracture propagation morphology signals in real time. This enables high-precision dual-channel acoustic and optical sensing of fracture spatial distribution. The optical fiber provides meter-level resolution of the extension path and energy evolution, while the downhole camera module provides intuitive fracture morphology and orientation information. The fusion of these two technologies fills the blind spot of traditional fracturing monitoring, which only measures pressure and does not detect fractures. At the same time, the thermobarometer and proppant concentration sensor accurately capture the thermal response and proppant-carrying dynamics at the fracture inlet, forming a multi-physics closed-loop observation of the entire fracture development process. This significantly improves the accuracy, robustness, and engineering interpretability of fracture identification, providing solid underlying data support for realizing visual and adjustable fracturing control of real three-dimensional fractures and breaking through the bottleneck of lag caused by reliance on later inversion.

[0064] In some embodiments of this application, the above-mentioned feedback control mechanism further includes adaptive optimization control, which is executed after each fracturing operation is completed. The adaptive optimization control includes: obtaining historical fracturing effect data from the historical fracturing database; and updating the preset evaluation threshold and the control parameters used for adjusting the fracture propagation morphology based on the fracture propagation morphology data of the current fracturing operation and the above-mentioned historical fracturing effect data using a machine learning algorithm.

[0065] Specifically, this embodiment further introduces an adaptive learning mechanism. After each fracturing operation, the fracture propagation morphology data (such as fracture length, width, dip angle, SRV, etc.) obtained from this operation are compared and analyzed with successful or failed cases under the same geological conditions in the historical fracturing database. Machine learning algorithms (such as reinforcement learning, support vector regression, or neural networks) are used to dynamically learn the nonlinear mapping relationship between control parameters, fracture morphology, and operation results, thereby intelligently optimizing safety thresholds (such as water pressure slope threshold, propagation rate limit) and adjustment strategies (such as displacement adjustment step size, viscosity response sensitivity, etc.), so that it can more accurately adapt to complex and changing geological conditions in subsequent operations.

[0066] By automatically integrating current fracture propagation morphology data with historical fracturing effect databases after each fracturing operation, and using machine learning algorithms to achieve autonomous iterative optimization of anomaly assessment thresholds and control parameters, this system possesses continuous learning and self-evolution capabilities. This overcomes the bottleneck of poor adaptability and weak generalization ability of traditional static threshold settings under complex geological conditions, significantly improving the accuracy, robustness, and intelligence of control strategies, greatly reducing reliance on human intervention, and increasing fracturing success rate and reservoir stimulation efficiency.

[0067] In some embodiments of this application, after acquiring downhole multi-source data during the fracturing process, the method further includes at least one of the following fracturing effect evaluation operations: based on the fracturing pipeline water pressure data, the hydraulic system oil pressure data, and the fracturing fluid flow rate data, evaluating whether the duration of the current fracturing operation meets a preset process threshold; comparing the water pressure versus time curve and flow rate versus time curve during the current fracturing process with historical successful fracturing curves stored in the database to evaluate whether the current fracturing process conforms to a preset typical fracturing response mode; based on the fracturing pipeline water pressure data, using a pressure inversion model to determine the fracture orientation and propagation radius; based on the fracture propagation morphology data, the temperature and pressure data at the fracture inlet, and the proppant concentration data, evaluating the fracture geometry and spatial distribution orientation, and calculating the reservoir stimulation volume.

[0068] Specifically, this embodiment further clarifies four comprehensive intelligent evaluation operations for fracturing effects performed after acquiring multi-source downhole data, constructing a multi-dimensional, multi-scale fracturing quality assessment system covering the construction process, morphological evolution, and engineering effects. By dynamically changing water pressure, oil pressure, and flow rate, the start and end times of the effective fracturing stage are identified, determining whether the operation has reached the designed duration threshold (preset process threshold), avoiding insufficient construction or excessive pumping. The real-time collected water pressure and time curves, and flow rate and time curves are compared with typical response patterns in a historical successful case library (such as fracture pressure points, linear flow stages, sand blockage characteristics, etc.) to achieve rapid diagnosis of construction health. Based on the dynamic characteristics of water pressure changes, combined with a geomechanical model (pressure inversion model), the wellbore stress field is inverted to infer the extension direction and radius of the main fracture, providing a basis for subsequent inter-segment avoidance and fracture layout design. By integrating multi-source data such as fracture propagation morphology (from optical fiber and video), fracture inlet temperature and pressure (reflecting fluid flow and energy dissipation), and proppant concentration (reflecting proppant carrying efficiency), a multi-parameter coupled model is used to quantitatively reconstruct the geometric dimensions (length, width, height) and spatial orientation (dip angle, strike) of fractures and calculate the reservoir stimulation volume (SRV), thus achieving a leap from qualitative observation to quantitative evaluation.

