Coal pillar dam body safety monitoring method and device based on sounding event and micro-seismic event

Abstract

The invention provides a coal pillar dam body safety monitoring method and device based on a sounding event and a microseismic event, and the method comprises the steps: carrying out a mechanical test through environment simulation, obtaining a voiceprint feature signal in a fracture evolution process through an acoustic emission monitoring technology, analyzing and determining a percolation threshold value, and constructing a percolation model; training a percolation prediction model based on the voiceprint feature signal, the fracture evolution process and the percolation model; acquiring micro-seismic data by using a micro-seismic sensor and determining micro-seismic event distribution to obtain a micro-seismic characteristic signal; inputting the microseismic characteristic signal into a percolation prediction model to obtain a target percolation model and a target stress state, and performing safety level evaluation; and when the evaluation result shows that the safety level is low, grouting reinforcement is conducted on fracture cluster communication points of the coal pillar dam body according to the target percolation model. The method solves the problems that in the prior art, a coal pillar dam body safety monitoring method adopts multiple types of equipment, safety level analysis conditions are complex, and feedback delay is caused.

Description

Technical Field

[0001] The present invention relates to the technical field of coal pillar dam monitoring, and in particular to a method, device, computer-readable storage medium and coal pillar dam monitoring system for coal pillar dam safety monitoring based on acoustic events and microseismic events. Background Art

[0002] Coal pillar dam refers to a section of unmined coal structure retained around or at the bottom of a reservoir in order to ensure the safety and stability of the reservoir and prevent the loss of groundwater during the construction of an underground reservoir in a coal mine.

[0003] The stability of the coal pillar dam mainly depends on the thickness of the coal seam and the physical and mechanical properties of the coal seam. In the evaluation of the stability of the coal pillar dam, the stability of the coal seam is the main evaluation object of the coal pillar dam, and its stability mainly depends on the stability of the coal seam. The stability of the coal seam mainly depends on the permeability of the coal seam, and the permeability mainly depends on the porosity and pore opening rate of the coal seam, both of which are related to the distribution of cracks in the coal seam. The distribution of cracks in the coal seam mainly depends on the occurrence environment of the coal seam, the stress disturbance caused by mining activities, and the impact of reservoir storage and water release. The occurrence environment includes the coal formation process of the coal seam and the physical and chemical reaction process of the coal seam after coal formation. In the coal formation process, cracks will form in the coal seam, which are called primary cracks. In the physical and chemical reaction process of the coal seam, cracks will form in the coal seam, which are called secondary cracks. The development of cracks in the coal seam directly affects the permeability of the coal seam.

[0004] In the prior art, the safety monitoring methods for the coal pillar dam of the underground reservoir include stress sensors, strain sensors, microseismic sensors, etc. Although a large number of sensors have collected a lot of data, in order to effectively judge the safety status of the coal pillar dam through these data, a comprehensive diagnosis is performed by adopting multiple monitoring methods. However, a large number of influencing factors and parameter configurations need to be considered in the diagnosis process, resulting in high monitoring costs and delayed judgment results. Summary of the invention

[0005] The main purpose of the present application is to provide a coal pillar dam safety monitoring method, device, computer-readable storage medium and coal pillar dam monitoring system based on acoustic events and microseismic events, so as to at least solve the problem that the coal pillar dam safety monitoring method in the prior art adopts a large number of equipment types, the safety level analysis conditions are complex, and the feedback is delayed.

[0006] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a method for monitoring the safety of coal pillar dams based on acoustic events and microseismic events is provided, including: performing environmental simulation based on different working condition parameter groups, and conducting mechanical tests in the simulated environment, monitoring the sound signals of coal rock samples during the evolution of cracks through acoustic emission monitoring technology, and obtaining soundprint characteristic signals, wherein the coal rock samples are rock samples collected from the rock layer where the coal pillar dam of the underground reservoir is located; analyzing based on the soundprint characteristic signals to determine the percolation threshold of the connectivity of the crack clusters, and constructing a percolation model based on the soundprint characteristic signals and the percolation threshold, wherein the percolation model is used to describe Connectivity of crack clusters under different operating parameter groups; learning based on acoustic print characteristic signals, crack evolution process and percolation model to obtain a percolation prediction model, which is used to predict the corresponding prediction model according to the number of acoustic print characteristic signals, and determine the stress state according to the percolation model; obtaining microseismic data through microseismic sensors, and determining the distribution of microseismic events based on the microseismic data to obtain microseismic characteristic signals; inputting the microseismic characteristic signals into the percolation prediction model to obtain the target percolation model and target stress state, conducting a safety level evaluation based on the target stress state and the target percolation model, and performing grouting reinforcement based on the safety level evaluation.

