Method, device and electronic equipment for predicting water discharge from tunnel during surface fracturing

Abstract

The present application proposes a method, device, and electronic device for predicting water discharge in a roadway during surface fracturing. The method includes: obtaining first pressure data from the fracturing wellhead history during coal rock roof fracturing, the first pressure data including at least the pressure curve at the wellhead; determining the fracturing stage of the coal rock roof fracturing based on the pressure curve, and determining the pressure curve characteristics corresponding to the pressure curve; determining a data set of the first water discharge event in the roadway history, and determining prior information for predicting water discharge in the roadway based on the data set, the fracturing stage, and the pressure curve characteristics; and predicting the second water discharge event in the roadway based on the prior information and the real-time second pressure data at the fracturing wellhead. Therefore, this solution can predict water discharge events in the roadway during coal rock roof fracturing based on a small amount of prior information, providing theoretical and technical support for real-time adjustment of fracturing parameters and fracturing schemes, thereby improving the fracturing effect.

Description

Technical Field

[0001] The present application relates to the field of coal mining technology, and in particular to a method, device and electronic equipment for predicting water discharge from a roadway during ground fracturing. Background Art

[0002] Surface hydraulic fracturing technology has been widely used to prevent and control coal seam roof pressure. The key technique involves injecting high-pressure liquid into the roof within a hundred meters above the coal seam to create pre-fabricated cracks, altering the roof structure and ground stress state to achieve pressure relief. However, during surface hydraulic fracturing, the fracture morphology is difficult to control, and it is common for fractures to penetrate into roadways, leading to severe water leakage and impacting roadway operations. Summary of the Invention

[0003] The purpose of this application is to solve one of the technical problems in the related art at least to a certain extent.

[0004] To this end, the first purpose of this application is to propose a method for predicting water discharge from a roadway during surface fracturing, so as to predict water discharge events from a roadway during coal roof fracturing based on a small amount of prior information.

[0005] The second purpose of this application is to provide a device for predicting water discharge from tunnels during ground fracturing.

[0006] The third objective of this application is to provide an electronic device.

[0007] The fourth object of this application is to provide a computer-readable storage medium.

[0008] A fifth object of this application is to provide a computer program product.

[0009] To achieve the above-mentioned purpose, the first embodiment of the present application proposes a method for predicting water discharge from a tunnel during ground fracturing, comprising: obtaining first pressure data of the wellhead history during coal rock roof fracturing, the first pressure data at least including the fracturing wellhead pressure; determining the fracturing stage of the coal rock roof fracturing based on the pressure curve, and determining the pressure curve characteristics corresponding to the pressure curve; determining a data set of the first water discharge event in the tunnel history, and determining prior information for predicting water discharge from the tunnel based on the data set, the fracturing stage, and the pressure curve characteristics; and predicting the second water discharge event from the tunnel based on the prior information and the real-time second pressure data of the wellhead.

[0010] To achieve the above-mentioned purpose, the second embodiment of the present application proposes a device for predicting water output from a tunnel during ground fracturing, including: an acquisition module for acquiring first pressure data of the fracturing wellhead history during coal rock roof fracturing, the first pressure data including at least the pressure curve of the wellhead; a first determination module for determining the fracturing stage of the coal rock roof fracturing based on the pressure curve, and determining the pressure curve characteristics corresponding to the pressure curve; a second determination module for determining a data set of the first water output event in the tunnel history, and determining the prior information for predicting water output from the tunnel based on the data set, the fracturing stage, and the pressure curve characteristics; a prediction module for predicting the second water output event in the tunnel based on the prior information and the real-time second pressure data of the fracturing wellhead.

[0011] To achieve the above-mentioned purpose, the third embodiment of the present application proposes an electronic device, comprising: a processor; and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory, so that the processor can execute the method for predicting water discharge from the tunnel during ground fracturing as described in the first embodiment above.

[0012] To achieve the above-mentioned purpose, the fourth embodiment of the present application proposes a computer-readable storage medium having a computer program stored thereon, wherein the computer instructions are used to enable the computer to execute the method for predicting water discharge from the tunnel during ground fracturing described in the first embodiment above.

[0013] To achieve the above-mentioned purpose, the fifth embodiment of the present application proposes a computer program product, including a computer program, which, when executed by a processor, implements the method for predicting water production in the tunnel during ground fracturing described in the first embodiment above.

[0014] The present application provides a method, device and electronic device for predicting water discharge in the roadway during ground fracturing, which obtains the first pressure data of the wellhead history, determines the fracturing stage of the coal rock roof fracturing, and the pressure curve characteristics corresponding to the pressure curve, and further determines the data set of the first water discharge event in the roadway history, and determines the prior information based on the data set, the fracturing stage, and the pressure curve characteristics, so that the second water discharge event in the roadway can be predicted based on the prior information and the real-time second pressure data of the wellhead. In this way, it is possible to predict the water discharge event in the roadway during coal rock roof fracturing based on a small amount of prior information, provide theoretical and technical support for real-time adjustment of fracturing parameters and fracturing schemes, and thus improve the fracturing effect. By predicting the water discharge event, the potential water discharge risk of the roadway can be discovered in advance, so that timely measures can be taken to prevent it, and avoid the water discharge event from threatening mine production and miners' safety.