[0069] The evaluation system constructed in this embodiment is no longer limited to a single pressure or flow rate index, but realizes a closed-loop evaluation of the entire chain of construction process, fluid response, fracture morphology and modification effect. It provides a scientific, quantitative and traceable decision-making basis for real-time adjustment of fracturing technology and optimization of subsequent schemes, and significantly improves the controllability, predictability and engineering economy of fracturing operations.

[0070] This application also provides a monitoring and feedback device for downhole hydraulic fracturing fractures. It should be noted that this monitoring and feedback device can be used to execute the monitoring and feedback method for downhole hydraulic fracturing fractures provided in this application. This device is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0071] The following describes the monitoring and feedback device for downhole hydraulic fracturing fractures provided in the embodiments of this application.

[0072] Figure 3 This is a structural block diagram of a downhole hydraulic fracturing fracture monitoring and feedback device according to an embodiment of this application. Figure 3As shown, the device includes a first acquisition unit 10, an identification unit 20, and a triggering unit 30. The first acquisition unit is used to acquire downhole multi-source data during the fracturing process, including fracturing pipeline water pressure data, hydraulic system oil pressure data, fracturing fluid flow rate data, fracture propagation morphology data, fracture inlet temperature and pressure data, and proppant concentration data. The identification unit is used to identify anomalies in the downhole multi-source data using a preset evaluation threshold, obtaining various anomaly identification results. The triggering unit is used to trigger a feedback control mechanism when any of the anomaly identification results indicates the existence of an abnormal operating condition. The feedback control mechanism includes at least audible and visual early warning and fracture propagation morphology adjustment.

[0073] This embodiment acquires multi-dimensional downhole sensor data (including water pressure, oil pressure, flow rate, fracture morphology, temperature and pressure, and proppant concentration) in real time during the fracturing process. Based on preset evaluation thresholds, it synchronously identifies anomalies in the above-mentioned multi-source data. When any abnormal signal is triggered, a feedback control mechanism including audible and visual warnings is immediately activated. This achieves a rapid anomaly response closed loop in downhole high-pressure hydraulic fracturing operations without relying on post-inversion or manual intervention, based on real-time perception of multiple parameters. This solves the problem that existing hydraulic fracture monitoring methods cannot achieve real-time feedback control during the fracturing process.

[0074] In the specific implementation process, the aforementioned anomaly identification results include a first anomaly identification result, a second anomaly identification result, and a third anomaly identification result. The aforementioned preset judgment thresholds include static thresholds, which include preset water pressure thresholds, preset oil pressure thresholds, and preset flow rate thresholds. The aforementioned identification unit includes a first judgment module, a second judgment module, and a third judgment module. The first judgment module is used to determine whether the water pressure data of the fracturing pipeline exceeds the aforementioned preset water pressure threshold, generating the aforementioned first anomaly identification result; the second judgment module is used to determine whether the oil pressure data of the hydraulic system exceeds the aforementioned preset oil pressure threshold, generating the aforementioned second anomaly identification result; the third judgment module is used to determine whether the fracturing fluid flow rate data exceeds the aforementioned preset flow rate threshold, generating the aforementioned third anomaly identification result.

[0075] By setting static thresholds for three key safety parameters in fracturing operations—fracturing pipeline water pressure, hydraulic system oil pressure, and fracturing fluid flow rate—the system achieves millisecond-level precise identification of the most direct and urgent safety risks, such as equipment overload, pipeline rupture, and flow control failure, generating three traceable anomaly identification results. Without relying on complex algorithms, it offers rapid response, clear logic, and strong anti-interference capabilities, effectively preventing equipment damage or blowout accidents caused by exceeding the limits of a single parameter. This significantly improves the safety of downhole high-pressure operations and provides a stable and reliable underlying triggering foundation for subsequent feedback control.