[0007] Optionally, an environmental simulation is performed based on different operating parameter groups, and a mechanical test is carried out under the simulated environment, and the sound signals of the coal and rock samples during the crack evolution process are monitored by acoustic emission monitoring technology to obtain soundprint characteristic signals, including: obtaining multiple preset saturations, multiple dry-wet cycle numbers, and multiple preset water pressures, and combining them based on the preset saturations, dry-wet cycle numbers, and preset water pressures to obtain multiple operating parameter groups; loading the test axial pressure and the test confining pressure to be consistent with the existing stress state of the coal pillar dam to obtain a first state; taking the first state as a reference, increasing the test axial pressure and the test confining pressure at a first preset rate until the coal and rock samples are destroyed to obtain a second state; monitoring the sound signals of the coal and rock samples entering the second state to obtain soundprint characteristic signals.

[0008] Optionally, analysis is performed based on the soundprint characteristic signal to determine the percolation threshold of the connectivity of the fracture clusters, and a percolation model is constructed based on the soundprint characteristic signal and the percolation threshold, including: positioning and marking based on the soundprint characteristic signal, marking the location where the acoustic emission event exists with the first identification information, and marking the location where the acoustic emission event does not exist with the second identification information; constructing squares of different lengths to cover the first identification information, and the squares do not completely overlap with each other; when there is surface contact between any two squares, the squares are determined to be in the same fracture cluster; if when the coal rock sample enters the second state, the fracture clusters are connected in any one of the x, y and z directions, the fracture network under the current grid length is determined to be a percolation state; scaling the grid length in the percolation state based on the dichotomy method until the fracture clusters corresponding to the squares are not connected in the x, y and z directions, and determining the grid length as the percolation threshold; determining the fracture clusters corresponding to the grid length as the percolation model.

[0009] Optionally, learning is performed based on the voiceprint characteristic signal, the crack evolution process and the percolation model to obtain a percolation prediction model, including: obtaining the evolution data of the crack clusters under different operating parameter groups, and annotating the evolution data based on different stress stages; screening the crack clusters corresponding to the crack initiation stress, crack damage stress and peak stress in the annotated evolution data, annotating them again, and using the twice updated evolution data as the first training data set; training the model based on the first training data set, the voiceprint characteristic signal and the percolation model to obtain the percolation prediction model.

[0010] Optionally, before obtaining microseismic data through the microseismic sensor, the method also includes: obtaining the height of the coal pillar dam, calibrating a first position on the coal pillar dam with a preset ratio and height; dividing the portion of the coal pillar dam below the first position into a grid of a first preset specification, and burying a microseismic sensor in the center of the grid; dividing the portion of the coal pillar dam above the first position into a grid of a second preset specification, and burying a microseismic sensor in the center of the grid.

[0011] Optionally, the microseismic sensor is buried at a depth that at least exceeds a second position, and the second position is obtained by calibration at a preset ratio on the width of the coal pillar dam.

[0012] Optionally, grouting reinforcement is performed on the connection points of the coal pillar dam body at least based on the target percolation model, including: when the target stress state is less than the crack initiation stress, the safety level of the coal pillar dam body is determined to be the first safety level; when the target stress state is greater than or equal to the crack initiation stress and less than or equal to the crack damage stress, the safety level of the coal pillar dam body is determined to be the second safety level; when the target stress state is greater than the crack damage stress, the safety level of the coal pillar dam body is determined to be the third safety level; when the coal pillar dam body is at the third safety level, the connection points of the fracture clusters in the coal pillar dam body are determined based on the target percolation model, and grouting reinforcement is performed at the connection points.

[0013] According to another aspect of the present application, a coal pillar dam safety monitoring device based on acoustic detection events and microseismic events is provided, the device comprising: a simulation unit, used to perform environmental simulation based on different working condition parameter groups, and to perform mechanical tests in the simulated environment, and to monitor the sound signals of coal rock samples during the crack evolution process by acoustic emission monitoring technology to obtain sound print characteristic signals, wherein the coal rock samples are rock samples collected from the rock layer where the coal rock dam of the underground reservoir is located; a first determination unit, used to perform analysis based on the sound print characteristic signals to determine the percolation threshold of the connection between the crack clusters, and to construct a percolation model based on the sound print characteristic signals and the percolation threshold, the percolation model being used to describe the different working condition parameter groups. The connectivity of the crack clusters under the array; a training unit, used to learn based on the acoustic print characteristic signal, the crack evolution process and the percolation model to obtain the percolation prediction model, the percolation prediction model is used to predict the corresponding prediction model according to the number of acoustic print characteristic signals, and determine the stress state according to the percolation model; a second determination unit, used to obtain microseismic data through microseismic sensors, and determine the distribution of microseismic events according to the microseismic data to obtain microseismic characteristic signals; a first calculation unit, used to input the microseismic characteristic signal into the percolation prediction model, obtain the target percolation model and the target stress state, perform safety level evaluation based on the target stress state and the target percolation model, and perform grouting reinforcement based on the safety level evaluation.

[0014] According to another aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute any one of the methods described.

[0015] According to another aspect of the present application, a coal pillar dam monitoring system 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 are configured to be executed by the one or more processors, and the one or more programs include methods for executing any one of the described methods.