[0015] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0017] Figure 1 A schematic flow chart of a method for predicting water discharge from a tunnel during surface fracturing provided in an embodiment of the present application;

[0018] Figure 2 A schematic diagram of a pressure curve provided in an embodiment of the present application;

[0019] Figure 3 A flow chart of another method for predicting water discharge from a roadway during surface fracturing provided in an embodiment of the present application;

[0020] Figure 4 A schematic diagram of key feature labels for different water output events provided in an embodiment of the present application;

[0021] Figure 5 A flow chart of another method for predicting water discharge from a roadway during surface fracturing provided in an embodiment of the present application;

[0022] Figure 6 A flow chart of another method for predicting water discharge from a roadway during surface fracturing provided in an embodiment of the present application;

[0023] Figure 7 A schematic diagram of energy characteristics provided by an embodiment of the present application;

[0024] Figure 8 This is a schematic diagram of the structure of a device for predicting water outflow in a tunnel during ground fracturing provided in an embodiment of the present application. DETAILED DESCRIPTION

[0025] The following describes in detail embodiments of the present application, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0026] The following describes a method and apparatus for predicting water discharge from a tunnel during surface fracturing according to an embodiment of the present application with reference to the accompanying drawings.

[0027] Figure 1 This is a flow chart of a method for predicting water discharge from a tunnel during ground fracturing according to an embodiment of the present application. Figure 1As shown, the method for predicting water discharge in the tunnel during surface fracturing in the embodiment of the present application includes but is not limited to the following steps:

[0028] S101, obtaining first pressure data of a fracturing wellhead history during coal rock roof fracturing, the first pressure data at least including a pressure curve of the wellhead.

[0029] It should be noted that the execution subject of the method for predicting water discharge from a roadway during ground fracturing provided in the embodiments of the present application is an electronic device, which may be a terminal device. Optionally, the terminal device may be a mobile electronic device or a non-mobile electronic device. For example, the mobile electronic device may be a mobile phone, tablet computer, laptop computer, PDA, in-vehicle electronic device, wearable device, ultra-mobile personal computer (UMPC), netbook, or personal digital assistant (PDA), etc., and the non-mobile electronic device may be a personal computer (PC), a television, etc. The embodiments of the present application are not specifically limited.

[0030] In some embodiments, when the coal rock roof is fractured, pressure measuring equipment can be used to collect pressure data at the wellhead, and a pressure curve can be generated based on the collected pressure data, and first pressure data can be generated based on the pressure curve and the pressure data, where the pressure data can be second-level pressure data.

[0031] In some embodiments, the volume of the fracturing fluid may be recorded during the fracturing of the coal rock roof, and the volume of the fracturing fluid may be correlated with the pressure curve to obtain a curve related to the pressure and the volume of the fracturing fluid, such as Figure 2 The schematic diagram of the pressure curve is shown in Figure 2 The displacement curve includes a pressure curve and a volume of the fracturing fluid. According to the pressure curve and the displacement curve, it can be seen that the displacement changes with the pressure. The greater the pressure, the greater the displacement.

[0032] In some embodiments, the first pressure data may be preprocessed to eliminate random noise in the first pressure data.

[0033] In some embodiments, a wavelet threshold denoising method may be used to clean random noise in the first pressure data. By performing thresholding processing on high frequency coefficients in the wavelet transform domain, noise may be removed while retaining the main features of the signal.

[0034] It can be understood that signals are usually concentrated in low frequencies and have larger wavelet coefficients; noise is usually distributed in high frequencies and has smaller wavelet coefficients. In other words, signals with wavelet coefficients greater than a threshold can be filtered to obtain a noise-removed signal.

[0035] In some embodiments, a wavelet transform is performed on the first pressure data to decompose a signal in the first pressure data to obtain a decomposed signal, wherein the decomposed signal has different wavelet coefficients. Furthermore, a threshold function is used to perform thresholding on the decomposed signal, and then an inverse wavelet transform is used to reconstruct the thresholded signal to obtain pressure data with random noise eliminated.

[0036] For example, let the signal with noise be f n (i) = f(i) + e(i), where e(i) is noise and the original signal is f(i). Then the decomposed signal obtained by wavelet decomposition of the noisy signal can be expressed as W j [k]=W(f n (i)), further, the thresholding of the coefficients of the decomposed signal can be expressed as Where T is the threshold function, λ is the threshold, and further, the inverse wavelet transform is performed to reconstruct the signal, which can be expressed as

[0037] Among them, the threshold function uses a soft threshold, which can shrink large coefficients while eliminating small coefficients, thereby reducing the deviation of the threshold. The formula is as follows:

[0038]

[0039] The calculation formula of the threshold λ is as follows:

[0040]

[0041] Where σ is the noise standard deviation, which is usually estimated by the high-frequency wavelet coefficients; MAD is the median absolute deviation of the wavelet coefficients; and n is the number of sampling points of the signal.