[0076] In some embodiments of this application, the various anomaly identification results also include a fourth anomaly identification result, a fifth anomaly identification result, a sixth anomaly identification result, and a seventh anomaly identification result. The preset judgment threshold also includes a dynamic threshold, which includes a preset water pressure slope threshold range, a preset amplitude threshold, a preset tolerance value, and a preset expansion rate range. The identification unit also includes a fourth judgment module, a fifth judgment module, a sixth judgment module, and a seventh judgment module. The fourth judgment module is used to determine whether the slope of the water pressure curve of the above-mentioned fracturing pipeline water pressure data is within the above-mentioned preset water pressure slope threshold range, and generates the above-mentioned fourth anomaly identification result; the fifth judgment module is used to determine whether the change amplitude of the slope of the above-mentioned fracturing pipeline water pressure data exceeds the above-mentioned preset amplitude threshold after the fracturing section has undergone a preset time, and generates the above-mentioned fifth anomaly identification result; the sixth judgment module is used to determine whether the spatial deviation between the above-mentioned fracture propagation morphology data and the expected fracture morphology predicted by the integrated geological engineering model exceeds the above-mentioned preset tolerance value, and generates the above-mentioned sixth anomaly identification result, wherein the above-mentioned integrated geological engineering model is a model for fracture propagation prediction based on geological parameters and fracturing parameters; the seventh judgment module is used to determine whether the fracture propagation rate exceeds the above-mentioned preset propagation rate range, and generates the above-mentioned seventh anomaly identification result.

[0077] By introducing a dynamic threshold mechanism, a four-dimensional real-time anomaly identification system based on the slope of the water pressure curve, the amplitude of slope change, fracture morphology deviation, and propagation rate was constructed, which significantly improved the accuracy and adaptability of anomaly identification in the fracturing process. By linking with the integrated geological engineering model, quantitative closed-loop control of fracture evolution behavior was achieved, enabling intelligent identification of key anomalies such as sand plugging, natural fracture communication, and fracture height loss of control within seconds. The anomaly response time was shortened from minutes to seconds, greatly enhancing the safety, stability, and accuracy of fracturing operations and reservoir stimulation.

[0078] In some embodiments of this application, the feedback control mechanism further includes an emergency stop operation, and the triggering unit includes an eighth judgment module, a first triggering module, and a second triggering module. The eighth judgment module is used to determine the abnormality level of the abnormal working condition when any of the above-mentioned abnormality identification results indicate the existence of an abnormal working condition; the first triggering module is used to trigger the above-mentioned audible and visual warning when the above-mentioned abnormality level is a first abnormality level; the second triggering module is used to trigger the above-mentioned audible and visual warning and perform the above-mentioned emergency stop operation when the above-mentioned abnormality level is a second abnormality level, the above-mentioned emergency stop operation includes controlling the power input of the fluid supply pump to disconnect from the hydraulic system, the urgency of the above-mentioned first abnormality level is less than the urgency of the above-mentioned second abnormality level; wherein, when the above-mentioned abnormality level is the above-mentioned first abnormality level or the above-mentioned second abnormality level, the above-mentioned fracture propagation morphology adjustment is performed after the above-mentioned audible and visual warning is triggered, the above-mentioned fracture propagation morphology adjustment includes adjusting the displacement of the fracturing pump, the fluid viscosity, or the proppant concentration.

[0079] By constructing a feedback control mechanism of "anomaly classification - layered response - synchronous regulation," the safety and efficiency of fracturing operations are optimized simultaneously. Mild anomalies (Level 1) trigger only audible and visual warnings and automatically fine-tune the flow rate, viscosity, or proppant concentration to proactively correct fracture morphology. Severe anomalies (Level 2) immediately trigger an emergency shutdown based on the warning, completely cutting off the fluid supply and hydraulic system to effectively prevent major accidents such as wellbore rupture. Regardless of the anomaly level, fracture morphology adjustment is performed synchronously after the alarm, breaking through the limitations of traditional "stop without adjustment" or "loss of control after shutdown," ensuring that while guaranteeing inherent safety, the continuity and precision of fracturing operations are maintained to the greatest extent possible.

[0080] In some embodiments of this application, the above-mentioned device further includes a second acquisition unit and a conversion unit. The second acquisition unit is used to acquire various sensor signals during the fracturing process before acquiring the downhole multi-source data during the fracturing process. The various sensor signals include water pressure sensor signals, oil pressure sensor signals, flow sensor signals, fracture propagation monitoring sensor signals, temperature and pressure signals at the fracture inlet, and proppant concentration signals. The conversion unit is used to convert the data format of the sensor signals to obtain the downhole multi-source data.

[0081] By collecting multi-dimensional raw sensor signals such as water pressure, oil pressure, flow rate, fracture propagation, fracture inlet temperature and pressure, and proppant concentration before fracturing operations, and uniformly conditioning and converting the signals, high-precision, high-synchronization, and standardized fusion of heterogeneous sensor data was achieved. This provides a reliable, consistent, and traceable data foundation for subsequent real-time monitoring and intelligent control, effectively solving the problems of monitoring distortion and response lag caused by inconsistent signal protocols, asynchronous sampling, and large noise interference.