[0016] By applying the technical solution of the present application, in the above-mentioned coal pillar dam safety monitoring method based on acoustic detection events and microseismic events, first, an environmental simulation is performed based on different working condition parameter groups, and a mechanical test is performed in the simulated environment, and the acoustic signal of the coal rock sample during the crack evolution process is monitored by acoustic emission monitoring technology to obtain a soundprint characteristic signal, and the coal rock sample is a rock sample collected from the rock layer where the coal rock dam of the underground reservoir is located; then, an analysis is performed based on the soundprint characteristic signal to determine the percolation threshold of the connection of the crack clusters, and a percolation model is constructed based on the soundprint characteristic signal and the percolation threshold, and the percolation model is used to describe the different working condition parameter groups. The connectivity of the lower fracture clusters; then, based on the acoustic print characteristic signal, the fracture evolution process and the percolation model, learning is performed to obtain the percolation prediction model, which is used to predict the corresponding prediction model according to the number of acoustic print characteristic signals, and determine the stress state according to the percolation model; then, microseismic data is obtained through microseismic sensors, and the distribution of microseismic events is determined according to the microseismic data to obtain microseismic characteristic signals; finally, the microseismic characteristic signals are input into the percolation prediction model to obtain the target percolation model and the target stress state, and the safety level is evaluated based on the target stress state and the target percolation model, and grouting reinforcement is performed based on the safety level evaluation. This application can more accurately predict and evaluate the safety status of the coal pillar dam by combining acoustic emission monitoring technology and microseismic monitoring technology. By constructing a percolation model and a percolation prediction model, the connectivity of the fracture clusters can be effectively predicted, and then the stress state and safety level of the coal pillar dam can be judged, and grouting reinforcement measures can be taken in time to prevent leakage or damage to the dam body caused by fracture connectivity, which significantly improves the safety and stability of the underground reservoir and provides technical support for the long-term safe operation of the underground reservoir. Moreover, through the combination of measured data and simulation tests, the accuracy and reliability of monitoring are improved. It is possible to monitor microseismic events and acoustic detection events of the coal pillar dam in real time, promptly discover potential safety hazards, and effectively prevent and control leakage of underground reservoirs and dam damage, which has significant practical application value and economic benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A schematic flow chart of a method for monitoring the safety of a coal pillar dam based on acoustic events and microseismic events according to an embodiment of the present application is shown;

[0018] Figure 2 A side view of an underground water reservoir and a coal pillar dam provided according to an embodiment of the present application is shown;

[0019] Figure 3 A schematic diagram of the distribution of microseismic sensors provided according to an embodiment of the present application is shown;

[0020] Figure 4 A structural block diagram of a coal pillar dam body safety monitoring device based on acoustic events and microseismic events provided according to an embodiment of the present application is shown.

[0021] The above drawings include the following reference numerals:

[0022] 1. Overlying rock strata; 2. Water storage area; 3. Coal pillar dam; 4. Microseismic sensor embedding holes; 5. Bottom plate; 6. Microseismic sensor. DETAILED DESCRIPTION

[0023] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0024] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0025] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0026] As introduced in the background technology, the prior art adopts multiple monitoring means for comprehensive diagnosis, but a large number of influencing factors and parameter configurations need to be considered in the diagnosis process, resulting in high monitoring costs and delayed judgment results. In order to solve the problem that the coal pillar dam safety monitoring method in the prior art adopts a large number of equipment types and complex safety level analysis conditions, resulting in delayed feedback, the embodiments of the present application provide a coal pillar dam safety monitoring method, device, computer-readable storage medium and coal pillar dam monitoring system based on acoustic events and microseismic events.

[0027] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0028] Figure 1FIG. 1 is a flow chart of a method for monitoring coal pillar dam safety based on acoustic events and microseismic events according to an embodiment of the present application. Figure 1 As shown, the method comprises the following steps:

[0029] Step S201, performing environmental simulation based on different working condition parameter groups, and conducting mechanical tests under the simulated environment, and monitoring the sound signals of coal rock samples during the crack evolution process by acoustic emission monitoring technology to obtain soundprint characteristic signals, wherein the coal rock samples are rock samples collected from the rock stratum where the coal rock dam of the underground reservoir is located;

[0030] Specifically, environmental simulation and mechanical tests based on different working condition parameter groups include: first, collecting rock samples from the rock strata where the coal-rock dam of the underground reservoir is located, and then simulating the environmental conditions of the dam under different working conditions (such as different saturations, water pressures, and dry-wet cycles) in the laboratory, and conducting mechanical loading tests. The setting of these working condition parameter groups is intended to cover all operating conditions that the dam may experience, so as to comprehensively evaluate its response under different environments. Acquiring acoustic print characteristic signals through acoustic emission monitoring technology includes: During the simulation process, using acoustic emission monitoring technology to record the acoustic signals generated when the cracks in the coal-rock samples develop, these signals are analyzed to form acoustic print characteristic signals, which become important data for judging the state of the cracks.

[0031] In an optional embodiment, the side view of the coal pillar dam and the underground reservoir is as follows: Figure 2 As shown, it includes: overlying rock layer 1, water storage area 2, coal pillar dam body 3, microseismic sensor embedding hole 4, and bottom plate 5.