[0042] S102: Determine the fracturing stage of the coal rock roof fracturing based on the pressure curve, and determine the pressure curve characteristics corresponding to the pressure curve.

[0043] In some embodiments, the fracturing stages of coal rock roof fracturing are divided into a displacement increase stage, a constant displacement stage, and a temporary plugging stage.

[0044] In some embodiments, the fracturing stages of coal rock roof fracturing can be divided into the following stages according to the pressure curve: Figure 2As shown in the pressure curve and displacement curve, when the pressure curve and the displacement curve are in the rising stage, the fracturing stage of the coal rock roof fracturing is the displacement increase stage; when the pressure curve and the displacement curve are in the horizontal unchanged stage and are after the displacement increase stage, the fracturing stage of the coal rock roof fracturing is the constant displacement stage; when the pressure curve and the displacement curve are after the constant displacement stage and before the next displacement increase stage, the fracturing stage of the coal rock roof fracturing is the temporary plugging stage. Figure 2 There are 3 displacement increase stages, 3 constant displacement stages, and 2 temporary blockage events.

[0045] In some embodiments, the pressure curve characteristics include time-frequency characteristics and energy characteristics of the pressure curve.

[0046] In some embodiments, the time-frequency characteristics of the pressure curve may be obtained by performing wavelet transform on the pressure curve, and then the time-frequency characteristics may be filtered according to a frequency threshold to obtain the energy characteristics of the pressure curve.

[0047] Optionally, the time-frequency feature that is smaller than the frequency threshold may be used as the energy feature.

[0048] S103, determining a data set of the first water discharge event in the history of the roadway, and determining prior information for predicting water discharge in the roadway based on the data set, the fracturing stage, and the pressure curve characteristics.

[0049] In some embodiments, a data set may be established based on the discharge time and discharge volume of the first water discharge event in the lane history. The data set for the first water discharge event is established by obtaining the first water discharge event in the lane history, determining the discharge time and discharge volume of the first water discharge event, and then based on the discharge time and discharge volume.

[0050] In some embodiments, the water output type of the first water output event can be determined based on the data set, and the pressure curve characteristics corresponding to the fracturing stage can be determined. Then, based on the water output type, the fracturing stage, and the pressure curve characteristics corresponding to the fracturing stage, prior information for predicting water output in the tunnel can be generated.

[0051] In some embodiments, the water output type of the first water output event can be determined based on the size of the water output in the data set. If the water output is greater than the water output threshold, the water output type of the first water output event is determined to be large water output; if the water output is less than or equal to the water output threshold, the water output type of the first water output event is determined to be small water output.

[0052] S104 , predicting a second water-discharge event in the tunnel based on the prior information and the real-time second pressure data at the fracturing wellhead.

[0053] In some embodiments, a small sample machine learning model can be established based on prior information, and the real-time second pressure data of the wellhead can be input into the model. The model can make predictions based on the second pressure data to obtain the predicted second water discharge event in the tunnel.

[0054] In some embodiments, the small sample machine learning model can predict whether there is a second water outflow event in the tunnel, and when it is determined that there is a second water outflow event, predict the water outflow time and water outflow volume of the second water outflow event, and then adjust the fracturing parameters according to the amount of water outflow to reduce the water outflow of the tunnel.

[0055] In the method for predicting water discharge from a tunnel during ground fracturing provided in an embodiment of the present application, by obtaining the first pressure data of the tunnel history, and determining the fracturing stage of the coal rock roof fracturing, and the pressure curve characteristics corresponding to the pressure curve, a data set of the first water discharge event in the tunnel history is further determined, and based on the data set, the fracturing stage, and the pressure curve characteristics, prior information is determined, so that the second water discharge event in the tunnel can be predicted based on the prior information and the real-time second pressure data of the wellhead. In this way, it is possible to predict the water discharge event in the tunnel during coal rock roof fracturing based on a small amount of prior information, providing theoretical and technical support for real-time adjustment of fracturing parameters and fracturing schemes, thereby improving the fracturing effect. By predicting the water discharge event, the potential water discharge risk of the tunnel can be discovered in advance, so that timely measures can be taken to prevent it, avoiding the threat posed by the water discharge event to mine production and miners' safety.

[0056] Figure 3 This is a flow chart of a method for predicting water discharge from a tunnel during ground fracturing according to an embodiment of the present application. Figure 3 As shown, the method for predicting water discharge in the tunnel during surface fracturing in the embodiment of the present application includes but is not limited to the following steps:

[0057] S301, obtaining first pressure data of the fracturing wellhead history during coal rock roof fracturing, the first pressure data at least including a pressure curve of the wellhead.

[0058] In the embodiment of the present application, the implementation method of step S301 can be implemented by any method in the various embodiments of the present application, which is not limited here and will not be repeated.

[0059] S302: Determine the fracturing stage of the coal rock roof fracturing based on the pressure curve, and determine the pressure curve characteristics corresponding to the pressure curve.

[0060] In the embodiment of the present application, the implementation method of step S302 can be implemented by any method in the various embodiments of the present application, which is not limited here and will not be repeated.

[0061] S303: Determine the water discharge time and water discharge volume of the first water discharge event.