[0082] Furthermore, the aforementioned fracture propagation monitoring sensor signal includes a fracture propagation morphology signal, and the aforementioned second acquisition unit includes a first acquisition module, a second acquisition module, a third acquisition module, and a fourth acquisition module. The first acquisition module is used to acquire the aforementioned water pressure sensor signal, the aforementioned oil pressure sensor signal, and the aforementioned flow sensor signal using a water pressure sensor, an aforementioned oil pressure sensor, and the aforementioned flow sensor signal, respectively; the second acquisition module is used to acquire the aforementioned fracture propagation morphology signal using a fracture propagation monitoring sensor group, the aforementioned fracture propagation monitoring sensor group including a distributed fiber optic sensor and a downhole camera module; the third acquisition module is used to acquire the aforementioned temperature and pressure signal at the fracture inlet using a thermobarometer; and the fourth acquisition module is used to acquire the aforementioned proppant concentration signal using a proppant concentration sensor.

[0083] By constructing a multimodal collaborative sensing system based on pressure, morphology, temperature and pressure, and concentration, a distributed optical fiber sensor (DAS / DTS) and a downhole camera module are used as the core combination to acquire fracture propagation morphology signals in real time. This enables high-precision dual-channel acoustic and optical sensing of fracture spatial distribution. The optical fiber provides meter-level resolution of the extension path and energy evolution, while the downhole camera module provides intuitive fracture morphology and orientation information. The fusion of these two technologies fills the blind spot of traditional fracturing monitoring, which only measures pressure and does not detect fractures. At the same time, the thermobarometer and proppant concentration sensor accurately capture the thermal response and proppant-carrying dynamics at the fracture inlet, forming a multi-physics closed-loop observation of the entire fracture development process. This significantly improves the accuracy, robustness, and engineering interpretability of fracture identification, providing solid underlying data support for realizing visual and adjustable fracturing control of real three-dimensional fractures and breaking through the bottleneck of lag caused by reliance on later inversion.

[0084] In some embodiments of this application, the above-mentioned feedback control mechanism further includes adaptive optimization control, which is executed after each fracturing operation is completed. The adaptive optimization control includes: obtaining historical fracturing effect data from the historical fracturing database; and updating the preset evaluation threshold and the control parameters used for adjusting the fracture propagation morphology based on the fracture propagation morphology data of the current fracturing operation and the above-mentioned historical fracturing effect data using a machine learning algorithm.

[0085] By automatically integrating current fracture propagation morphology data with historical fracturing effect databases after each fracturing operation, and using machine learning algorithms to achieve autonomous iterative optimization of anomaly assessment thresholds and control parameters, this system possesses continuous learning and self-evolution capabilities. This overcomes the bottleneck of poor adaptability and weak generalization ability of traditional static threshold settings under complex geological conditions, significantly improving the accuracy, robustness, and intelligence of control strategies, greatly reducing reliance on human intervention, and increasing fracturing success rate and reservoir stimulation efficiency.

[0086] In some embodiments of this application, after acquiring downhole multi-source data during the fracturing process, the method further includes at least one of the following fracturing effect evaluation operations: based on the fracturing pipeline water pressure data, the hydraulic system oil pressure data, and the fracturing fluid flow rate data, evaluating whether the duration of the current fracturing operation meets a preset process threshold; comparing the water pressure versus time curve and flow rate versus time curve during the current fracturing process with historical successful fracturing curves stored in the database to evaluate whether the current fracturing process conforms to a preset typical fracturing response mode; based on the fracturing pipeline water pressure data, using a pressure inversion model to determine the fracture orientation and propagation radius; based on the fracture propagation morphology data, the temperature and pressure data at the fracture inlet, and the proppant concentration data, evaluating the fracture geometry and spatial distribution orientation, and calculating the reservoir stimulation volume.

[0087] The evaluation system constructed in this embodiment is no longer limited to a single pressure or flow rate index, but realizes a closed-loop evaluation of the entire chain of construction process, fluid response, fracture morphology and modification effect. It provides a scientific, quantitative and traceable decision-making basis for real-time adjustment of fracturing technology and optimization of subsequent schemes, and significantly improves the controllability, predictability and engineering economy of fracturing operations.

[0088] The aforementioned downhole hydraulic fracturing fracture monitoring and feedback device includes a processor and a memory. The first acquisition unit, identification unit, and triggering unit are all stored as program units in the memory, and the processor executes these program units to achieve the corresponding functions. All of the above modules are located in the same processor; alternatively, the modules may be located in different processors in any combination.