[0032] Step S202, analyzing the above-mentioned voiceprint characteristic signal to determine the percolation threshold of the connectivity of the fracture clusters, and constructing a percolation model based on the above-mentioned voiceprint characteristic signal and the above-mentioned percolation threshold, wherein the above-mentioned percolation model is used to describe the connectivity of the fracture clusters under different above-mentioned operating condition parameter groups;

[0033] Specifically, analyzing the characteristic signal of the voiceprint, determining the percolation threshold and constructing the percolation model includes: analyzing the characteristic signal of the voiceprint through an artificial intelligence system, identifying the critical point of the connection of the crack cluster, that is, the percolation threshold. When the crack network is connected in any direction, it is considered to have reached the percolation state. The crack distribution and connectivity at this time form a percolation model to describe the connectivity of the crack cluster under different working conditions.

[0034] Step S203, learning based on the voiceprint characteristic signal, the crack evolution process and the percolation model to obtain a percolation prediction model, wherein the percolation prediction model is used to predict the corresponding prediction model according to the number of the voiceprint characteristic signal, and determine the stress state according to the percolation model;

[0035] Specifically, based on the soundprint characteristic signal, the crack evolution process and the percolation model, the percolation prediction model is obtained by learning the collected soundprint characteristic signal, the crack evolution process and the percolation model using an artificial intelligence algorithm to obtain a percolation prediction model. The model can predict the connectivity state of the current crack cluster according to the number of soundprint characteristic signals monitored in real time, and further determine the stress state of the dam body.

[0036] Step S204, acquiring microseismic data through a microseismic sensor, and determining the distribution of microseismic events based on the microseismic data to obtain a microseismic characteristic signal;

[0037] Specifically, obtaining microseismic data through microseismic sensors and analyzing them include: arranging microseismic sensors outside the actual coal pillar dam to collect microseismic data. The distribution and characteristic signals of microseismic events are determined, and these data reflect the dynamic changes of cracks inside the dam.

[0038] Step S205, inputting the above-mentioned microseismic characteristic signal into the above-mentioned percolation prediction model to obtain a target percolation model and a target stress state, performing a safety level evaluation based on the target stress state and the above-mentioned target percolation model, and performing grouting reinforcement based on the safety level evaluation.

[0039] Specifically, the safety level evaluation and grouting reinforcement decision based on the percolation prediction model include: inputting the microseismic characteristic signal into the percolation prediction model to obtain the corresponding target percolation model and target stress state. Based on these results, the safety level of the dam body is evaluated, and grouting reinforcement is performed when necessary (such as the safety level is level 3) to prevent further expansion of cracks and ensure the safety of the dam body.

[0040] In the specific implementation, rock samples are first obtained and a series of physical and mechanical tests are carried out, including changing saturation, water pressure and number of dry-wet cycles, while monitoring acoustic emission events. For example, in the simulation test of the coal pillar dam, five different saturation conditions (0%, 25%, 50%, 75%, 100%), six sets of water pressure conditions (corresponding to different water level heights), and six different numbers of dry-wet cycles (representing the operating cycle of the reservoir) were set. During the test, the spatial position and time of the acoustic emission events were recorded in detail to analyze the evolution of the cracks.

[0041] By analyzing these acoustic emission data through artificial intelligence, the percolation threshold and percolation model under different conditions were determined. After identifying the percolation model, the system learned the evolution law of the largest crack clusters at different stress stages, so as to predict and determine the current stress state of the dam body.

[0042] During the implementation phase, monitoring personnel deployed microseismic sensors around the coal pillar dam of the underground reservoir, especially in the bottom area of ​​the dam. The data of the microseismic sensors were collected in real time and converted into microseismic characteristic signals. The signals were input into the trained artificial intelligence system, which predicted the stress state of the dam and the connectivity state of the fracture clusters based on the analysis method of the soundprint characteristic signals, and then evaluated the safety level of the dam.

[0043] When the safety level reaches level 3, it indicates that the connectivity of the fracture clusters has posed a threat to the stability of the dam. At this point, the key nodes of fracture connectivity are determined through the percolation model, and grouting reinforcement measures are implemented to prevent further expansion of the fractures. After reinforcement, data is collected again through the microseismic monitoring system to ensure that the stress state of the dam has been reduced to a safe level.

[0044] The entire technical solution realizes real-time monitoring and safety assessment of the fracture status of the coal pillar dam by combining laboratory simulation with on-site monitoring, effectively reducing monitoring costs and improving the timeliness of monitoring, providing strong technical support for the safe operation of the reservoir.