[0062] S304: Establish a data set based on the water output time and water output.

[0063] In some embodiments, the data set includes two columns of information: water outflow time and water outflow volume, which is obtained by obtaining the first water outflow event in history and determining the water outflow time of the first water outflow event.

[0064] In some embodiments, after water is discharged from the tunnel, the water accumulates inside the tunnel and needs to be pumped out. During the pumping process, the pumping rate and the residual water volume within the time T can be recorded, and then the water output of the first water discharge event can be calculated based on the pumping rate and the residual water volume.

[0065] Alternatively, the formula for calculating the water output is as follows:

[0066]

[0067] Among them, Fluid Rate represents the water output, V ext represents the pumping rate, T represents the time, V res Indicates the residual water amount.

[0068] For example, a data set of the first water production event can be generated according to the fracturing stage, and the data set can be expressed as: The first column in the data set represents different fracturing stages, and the second column shows the amount of water.

[0069] S305 , matching the first water production event with the fracturing stage based on the water production time, and determining a target fracturing stage corresponding to the first water production event.

[0070] In some embodiments, the target fracturing stage corresponding to the first water production event is determined by determining the water production time of the first water production event and matching the first water production event with the fracturing stage according to the water production time.

[0071] For example, Figure 2 Taking the first rate increase stage as an example, if the time period of the first rate increase stage is AB, the time when the first water production event 1 occurs is C, and C is between AB, then the target fracturing stage corresponding to the first water production event 1 is determined to be the first rate increase stage.

[0072] S306 , determining target pressure curve characteristics of the target fracturing stage based on the pressure curve characteristics, and extracting key features of the target pressure curve characteristics.

[0073] In some embodiments, the pressure curve characteristics corresponding to different fracturing stages can be determined based on the pressure curve and the pressure curve characteristics, by determining the target fracturing stage corresponding to each first water production event in the data set, and determining the target pressure curve characteristics of the target fracturing stage from the pressure curve characteristics corresponding to the different fracturing stages.

[0074] Furthermore, a key feature may be extracted from the target pressure curve feature, where the key feature may be a peak feature in the target pressure curve feature.

[0075] Optionally, labels can be created at key features, such as Figure 4 Schematic diagram of key feature labels for different water output events shown. Figure 4 In the method, large water discharge events and small water discharge events are divided according to the water discharge volume. The target pressure curve feature is the signal energy feature, and the peak of the signal energy feature is determined as the key feature. Then, labels are established at the peak, which are the key feature labels of small water discharge events and large water discharge events respectively.

[0076] S307: Determine the water production type of the target fracturing stage based on the water production of the first water production event.

[0077] In some embodiments, the water production type of the target fracturing stage is determined by determining a water production threshold and comparing the water production of the first water production event with the water production threshold.

[0078] In some embodiments, in response to the water output of the first water output event being greater than a water output threshold, the water output type of the first water output event is determined to be large water output; in response to the water output of the first water output event being less than or equal to the water output threshold, the water output type of the first water output event is determined to be small water output.

[0079] S308 , generating prior information based on the target fracturing stage, key characteristics, and water production type.

[0080] In some embodiments, a priori information can be obtained by combining target fracturing stages, key characteristics, and water production types.

[0081] For example, assume that the target fracturing stage is the 1st to 5th stage, the key features corresponding to the first 4 stages are the key features of small water production events, and the key features corresponding to the 5th stage are the key features of large water production events. In other words, the water production type corresponding to the first 4 stages is small water production, and the water production type corresponding to the 5th stage is large water production. The generated prior information is as follows:

[0082]

[0083] S309 , predicting a second water discharge event in the tunnel based on the prior information and the real-time second pressure data at the wellhead.

[0084] In the embodiment of the present application, the implementation method of step S309 can be implemented by any method in the various embodiments of the present application, which is not limited here and will not be repeated.

[0085] In the method for predicting water discharge from a roadway during surface fracturing provided in an embodiment of the present application, the target fracturing stage corresponding to the first water discharge event is determined, and the target pressure curve characteristics of the target fracturing stage are determined based on the pressure curve characteristics, thereby extracting the key features of the target pressure curve characteristics. The water discharge type of the target fracturing stage is further determined to generate prior information based on the target fracturing stage, key characteristics, and water discharge type. Thus, by generating prior information based on the target fracturing stage, key characteristics, and water discharge type, it is possible to more accurately assess water discharge events in the roadway, thereby providing data support for predicting water discharge events in the roadway during coal roof fracturing, further improving the accuracy of water discharge event prediction.

[0086] Figure 5 This is a flow chart of a method for predicting water discharge from a tunnel during ground fracturing according to an embodiment of the present application. Figure 5 As shown, the method for predicting water discharge in the tunnel during surface fracturing in the embodiment of the present application includes but is not limited to the following steps:

[0087] S501, obtaining first pressure data of the fracturing wellhead history during coal rock roof fracturing, the first pressure data at least including a pressure curve of the wellhead.

[0088] In the embodiment of the present application, the implementation method of step S501 can be implemented by any method in the various embodiments of the present application, which is not limited here and will not be repeated.