[0089] The memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0090] This invention provides a monitoring and feedback system for downhole hydraulic fracturing fractures. This system is used for segmented fracturing operations in horizontal wells for underground gas extraction and roof cutting and pressure relief in coal mines. For example... Figure 4As shown, the system includes: a data acquisition module, a signal conversion module, a real-time display module, an anomaly monitoring module, a feedback control module, a data analysis module, a fracture propagation monitoring module, a wireless communication module, a fracture morphology analysis module, a central processing unit, and a data storage module. The data acquisition module collects signals from a water pressure sensor, an oil pressure sensor, a flow sensor, and a fracture propagation monitoring sensor at preset acquisition intervals. The signal conversion module converts the acquired signals into corresponding water pressure data, oil pressure data, flow data, and fracture propagation data. The real-time display module displays the data in real-time as a time curve. The anomaly monitoring module determines whether abnormal conditions have occurred based on built-in evaluation conditions. The feedback control module performs early warning and automatic control operations when abnormal conditions occur. The data analysis module performs a comprehensive evaluation of the fracturing effect based on multi-source data and outputs fracture propagation parameters. The fracture propagation monitoring module monitors the fracture propagation process in real time through distributed fiber optic sensors and downhole cameras, and feeds back fracture morphology data to the feedback control module to achieve active adjustment of the fracturing process. The wireless communication module is used to remotely transmit monitoring data via Bluetooth or fiber optics. The system enables networked access and centralized monitoring of multi-well site data, uploading the data to a cloud server for big data analysis and intelligent decision support. The fracture morphology analysis module identifies fractures using image data collected by downhole camera units and fuses data using multimodal sensors. Through 3D modeling and feature extraction techniques, it accurately analyzes the geometric morphology, spatial distribution, and development trend of fractures, providing quantitative evidence for risk assessment and decision-making. The central processing unit communicates with the data acquisition module, signal conversion module, anomaly monitoring module, feedback control module, data analysis module, and wireless communication module, coordinating the working sequence of each module, allocating computational tasks, and managing data flow. The data storage module locally caches raw data collected by the data acquisition module, data processed by the signal conversion module, and result data generated by the data analysis module, ensuring data integrity even when the network connection to the cloud server is interrupted.

[0091] like Figure 5As shown, the data acquisition module acquires information from various sensors in parallel based on high-frequency acquisition intervals: High-pressure water pressure sensor: Employs a sputtered thin-film piezoresistive sensor, directly installed in the high-pressure zone of the fracturing pipeline, with a typical range of 0-150MPa and an accuracy of ±0.1%FS, used to monitor the pressure dynamics of fluids within the wellbore. Oil pressure sensor: Monitors the pressure of the hydraulic system of the fracturing truck, with a range of 0-40MPa, providing a basis for judging the equipment's operating status. Flow sensor: Uses a high-precision electromagnetic flowmeter, installed on the fluid supply pipeline, to collect the instantaneous and cumulative flow of the fracturing fluid in real time. Fracture propagation monitoring sensor group: This is the core of multimodal monitoring, including: Distributed optical fiber sensor (DAS / DTS): The sensing optical fiber is directly armored in the downhole tubing or implanted via pump, deployed along the entire wellbore, and acquires acoustic vibration and temperature signals through a demodulator to locate the fracture initiation point with meter-level resolution; Downhole camera module: Its specific implementation structure is shown in the figure. Figure 6 As shown. The downhole camera module includes: a cleaning nozzle, connected to the fracturing water channel, used to spray water to remove impurities in front of the lens; an electronic compass, which determines the fracture location based on a magnetoresistive sensor; a local storage unit, used to directly store the acquired image data downhole; and a thermobaric sensor protective housing, a box-shaped structure with side openings, used to protect the temperature and pressure sensors and install the gas guide pipe.

[0092] Thermobarometers: Multiple thermometers are deployed near the perforation cluster to monitor temperature and pressure changes at the fracture inlet. Propionate concentration sensor: A sensor based on ultrasonic attenuation is installed on the outlet pipeline of the sand mixing unit to detect real-time changes in proppant concentration in the proppant-carrying fluid and assess the execution of the proppant addition procedure.

[0093] The raw analog / digital signals collected by the various sensors are transmitted to the signal conversion module. This module consists of a series of signal conditioning circuits and a high-precision ADC (analog-to-digital converter). It is responsible for standardizing signals with different interfaces and protocols and converting them into a unified digital signal format (such as converting a 4-20mA current signal into an engineering floating-point number). This results in regularized data packets of water pressure, oil pressure, flow rate, and crack propagation for use by subsequent modules.