[0045] Through this embodiment, first, an environmental simulation is performed based on different operating parameter groups, and a mechanical test is performed under the simulated environment. The acoustic signal of the coal rock sample during the crack evolution process is monitored by the acoustic emission monitoring technology to obtain a soundprint characteristic signal, and the coal rock sample is a rock sample collected from the rock layer where the coal rock dam of the underground reservoir is located; then, an analysis is performed based on the soundprint characteristic signal to determine the percolation threshold of the connectivity of the crack clusters, and a percolation model is constructed based on the soundprint characteristic signal and the percolation threshold. The percolation model is used to describe the connectivity of the crack clusters under different operating parameter groups; then, based on the acoustic emission characteristic signal, a soundprint characteristic signal is generated. The percolation prediction model is obtained by learning the acoustic wave characteristic signal, the crack evolution process and the percolation model. The percolation prediction model is used to predict the corresponding prediction model according to the number of acoustic wave characteristic signals, and the stress state is determined according to the percolation model; then, the microseismic data is obtained through the microseismic sensor, and the distribution of microseismic events is determined according to the microseismic data to obtain the microseismic characteristic signal; finally, the microseismic characteristic signal is input into the percolation prediction model to obtain the target percolation model and the target stress state, and the safety level is evaluated based on the target stress state and the target percolation model, and grouting reinforcement is performed based on the safety level evaluation. This application can more accurately predict and evaluate the safety status of the coal pillar dam by combining the acoustic emission monitoring technology and the microseismic monitoring technology. By constructing the percolation model and the percolation prediction model, the connectivity of the crack clusters can be effectively predicted, and then the stress state and safety level of the coal pillar dam can be judged, and grouting reinforcement measures can be taken in time to prevent leakage or damage to the dam body caused by the connection of cracks, which significantly improves the safety and stability of the underground reservoir and provides technical support for the long-term safe operation of the underground reservoir. Moreover, through the combination of measured data and simulation tests, the accuracy and reliability of monitoring are improved. It is possible to monitor microseismic events and acoustic detection events of the coal pillar dam in real time, promptly discover potential safety hazards, and effectively prevent and control leakage of underground reservoirs and dam damage, which has significant practical application value and economic benefits.

[0046] In order to obtain the above voiceprint characteristic signal, in an optional implementation, the above step S201 includes:

[0047] Step S2011, obtaining a plurality of preset saturations, a plurality of dry-wet cycle times, and a plurality of preset water pressures, and combining the preset saturations, the dry-wet cycle times, and the preset water pressures to obtain a plurality of the operating condition parameter groups;

[0048] Specifically, obtaining the working condition parameter group includes: first, the experimental designer will set a series of parameters, including different saturations, dry-wet cycles and water pressures, which reflect the various environmental conditions that the coal pillar dam may encounter during actual operation. By combining these parameters, multiple working condition parameter groups are formed to fully cover various working conditions that may affect the safety of the dam.

[0049] Step S2012, loading the test axial pressure and the test confining pressure to be consistent with the existing stress state of the coal pillar dam body to obtain a first state;

[0050] Specifically, the simulation of the existing stress state of the coal pillar dam body includes: in the experiment, the coal rock sample will be placed in the loading device, and the loaded axial pressure and confining pressure will match the actual existing stress state of the coal pillar dam body under specific working conditions, that is, the stress state without water pressure or under initial water pressure, which is defined as the first state. In this way, it can be ensured that the test conditions in the laboratory can simulate the actual working conditions on site as much as possible.

[0051] Step S2013, taking the first state as a reference, increasing the test axial pressure and the test confining pressure at a first preset rate until the coal-rock sample is destroyed, thereby obtaining a second state;

[0052] Specifically, the test until the coal-rock sample is destroyed includes: after reaching the first state, the experimenter will gradually increase the axial pressure and confining pressure, usually at a preset rate, until the coal-rock sample is destroyed. This process simulates the response of the coal pillar dam under external forces such as increased water pressure, and the final state is defined as the second state. By gradually loading until destruction, the development and connectivity of cracks in coal-rock materials under different stress conditions can be observed and recorded.

[0053] Step S2014: monitor the sound signal of the coal rock sample entering the second state to obtain the voiceprint feature signal.

[0054] Specifically, the acquisition and analysis of the acoustic signature signal includes: when the coal rock sample enters the second state, the acoustic emission monitoring system will capture the sound signal generated by the expansion of the crack. The characteristics of these sound signals (such as frequency, amplitude, duration, etc.) are analyzed and processed to form the acoustic signature signal. The acoustic signature signal is a record of the acoustic characteristics during the development of the crack, which can reveal the evolution path and connectivity of the crack, and is crucial for evaluating the safety of the coal pillar dam.

[0055] In the specific implementation, the following operating condition parameter groups are assumed: Saturation parameter group: 0%, 25%, 50%, 75%, 100%. Dry-wet cycle number parameter group: 0 times, 10 times, 20 times, 30 times, 40 times, 50 times, representing the number of water storage and drainage times of the coal mine underground reservoir in different operating years. Water pressure parameter group: 0MPa, 0.2MPa, 0.4MPa, 0.6MPa, 0.8MPa, and the water pressure test is only carried out when the saturation is 100%.