[0089] S502: Determine the fracturing stage of the coal rock roof fracturing based on the pressure curve, and determine the pressure curve characteristics corresponding to the pressure curve.

[0090] In the embodiment of the present application, the implementation method of step S502 can be implemented by any method in the various embodiments of the present application, which is not limited here and will not be repeated.

[0091] S503 , determining a data set of the first water discharge event in the history of the roadway, and determining prior information for predicting water discharge in the roadway based on the data set, the fracturing stage, and the pressure curve characteristics.

[0092] In the embodiment of the present application, the implementation method of step S503 can be implemented by any method in the various embodiments of the present application, which is not limited here and will not be repeated.

[0093] S504, establishing a small sample machine learning model based on prior information.

[0094] S505 , determining prediction information of the lane based on the small sample machine learning model and the second pressure data.

[0095] S506 : In response to the prediction information indicating the presence of a second water outflow event, determining the second water outflow event and a water outflow type corresponding to the second water outflow event.

[0096] In some embodiments, a small sample machine learning model is obtained by determining a machine learning algorithm that performs well in a small sample case, using the machine learning algorithm to train a model, and determining the hyperparameters of the model based on prior information, so as to achieve the establishment of a small sample machine learning model based on prior information.

[0097] In some embodiments, by collecting real-time second pressure data at the wellhead and determining the pressure curve characteristics corresponding to the second pressure data based on the pressure curve in the second pressure data, the pressure curve characteristics corresponding to the second pressure data are input into a small sample machine learning model, and combined with the Bayesian learning method, the small sample machine learning model predicts water outflow events in the tunnel, thereby outputting prediction information.

[0098] Alternatively, the algorithm for determining the prediction information can be expressed as:

[0099]

[0100] Wherein, P(θ|D) represents prediction information, P(D|θ) represents likelihood function, P(θ) represents prior information, and P(D) represents pressure curve characteristics corresponding to the second pressure data.

[0101] In some embodiments, it is possible to determine from the prediction information whether there is a second water discharge event in the lane, and when the prediction information indicates the presence of a second water discharge event, determine the water discharge volume corresponding to the second water discharge event, and determine the water discharge type corresponding to the second water discharge event based on the water discharge volume.

[0102] In some embodiments, in response to the water output type corresponding to the second water output event being large water output, that is, in response to the water output type corresponding to the second water output event indicating that the water output in the roadway is greater than the water output threshold, the fracturing parameters of the coal rock roof fracturing are adjusted to reduce the water output in the roadway.

[0103] Optionally, the fracturing parameters of the coal rock roof fracturing may be the amount of fracturing fluid used and the number of temporary pluggings. By reducing the amount of fracturing fluid used and performing multiple temporary pluggings, the water output of the roadway can be reduced.

[0104] It is understandable that the large amount of water output in the tunnel during fracturing may be caused by the expansion of the cracks to the tunnel surface or the connection and communication with the formation structure in the tunnel, which causes a large amount of fracturing fluid to flow to the tunnel surface during fracturing, resulting in a large amount of water output. Reducing the amount of fracturing fluid can reduce the water output in the tunnel.

[0105] Temporary plugging can seal the original cracks and create new cracks, so that the fracturing fluid can be used to increase the volume of crack transformation, thereby reducing the water output of the tunnel.

[0106] In the method for predicting water discharge in a roadway during surface fracturing provided in an embodiment of the present application, a small sample machine learning model is established based on prior information, and prediction information for the roadway is determined based on the small sample machine learning model and the second pressure data. When the prediction information indicates the presence of a second water discharge event, the second water discharge event and the corresponding water discharge type are determined. Thus, by predicting water discharge events, potential water discharge risks in the roadway can be discovered in advance, allowing timely preventive measures to be taken to avoid threats to mine production and miner safety posed by water discharge events.

[0107] Figure 6 This is a flow chart of a method for predicting water discharge from a tunnel during ground fracturing according to an embodiment of the present application. Figure 6 As shown, the method for predicting water discharge in the tunnel during surface fracturing in the embodiment of the present application includes but is not limited to the following steps:

[0108] S601, obtaining first pressure data of the fracturing wellhead history during coal rock roof fracturing, the first pressure data at least including a pressure curve of the wellhead.

[0109] In the embodiment of the present application, the implementation method of step S601 can be implemented by any method in the various embodiments of the present application, which is not limited here and will not be repeated.

[0110] S602: Determine the fracturing stage of the coal roof fracturing based on the pressure curve.

[0111] In the embodiment of the present application, the implementation method of step S602 can be implemented by any method in the various embodiments of the present application, which is not limited here and will not be repeated.

[0112] S603 , performing wavelet transform processing on the pressure curve to obtain time-frequency features of the pressure curve, where the time-frequency features include time domain features and frequency domain features.

[0113] In some embodiments, the time-frequency characteristics of the pressure curve may be obtained by performing wavelet transform on the pressure curve and analyzing the time-domain characteristics and frequency-domain characteristics of the pressure curve.