[0094] The converted standard data stream first enters the central processing unit (CPU, typically a high-performance industrial-grade embedded processor). As the system's central hub, the CPU coordinates the timing of each module's operation, allocates computational tasks (such as distributing sensor data packets to display, storage, and analysis modules), and manages the entire system's data flow to ensure real-time performance. Real-time display module: The CPU synchronously sends data to the real-time display module, which drives a high-resolution operator workstation to dynamically display all data in real-time as multi-channel time curves (such as pressure-time, flow-time, and crack length-time curves), providing field engineers with an intuitive visualization of the operating conditions. Anomaly monitoring and feedback control: Its logic flow is as follows... Figure 7 Anomaly Monitoring Module: The CPU sends real-time data to this module, comparing it with built-in multi-dimensional evaluation conditions. These conditions include not only judging whether water pressure, oil pressure, and flow rate data exceed static safety thresholds, but also evaluating dynamic characteristics, such as: whether the slope of the water pressure curve is within the threshold range (judging the fracture pressure point); whether the change in the slope of the water pressure curve after the initial fracturing stage exceeds the threshold (judging whether sand blockage or connection to natural fractures has occurred); whether the deviation between the fracture propagation data and the fracture morphology expected by the integrated geological engineering model exceeds the tolerance value; and whether the fracture propagation rate is within the safe range (preventing uncontrolled fracture height and layer crossing). Feedback Control Module: This module responds immediately once an abnormal condition is determined. Audible and Visual Alarm Unit: Triggers on-site warning lights and buzzers to issue audiovisual alarms. Parameter Adjustment Unit / Fracturing Process Control Unit: For adjustable anomalies, such as fracture propagation deviating from the model, it automatically adjusts parameters such as pump discharge rate and liquid viscosity (by controlling the additive injection pump) to actively adjust the fracture morphology, aiming to achieve an idealized transformation volume of "simple fracture network near the wellbore and complex fracture network far from the wellbore." Emergency Stop Control Unit: In case of severe anomalies (such as pipeline burst pressure warning), a hard-wired signal is sent to automatically stop all fluid supply pumps and the hydraulic system to ensure safety. Adaptive Optimization Unit: Based on the crack propagation parameters of this construction operation and the historical fracturing effect database output by the data analysis module, this unit uses pre-set machine learning algorithms (such as reinforcement learning) to dynamically optimize and adjust the judgment thresholds of the anomaly monitoring module and the control strategies of the parameter adjustment unit, making the system increasingly intelligent with use.

[0095] Data analysis and crack morphology fusion analysis: its data processing and decision support process is as follows Figure 8As shown. Data Analysis Module: This module performs a comprehensive evaluation of the fracturing effect; its operations include: evaluating whether the effective fracturing duration has reached the design threshold based on flow rate and pressure data; evaluating the rationality of the current fracturing curve by comparing the current fracturing curve with historical successful data from adjacent wells built into the database; determining the orientation and potential expansion radius of the main fracture by inverting the geostress state around the wellbore based on real-time water pressure data; evaluating the geometry and orientation of the fracture network by integrating all fracture expansion data, and finally calculating the reservoir stimulation volume (SRV); predicting the fracture height expansion trend based on real-time data and generating specific fracturing process adjustment suggestions (such as "suggest increasing viscosity by 0.5% to control fracture height"). Fracture Morphology Analysis Module: This module receives image data from the downhole camera unit and other multimodal sensor data (fiber optic, thermobarometer). First, it performs noise reduction and enhancement processing on the images, and then uses deep learning algorithms (such as convolutional neural networks, CNN) to automatically identify and delineate fracture edges. Subsequently, it employs multi-sensor data fusion technology to calibrate and overlay the visually identified fracture morphology with the fracture development length monitored by the fiber optic and the inlet parameters monitored by the thermobarometer. Finally, through 3D modeling algorithms (such as finite element analysis) and feature extraction technology, it reconstructs a 3D digital model of the downhole fracture network, accurately outputting the geometric dimensions (length, width, height), spatial distribution (azimuth, dip), and real-time development trend of the fractures, providing quantitative basis for risk assessment and engineering decision-making.