[0056] For each operating parameter group, perform the following steps:

[0057] 1. Preload to the existing stress state: Load the coal rock sample to a pressure consistent with the initial existing stress state of the coal pillar dam in the underground coal mine, and record the crack state and acoustic emission signal at this time, which is defined as the first state.

[0058] 2. Gradually load to failure: Starting from the first state, increase the axial pressure and confining pressure at a rate of 0.1 MPa / s until the coal rock sample is destroyed. This failure state is defined as the second state. During this process, the acoustic emission monitoring system continuously records all acoustic emission events generated.

[0059] 3. Analyze acoustic signature signals: Once the coal and rock samples reach a state of destruction, the experimenters will extract acoustic signature signals from the acoustic emission data, including the acoustic signal intensity, frequency, and pattern when the cracks expand. These signals will be used for subsequent model construction and analysis.

[0060] For example, under the test conditions of 100% saturation, 50 dry-wet cycles, and 0.6 MPa water pressure, the coal-rock samples generated a series of acoustic emission events during the loading process. The time, frequency, and amplitude characteristics of these events were recorded to form specific acoustic signature signals. When the axial pressure and confining pressure increase to a certain extent, the cracks begin to accelerate and eventually lead to the destruction of the coal-rock samples. The acoustic signature signals at this time are particularly critical and are used to train the percolation model to predict the evolution of cracks and the safety status of the dam under similar working conditions.

[0061] In order to determine the percolation model, in an optional implementation, the step S202 includes:

[0062] Step S2021, positioning and marking based on the voiceprint characteristic signal, marking the location where the acoustic emission event exists with the first identification information, and marking the location where the acoustic emission event does not exist with the second identification information;

[0063] Specifically, positioning and marking based on acoustic print characteristic signals include: acoustic print characteristic signals refer to acoustic emission signals generated when cracks in coal and rock samples develop during mechanical tests. By analyzing these signals, the specific location where the cracks occur can be located. After the acoustic emission monitoring system records the signal, each monitoring point in the sample is marked, and the location where the acoustic emission event occurs is marked by the first identification information (for example, marked as "1"), while the location where the acoustic emission event does not exist is marked by the second identification information (for example, marked as "0"). In this way, the crack distribution information of the sample under different stress states is clearly recorded.

[0064] Step S2022, constructing squares of different lengths to cover the first identification information, wherein the squares do not completely overlap with each other;

[0065] Specifically, construct squares of different lengths to cover the first identification information: Next, design a series of squares of different lengths to cover all positions marked as "1", that is, the crack positions where acoustic emission events exist. It is worth noting that these squares cannot completely overlap with each other to ensure that each square can independently reflect the connectivity of the crack.

[0066] Step S2023, when any two of the squares are in contact with each other, determining that the squares are in the same crack cluster;

[0067] Specifically, the determination of fracture clusters includes: if there is surface contact between any two squares, that is, adjacent squares have a common fracture on a certain surface, then the two squares are considered to be in the same fracture cluster. This method of determining fracture clusters by contact surface can help analyze the connectivity and distribution pattern of fractures.

[0068] Step S2024: if the fracture clusters are connected in any one of the x, y and z directions when the coal rock sample enters the second state, the fracture network under the current grid length is determined to be in a percolation state;

[0069] Specifically, the determination of the percolation state includes: when the coal rock sample enters the second state (usually the state where the cracks begin to connect), if the crack clusters are connected in any direction (x, y, z) in three-dimensional space, this indicates that the current fracture network has reached the percolation state, that is, the cracks tend to form a continuous path, which may affect the structural stability.

[0070] Step S2025, scaling the grid length in the percolation state based on a dichotomy method until the crack clusters corresponding to the grid are not connected in the x, y and z directions, and determining the grid length as the percolation threshold;

[0071] Specifically, the determination of the percolation threshold includes: continuously adjusting the size of the grid through dichotomy until the fracture clusters are not connected in the x, y, and z directions at the current grid length. This process is similar to finding the critical point of the fracture connectivity state. Ultimately, the grid size that makes the fracture network not reach the percolation state is considered to be the percolation threshold. The determination of the percolation threshold is crucial to identifying when the fracture network changes from local connectivity to global connectivity.

[0072] Step S2026, determining the above-mentioned crack cluster corresponding to the above-mentioned grid length as the above-mentioned percolation model.

[0073] Specifically, the construction of the percolation model includes: Finally, the distribution of fracture clusters under the determined percolation threshold is regarded as the percolation model. This model not only describes the distribution state of fracture clusters under specific conditions, but also reflects the critical conditions for fracture connectivity, which can be used to predict and evaluate the fracture connectivity of coal-rock dams under different working conditions, and then judge their safety status.

[0074] In the specific implementation, we first collected rock samples from the coal-rock dam of the underground reservoir, and carried out mechanical loading tests in a simulated environment by changing parameters such as water pressure and the number of dry-wet cycles. At the same time, we used acoustic emission monitoring equipment to record the characteristic signals of the soundprint during the development of the cracks. For example, the saturation of the test was set to five groups (0%, 25%, 50%, 75%, 100%), the number of dry-wet cycles was set to six groups (0, 0.2, 0.4, 0.6, 0.8, 1.0), and the water pressure was set to six groups (0, 0.2, 0.4, 0.6, 0.8, 1.0 MPa).