[0114] Optionally, the formula for wavelet transform processing is as follows:

[0115]

[0116] Among them, W n(s) is a continuous function, * represents the complex conjugate, N is the length of the data sequence, s is the wavelet scale, δ t is the sampling interval and n is the local time index.

[0117] Alternatively, a complex Gaussian windowed sine wave can be used for time-frequency analysis of continuous signals, which is defined in the time and frequency domains as follows:

[0118]

[0119]

[0120] Where η is the dimensionless time parameter, m is the wave number, ω is the frequency, and H is the function. Using time as the horizontal axis and frequency as the vertical axis, the signal components are displayed at different times and frequencies.

[0121] S604: Obtain a set frequency threshold, and filter the time-frequency feature based on the set frequency threshold to obtain an energy feature of the pressure curve.

[0122] S605: Use the time-frequency feature and the energy feature as pressure curve features.

[0123] In some embodiments, by determining a set frequency threshold, the time-frequency features are filtered according to the set frequency threshold to extract the energy features of the pressure curve. For example, the energy features less than f can be extracted. k The time-frequency characteristics of are used as energy features. The schematic diagram of the extracted energy features is shown in Figure 7 shown.

[0124] That is, based on the set frequency threshold, the time-frequency features greater than the set frequency threshold are filtered to obtain the energy features of the pressure curve.

[0125] Furthermore, the time-frequency characteristics and energy characteristics can be used as pressure curve characteristics.

[0126] S606 , determining a data set of the first water discharge event in the history of the roadway, and determining prior information for predicting water discharge in the roadway based on the data set, the fracturing stage, and the pressure curve characteristics.

[0127] In the embodiment of the present application, the implementation method of step S606 can be implemented by any method in the various embodiments of the present application, which is not limited here and will not be repeated.

[0128] S607 , predicting a second water-discharge event in the tunnel based on the prior information and the real-time second pressure data at the fracturing wellhead.

[0129] In the embodiment of the present application, the implementation method of step S607 can be implemented by any method in the various embodiments of the present application, which is not limited here and will not be repeated.

[0130] In the method for predicting tunnel water discharge during surface fracturing provided in the embodiments of the present application, a wavelet transform is performed on the pressure curve to obtain the time-frequency characteristics of the pressure curve. The time-frequency characteristics are then filtered according to a set frequency threshold to obtain the energy characteristics of the pressure curve. The time-frequency characteristics and energy characteristics are then used as pressure curve features. Thus, using the time-frequency characteristics and energy characteristics as pressure curve features can capture dynamic changes in pressure, simplify pressure data processing, and enable comprehensive analysis of pressure data.

[0131] For example, a horizontal well in Hongqinghe Coal Mine is parallel to the working face rubber transport drift, about 2,600 meters in front of the cutting face, about 80 meters from the outer rubber transport lane, and about 60 meters vertically above the coal seam. The lithology of the horizontal well is the sandstone of the Zhiluo Formation, which is the thick hard roof above the coal seam. A fracturing cluster is set up in the horizontal section of the horizontal well for fracturing construction. The hydraulic pumping cable bridge plug cluster perforation process is used. Low-viscosity slickwater fracturing fluid is used, and the designed fluid volume per section is 1,300m 3 , designed 2 temporary pluggings, each time using 250kg of temporary plugging agent, and a total of 17 fracturing sections were designed.

[0132] By recording the first pressure data of the wellhead during the fracturing process and performing data preprocessing;

[0133] The water output events in the first five fracturing stages during the fracturing process were classified as follows: the water output in stages 1 to 4 was small (15-20m 3 / h), the 5th section has a large water output (50m 3 / h), by pre-processing the 1st to 5th fracturing curves, performing continuous wavelet transform processing and analyzing them in stages, the differences in the time-frequency characteristics of pressure in different stages of the fracturing sections with different water outflow events were identified, and a data set of tunnel water outflow events was formed:

[0134]

[0135] Extracting less than f based on time-frequency features k Signal energy characteristics at frequencies <0.4Hz, and the time-frequency characteristics and energy characteristics are used as pressure curve characteristics;

[0136] Extract key features of the pressure curve and establish labels: The key feature label for low-water-yield events is: the signal energy in the displacement increase phase after temporary plugging in the 1st to 4th fracturing stages presents a single peak or multiple peaks; the key feature label for high-water-yield events is: the signal energy in the displacement increase phase after temporary plugging in the 5th fracturing stage presents no rising segment before the peak, and only a falling segment after the peak. Prior information is established based on these key feature labels.

[0137]

[0138] Furthermore, water outflow events are predicted based on prior information:

[0139] During the 6th stage fracturing process, the second pressure data was recorded and processed by continuous wavelet transform in real time. Based on the prior information, a small sample machine learning model was established. The model was used to predict the occurrence of a large water flow event in the 6th stage tunnel. The prediction was completed within 3 minutes of the occurrence of the key features of the large water flow event. According to the tunnel water flow monitoring, it was confirmed that the tunnel water flow during the 6th stage fracturing was about 50m 3 / h.