[0096] In summary, this downhole hydraulic fracturing fracture monitoring and feedback system, by incorporating a fracture morphology analysis module and a fracture propagation monitoring module, and employing a multimodal monitoring approach combining distributed fiber optic sensors and downhole camera units, achieves real-time visual monitoring and three-dimensional morphological analysis of the fracture propagation process. This overcomes the response delay problem caused by the reliance on post-processing inversion algorithms in existing technologies, enabling the system to instantly capture dynamic changes in fracture geometry and spatial distribution, providing accurate data for fracturing process adjustments. Furthermore, through the multi-parameter evaluation mechanism of the anomaly monitoring module and the rapid response capability of the feedback control module, a real-time evaluation system based on multi-dimensional safety thresholds such as the slope of the hydraulic pressure curve and the fracture propagation rate is established. This system can identify abnormal operating conditions within seconds and automatically execute parameter adjustments or emergency stop control, reducing the anomaly response time from minutes in traditional technologies to seconds, significantly improving the safety and reliability of fracturing operations. Furthermore, by coordinating the working sequence of each module through the central processing unit, and combining the local caching function of the data storage module and the multi-protocol transmission capability of the wireless communication module, real-time networked query and intelligent decision support of multi-well site data are realized. At the same time, with the help of the fracturing effect comprehensive evaluation function of the data analysis module, the in-situ stress state can be inverted based on real-time data, the fracture height expansion trend can be predicted, and process adjustment suggestions can be generated. This provides accurate decision-making basis for fracturing operations under complex geological conditions, greatly improving reservoir stimulation effect and extraction efficiency.

[0097] This invention provides a computer-readable storage medium including a stored program, wherein, when the program is executed, it controls the device containing the computer-readable storage medium to perform the downhole hydraulic fracturing fracture monitoring and feedback method.

[0098] This invention provides a processor for running a program, wherein the program executes the downhole hydraulic fracturing fracture monitoring and feedback method.

[0099] This invention provides an electronic device, which includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it implements the steps of the aforementioned method for monitoring and responding to hydraulic fracturing fractures in wells. The device described herein can be a server, PC, tablet, mobile phone, etc.

[0100] This application also provides a computer program product that, when executed on a data processing device, is adapted to perform the steps of initializing the monitoring and feedback method for the aforementioned downhole hydraulic fracturing fractures.

[0101] It is obvious to those skilled in the art that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. They can be implemented using computer-executable program code, and thus can be stored in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those described herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0102] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0103] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0104] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0105] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0106] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0107] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0108] Computer-readable media include both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0109] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0110] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0111] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for monitoring and feedback of hydraulic fracturing fractures in wells, characterized in that, include: Acquire downhole multi-source data during the fracturing process, including fracturing pipeline water pressure data, hydraulic system oil pressure data, fracturing fluid flow rate data, fracture propagation morphology data, fracture inlet temperature and pressure data, and proppant concentration data; Anomaly identification was performed on the downhole multi-source data using a preset evaluation threshold, resulting in various anomaly identification results. If any of the anomaly identification results indicates the presence of an abnormal operating condition, a feedback control mechanism is triggered, which includes at least audible and visual early warning and crack propagation morphology adjustment.

2. The method according to claim 1, characterized in that, The various anomaly identification results include a first anomaly identification result, a second anomaly identification result, and a third anomaly identification result. The preset evaluation thresholds include static thresholds, which include preset water pressure thresholds, preset oil pressure thresholds, and preset flow rate thresholds. A preset evaluation mechanism is used to identify anomalies in the downhole multi-source data, resulting in various anomaly identification results, including: Determine whether the water pressure data of the fracturing pipeline exceeds the preset water pressure threshold, and generate the first anomaly identification result; Determine whether the hydraulic system oil pressure data exceeds the preset oil pressure threshold, and generate the second anomaly identification result; Determine whether the fracturing fluid flow rate data exceeds the preset flow rate threshold, and generate the third anomaly identification result.

3. The method according to claim 1, characterized in that, The various anomaly identification results also include a fourth anomaly identification result, a fifth anomaly identification result, a sixth anomaly identification result, and a seventh anomaly identification result. The preset evaluation threshold also includes a dynamic threshold, which includes a preset water pressure slope threshold range, a preset amplitude threshold, a preset tolerance value, and a preset spread rate range. Anomaly identification is performed on the downhole multi-source data using a preset evaluation mechanism to obtain various anomaly identification results, including: Determine whether the slope of the water pressure curve of the fracturing pipeline water pressure data is within the preset water pressure slope threshold range, and generate the fourth anomaly identification result; After a fracturing phase lasting a preset time, it is determined whether the change in the slope of the water pressure curve of the fracturing pipeline water pressure data exceeds the preset amplitude threshold, and the fifth anomaly identification result is generated. Determine whether the spatial deviation between the fracture propagation morphology data and the expected fracture morphology predicted by the integrated geological engineering model exceeds the preset tolerance value, and generate the sixth anomaly identification result. The integrated geological engineering model is a model for predicting fracture propagation based on geological parameters and fracturing parameters. Determine whether the crack propagation rate exceeds the preset propagation rate range, and generate the seventh anomaly identification result.