[0075] During the experiment, the characteristic signals of the soundprint were recorded in detail, and the locations where the acoustic emission events existed were marked as "1", and those where they did not exist were marked as "0". Then, these marks were covered with squares of different lengths, and the minimum square length was adjusted from large to small through dichotomy until the minimum square length was found, at which the crack network was no longer connected in any direction. This minimum square length is the percolation threshold.

[0076] When the fracture network reaches the percolation state, the researchers determined the distribution of fracture clusters in the x, y, and z directions and constructed a percolation model. In the percolation model, the location, size, and connectivity of each fracture cluster are recorded in detail, which provides basic data for subsequent dam safety assessments.

[0077] Through this series of experiments and analyses of coal and rock samples in the laboratory, the researchers were able to establish a percolation prediction model that can predict the connectivity of fracture clusters based on the number of acoustic signature signals and assess the stress state and safety level of the coal pillar dam in actual operation. This technology provides a scientific basis for mine ecological restoration and underground reservoir dam safety monitoring, reducing monitoring costs and improving monitoring efficiency.

[0078] In order to obtain the above percolation prediction model, in an optional implementation, the above step S203 includes:

[0079] Step S2031, obtaining the evolution data of the above-mentioned crack clusters under different working condition parameter groups, and marking the above-mentioned evolution data based on different stress stages;

[0080] Specifically, obtaining the evolution data of fracture clusters under different operating parameter groups includes: first, in the laboratory, a simulation test is conducted on rock samples collected from the coal-rock dam of the underground reservoir. The test covers different parameters such as saturation, water pressure and number of dry-wet cycles to simulate the stress environment of the dam under various operating conditions. During the test, the development and connectivity of fracture clusters are recorded in detail, including the formation, expansion, connectivity and final rupture of fractures, to form the evolution data of fracture clusters. The evolution data is annotated based on different stress stages, including: preliminary analysis of the evolution data of fracture clusters to identify the fracture state of samples at different stress stages, such as the initiation stage, damage stage and rupture (peak stress) stage. The data of each stage is clearly annotated to reflect the characteristics of the fracture clusters at that stage.

[0081] Step S2032, selecting the crack clusters corresponding to the crack initiation stress, the crack damage stress and the peak stress in the annotated evolution data, annotating them again, and using the evolution data updated twice as the first training data set;

[0082] Specifically, the key crack clusters are screened and annotated twice: on the basis of the preliminary annotation, the crack cluster data corresponding to the three key points of crack initiation stress, crack damage stress and peak stress are further selected. These data points are crucial for understanding the development process of cracks and predicting the stability of the dam. Then, these key crack clusters are annotated again in detail to ensure that their characteristics are fully captured. Construct the first training data set: the evolution data of the crack clusters after two annotations are integrated to form the first training data set. This data set not only contains the information of the entire process of crack development, but also highlights the crack characteristics at the key stages, providing a basis for training the percolation prediction model.

[0083] Step S2033: training the model based on the first training data set, the voiceprint feature signal and the percolation model to obtain the percolation prediction model.

[0084] Specifically, the percolation prediction model is trained: the first training data set, the soundprint characteristic signal, and the percolation model established through the above steps are input into the artificial intelligence system. The soundprint characteristic signal reflects the dynamic acoustic characteristics of the development of the crack, and the percolation model describes the critical point of the crack connectivity state. By learning these data, the artificial intelligence system gradually builds a percolation prediction model, which can predict the connectivity of the crack clusters and judge the stress state of the dam body according to the soundprint characteristic signal and different working condition parameters.

[0085] In the specific implementation, firstly, a comprehensive mechanical test was carried out on the coal and rock samples to simulate the working conditions of the underground reservoir under different water levels, saturation and dry-wet cycles. In the test, the acoustic emission system was used to monitor the development of cracks in the samples, recording the acoustic signals of the whole process from the initiation to the final rupture of the cracks, which were processed into acoustic signature signals.

[0086] Subsequently, based on the characteristic acoustic signature of the cracks, the researchers analyzed the evolution of the crack clusters at different stress stages, such as crack initiation, damage, and final rupture (peak stress). The state of the crack clusters at each stage was carefully annotated, especially at the three key points of crack initiation, crack damage, and peak stress. The researchers conducted a second detailed annotation to ensure that the model can accurately identify the crack characteristics at these stages.

[0087] The labeled data was integrated into the first training data set for training the artificial intelligence system. During the training process, the system not only learned the evolution law of crack clusters, but also combined the voiceprint characteristic signals and the percolation model to gradually improve the accuracy of the prediction and finally formed a percolation prediction model.

[0088] The percolation prediction model can predict the connectivity of the crack clusters in the coal-rock dam body and assess whether the stress state of the dam body is within a safe range based on the real-time monitored acoustic signature signals and current operating parameters. For example, when the microseismic monitoring data shows a large number of microseismic events inside the dam body, the percolation prediction model can analyze these microseismic signature signals to quickly assess the connectivity of the cracks and stress levels in the dam body, providing real-time data support for safety management and maintenance decisions.