[0140] The above-mentioned embodiments correspond to the methods for predicting water outflow from the tunnel during ground fracturing. An embodiment of the present application further proposes a device for predicting water outflow from the tunnel during ground fracturing. Since the device for predicting water outflow from the tunnel during ground fracturing proposed in the embodiment of the present application corresponds to the methods for predicting water outflow from the tunnel during ground fracturing proposed in the above-mentioned embodiments, the implementation methods of the above-mentioned methods for predicting water outflow from the tunnel during ground fracturing are also applicable to the device for predicting water outflow from the tunnel during ground fracturing proposed in the embodiment of the present application, and will not be described in detail in the following embodiments.

[0141] In order to implement the above embodiment, the present application also proposes a device for predicting water discharge in tunnels during surface fracturing.

[0142] Figure 8 A schematic diagram of the structure of a device for predicting water outflow in a tunnel during ground fracturing provided in an embodiment of the present application.

[0143] like Figure 8 As shown, the device 800 for predicting water discharge in a roadway during surface fracturing includes:

[0144] An acquisition module 801 is configured to acquire first pressure data of a fracturing wellhead history during coal rock roof fracturing, wherein the first pressure data at least includes a pressure curve of the wellhead;

[0145] A first determining module 802 is configured to determine a fracturing stage of the coal roof fracturing based on the pressure curve, and determine a pressure curve feature corresponding to the pressure curve;

[0146] The second determination module 803 is used to determine a data set of the first water discharge event in the history of the roadway, and determine the prior information for predicting water discharge in the roadway based on the data set, the fracturing stage, and the pressure curve characteristics;

[0147] Prediction module 804 is configured to predict a second water outflow event in the tunnel based on prior information and real-time second pressure data at the fracturing wellhead. In one possible implementation of the embodiment of the present application, second determination module 803 is further configured to: determine the water outflow time and water outflow volume of the first water outflow event; and establish a data set based on the water outflow time and water outflow volume.

[0148] In a possible implementation of an embodiment of the present application, the second determination module 803 is further used to: match the first water discharge event with the fracturing stage based on the water discharge time, and determine the target fracturing stage corresponding to the first water discharge event; determine the target pressure curve characteristics of the target fracturing stage based on the pressure curve characteristics, and extract the key characteristics of the target pressure curve characteristics; determine the water discharge type of the target fracturing stage based on the water discharge volume of the first water discharge event; and generate prior information based on the target fracturing stage, key characteristics and water discharge type.

[0149] In a possible implementation of an embodiment of the present application, the prediction module 804 is also used to: establish a small sample machine learning model based on prior information; determine the prediction information of the tunnel based on the small sample machine learning model and the second pressure data; and in response to the prediction information indicating the presence of a second water outflow event, determine the second water outflow event and the water outflow type corresponding to the second water outflow event.

[0150] In a possible implementation of an embodiment of the present application, the prediction module 804 is also used to: in response to the water output type corresponding to the second water output event indicating that the water output of the tunnel is greater than the water output threshold, adjust the fracturing parameters of the coal rock roof fracturing to reduce the water output of the tunnel.

[0151] In a possible implementation of an embodiment of the present application, the first determination module 802 is further used to: perform wavelet transform processing on the pressure curve to obtain the time-frequency characteristics of the pressure curve, where the time-frequency characteristics include time domain characteristics and frequency domain characteristics; obtain a set frequency threshold, and filter the time-frequency characteristics based on the set frequency threshold to obtain the energy characteristics of the pressure curve; and use the time-frequency characteristics and energy characteristics as pressure curve characteristics.

[0152] In the prediction device for water discharge in the roadway during ground fracturing provided in the embodiment of the present application, by obtaining the first pressure data of the roadway history, and determining the fracturing stage of the coal rock roof fracturing, and the pressure curve characteristics corresponding to the pressure curve, the data set of the first water discharge event in the roadway history is further determined, and based on the data set, the fracturing stage, and the pressure curve characteristics, the prior information is determined, so that the second water discharge event in the roadway can be predicted based on the prior information and the real-time second pressure data of the wellhead. In this way, it is possible to predict the water discharge event in the roadway during coal rock roof fracturing based on a small amount of prior information, provide theoretical and technical support for real-time adjustment of fracturing parameters and fracturing schemes, thereby improving the fracturing effect. By predicting the water discharge event, the potential water discharge risk of the roadway can be discovered in advance, so that timely measures can be taken to prevent it, and avoid the water discharge event from threatening mine production and miners' safety.

[0153] It should be noted that the above explanation of the embodiment of the method for predicting water discharge from a tunnel during surface fracturing is also applicable to the device for predicting water discharge from a tunnel during surface fracturing in this embodiment, and will not be repeated here.

[0154] In order to implement the above embodiments, the present application also proposes an electronic device, comprising: a processor, and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the method provided by the above embodiments.

[0155] In order to implement the above embodiments, the present application also proposes a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the methods provided by the above embodiments.

[0156] In order to implement the above embodiments, the present application also proposes a computer program product, including a computer program, which implements the methods provided by the above embodiments when executed by a processor.

[0157] The collection, storage, use, processing, transmission, provision and application of user personal information involved in this application are in compliance with relevant laws and regulations and do not violate public order and good morals.