4. The method according to claim 1, characterized in that, The feedback control mechanism also includes an emergency stop operation, which is triggered when any of the anomaly identification results indicates an abnormal operating condition, including: If any of the above anomaly identification results indicate the existence of an abnormal operating condition, the anomaly level of the abnormal operating condition shall be determined. If the anomaly level is the first anomaly level, the audible and visual warning will be triggered. When the anomaly level is the second anomaly level, the audible and visual warning is triggered and the emergency stop operation is performed. The emergency stop operation includes disconnecting the power input of the liquid supply pump from the hydraulic system. The urgency of the first anomaly level is less than that of the second anomaly level. In cases where the anomaly level is either the first anomaly level or the second anomaly level, the crack propagation morphology adjustment is performed after the audible and visual warning is triggered. The crack propagation morphology adjustment includes adjusting the fracturing pump displacement, liquid viscosity, or proppant concentration.

5. The method according to claim 1, characterized in that, Before acquiring downhole multi-source data during the fracturing process, the method further includes: The fracturing process acquires various sensor signals, including water pressure sensor signals, oil pressure sensor signals, flow sensor signals, fracture propagation monitoring sensor signals, temperature and pressure signals at the fracture inlet, and proppant concentration signals. The sensor signals are converted into a data format to obtain the downhole multi-source data.

6. The method according to claim 5, characterized in that, The fracture propagation monitoring sensor signal includes fracture propagation morphology signal, and acquires multiple sensor signals during the fracturing process, including: The water pressure sensor signal, the oil pressure sensor signal, and the flow sensor signal are acquired using a water pressure sensor, an oil pressure sensor, and a flow sensor, respectively. The fracture propagation morphology signal is acquired using a fracture propagation monitoring sensor group, which includes a distributed fiber optic sensor and a downhole camera module. The temperature and pressure signals at the crack inlet were obtained using a thermobarometer; The proppant concentration signal is acquired using a proppant concentration sensor.

7. The method according to claim 1, characterized in that, The feedback control mechanism also includes adaptive optimization control, which is executed after each fracturing operation, including: Obtain historical fracturing effect data from the historical fracturing database; Based on the fracture propagation morphology data of the current fracturing operation and the historical fracturing effect data, a machine learning algorithm is used to update the preset evaluation threshold and the control parameters used to adjust the fracture propagation morphology.

8. The method according to claim 1, characterized in that, After acquiring downhole multi-source data during the fracturing process, the method further includes at least one of the following fracturing effect evaluation operations: Based on the hydraulic pressure data of the fracturing pipeline, the oil pressure data of the hydraulic system, and the fracturing fluid flow rate data, it is determined whether the duration of the current fracturing operation meets the preset process threshold. The water pressure versus time curve and flow rate versus time curve during the current fracturing process are compared with historical successful fracturing curves stored in the database to determine whether the current fracturing process conforms to the preset typical fracturing response mode. Based on the hydraulic pressure data of the fracturing pipeline, the fracture orientation and propagation radius are determined using a pressure inversion model. Based on the fracture propagation morphology data, the temperature and pressure data at the fracture inlet, and the proppant concentration data, the geometry and spatial orientation of the fracture are evaluated, and the reservoir stimulation volume is calculated.

9. A monitoring and feedback device for downhole hydraulic fracturing fractures, characterized in that, include: The first acquisition unit is used to acquire downhole multi-source data during the fracturing process. The downhole multi-source data includes fracturing pipeline water pressure data, hydraulic system oil pressure data, fracturing fluid flow data, fracture propagation morphology data, fracture inlet temperature and pressure data, and proppant concentration data. The identification unit is used to identify anomalies in the downhole multi-source data using a preset evaluation threshold, and to obtain various anomaly identification results. A triggering unit is used to trigger a feedback control mechanism when any of the anomaly identification results in the plurality of anomaly identification results indicates the existence of an abnormal working condition. The feedback control mechanism includes at least an audible and visual warning and crack propagation morphology adjustment.

10. A monitoring and feedback system for downhole hydraulic fracturing fractures, characterized in that, include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including a method for monitoring and responding to downhole hydraulic fracturing fractures as described in any one of claims 1 to 8.

Images