[0158] It is important to note that personal information collected from users should be used for legitimate and reasonable purposes and should not be shared or sold beyond these legitimate uses. Furthermore, such collection / sharing should be conducted only after receiving the user's informed consent, including but not limited to notifying the user to read the user agreement / user notice and sign an agreement / authorization that includes the relevant user information before using the feature. Furthermore, any necessary steps must be taken to safeguard and secure access to such personal information and ensure that others with access to personal information comply with its privacy policy and procedures.

[0159] This application contemplates providing implementation options for users to selectively block the use or access of personal information data. Specifically, this application contemplates providing hardware and / or software to prevent or block access to such personal information data. Risks can be minimized by limiting data collection and deleting data once it is no longer needed. Furthermore, where applicable, such personal information can be de-identified to protect user privacy.

[0160] In the descriptions of the foregoing embodiments, the reference terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" mean that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are mutually inconsistent.

[0161] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of such features. Throughout the description of this application, "plurality" means at least two, for example, two, three, etc., unless otherwise specifically defined.

[0162] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may be performed out of the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present application belong.

[0163] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and programmable read-only memory (EPROM or flash memory), fiber optic devices, and a portable compact disc read-only memory (CDROM). Furthermore, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing it in another suitable manner if necessary, and then storing it in a computer memory.

[0164] It should be understood that various parts of the present application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used to implement: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0165] Those skilled in the art will understand that all or part of the steps in the method of the above embodiment can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0166] In addition, the functional units in the various embodiments of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into a module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0167] The storage medium mentioned above may be a read-only memory, a magnetic disk, or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application. Persons skilled in the art may make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. A method for predicting water discharge in a roadway during surface fracturing, characterized in that: The method comprises: Acquire first pressure data of a fracturing wellhead history during coal rock roof fracturing, wherein the first pressure data at least includes a pressure curve of the wellhead; determining a fracturing stage of the coal rock roof fracturing based on the pressure curve, and determining a pressure curve characteristic corresponding to the pressure curve; Determining a data set of a first water discharge event in the history of the roadway, and determining prior information for predicting water discharge in the roadway based on the data set, the fracturing stage, and the pressure curve characteristics; Based on the priori information and the real-time second pressure data of the fracturing wellhead, a second water production event of the tunnel is predicted.

2. The method according to claim 1, characterized in that The data set for determining the first water discharge event in the history of the roadway includes: Determine the water discharge time and water discharge volume of the first water discharge event; The data set is established based on the water output time and water output.

3. The method according to claim 2, characterized in that The determining of the prior information for predicting water output from the tunnel based on the data set, the fracturing stage, and the pressure curve characteristics includes: Based on the water production time, matching the first water production event with the fracturing stage to determine a target fracturing stage corresponding to the first water production event; determining target pressure curve characteristics of the target fracturing stage according to the pressure curve characteristics, and extracting key features of the target pressure curve characteristics; determining a water production type of the target fracturing stage based on the water production of the first water production event; The prior information is generated based on the target fracturing stage, the key characteristics, and the water production type.

4. The method according to claim 1, wherein The predicting of the second water discharge event of the roadway based on the prior information and the real-time second pressure data of the fracturing wellhead includes: Establishing a small sample machine learning model based on the prior information; Determining prediction information of the roadway based on the small sample machine learning model and the second pressure data; In response to the prediction information indicating that a second water outflow event exists, the second water outflow event and a water outflow type corresponding to the second water outflow event are determined.

5. The method according to claim 4, characterized in that After predicting the second water discharge event of the lane, the method includes: In response to the water output type corresponding to the second water output event indicating that the water output of the roadway is greater than a water output threshold, the fracturing parameters of the coal roof fracturing are adjusted to reduce the water output of the roadway.

6. The method according to claim 1, characterized in that Determining the pressure curve feature corresponding to the pressure curve includes: Performing wavelet transform processing on the pressure curve to obtain time-frequency characteristics of the pressure curve, wherein the time-frequency characteristics include time domain characteristics and frequency domain characteristics; Obtaining a set frequency threshold, and filtering the time-frequency feature based on the set frequency threshold to obtain an energy feature of the pressure curve; The time-frequency feature and the energy feature are used as the pressure curve feature.

7. A device for predicting water discharge in tunnels during surface fracturing, characterized in that: The device comprises: An acquisition module, configured to acquire first pressure data of a fracturing wellhead history during coal rock roof fracturing, wherein the first pressure data at least includes a pressure curve of the wellhead; A first determining module is configured to determine a fracturing stage of the coal roof fracturing based on the pressure curve, and determine a pressure curve feature corresponding to the pressure curve; A second determination module is configured to determine a data set of a first water discharge event in the history of the roadway, and determine prior information for predicting water discharge in the roadway based on the data set, the fracturing stage, and the pressure curve characteristics; A prediction module is used to predict a second water production event of the tunnel based on the prior information and the real-time second pressure data of the fracturing wellhead.

8. An electronic device, characterized in that: include: a processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 6 when executed by a processor.

10. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 6 when the computer program is executed by a processor.

Images