[0089] Through this process, this technical solution realizes the intelligent monitoring and evaluation of the crack status of the coal-rock dam body, providing advanced technical means for the safe operation of the underground reservoir.

[0090] In order to determine the layout of the microseismic sensors, in an optional implementation, before acquiring the microseismic data through the microseismic sensors, the method further includes:

[0091] Step S301, obtaining the height of the coal pillar dam, and calibrating a first position on the coal pillar dam using a preset ratio and the height;

[0092] Specifically, obtaining the height of the coal pillar dam and calibrating the first position include: First, the height of the coal pillar dam needs to be accurately measured. This step is the basis for the subsequent sensor arrangement. Since the bottom area of ​​the dam body is usually subjected to greater water pressure, the development of cracks may be more rapid and complex, so the bottom of the dam body is selected as the key area of ​​concern. According to the total height of the coal pillar dam body, the researchers determined a key height as the first position with a preset ratio.

[0093] Step S302, dividing the portion of the coal pillar dam body below the first position into grids of a first preset specification, and embedding microseismic sensors in the center of the grids;

[0094] Specifically, grid division and microseismic sensor embedding: Next, the portion of the coal pillar dam below the first position is divided into a plurality of grids of a first preset specification, which are usually smaller and denser grids, so as to more accurately capture microseismic signals. At the center point of each grid, a microseismic sensor is drilled and embedded.

[0095] Step S303: dividing the portion of the coal pillar dam body higher than the first position into a grid of a second preset specification, and embedding the microseismic sensor in the center of the grid.

[0096] Specifically, for the portion above the first position, a second preset grid is used, and the size and density of the grid may be different from the first portion to meet the monitoring needs of different areas of the dam. In the center of each grid, a microseismic sensor is also buried.

[0097] In the specific implementation, assuming that the total height of the coal pillar dam of the underground reservoir is 90 meters, the researchers determined that the height of the first position is 30 meters, that is, the height of the lower area of ​​concern is 30 meters, and the height of the upper area is 60 meters. To ensure the accuracy and coverage of monitoring, the lower area (below 30 meters) is divided into smaller grids, each with a size of 2 meters × 1 meter, so that possible microseismic events can be captured more carefully; while the upper area (above 30 meters) uses a relatively large grid with a size of 4 meters × 2 meters, because the water pressure in the upper area is relatively small, and the development of cracks may not be as frequent and intense as in the lower area.

[0098] This microseismic sensor layout strategy based on high segmentation and grid division can effectively distinguish the monitoring needs of different areas, and through the collection and analysis of microseismic data, it can evaluate the development of cracks in real time, warn of safety issues in advance, and provide a scientific basis for the maintenance and management of the dam. At the same time, the analysis of microseismic data through the artificial intelligence system can further improve the accuracy and efficiency of monitoring and ensure the safety of underground reservoir operations.

[0099] In the above embodiment, in order to ensure that the microseismic sensor can effectively monitor the dynamic changes of the cracks inside the coal pillar dam, the buried depth requirement of the sensor is specially set. Specifically, the buried position of the sensor needs to go deep into the dam body, and the depth must at least exceed the second position calibrated on the width of the coal pillar dam body by the preset ratio. The setting of this preset ratio is intended to balance the monitoring effect and construction cost, ensuring that the sensor can capture key microseismic signals while avoiding unnecessary deep excavation.

[0100] Furthermore, the determination of the preset ratio includes: the preset ratio is obtained by comprehensive analysis of factors such as the material properties of the coal pillar dam, the distribution of groundwater pressure, and the law of fracture development. Usually, this ratio ensures that the sensor is located in the area where fracture activity is most frequent, that is, the lower area of ​​the dam body that is subjected to the maximum water pressure, so as to capture the most direct fracture activity information. The calibration of the second position includes: the second position is obtained by calibration in the width direction of the coal pillar dam body at a preset ratio. For example, if the preset ratio is 1 / 3 of the width of the dam body, then the second position starts from the surface of the dam body and goes deep into the interior to 1 / 3 of the width of the dam body. This calibration method ensures that the sensor is buried deep enough to sense the microseismic signals inside the dam body, while not being too close to the bottom of the dam body, thereby avoiding the costs and risks brought about by excessive construction.

[0101] In one embodiment, the arrangement of the microseismic sensors 6 is as follows: Figure 3 shown.

[0102] In the specific implementation, in the safety monitoring of the coal pillar dam of the underground reservoir implementing this technical solution, the specific operations are as follows:

[0103] Assuming the total width of the coal pillar dam is W, based on laboratory simulation and analysis, the researchers determined that the area with the most frequent fissure activity is located in the lower part of the dam, and the depth should be at least 1 / 3 of the dam width. Therefore, the second position is set to start from the surface of the dam and go deep into the interior at a position of W / 3.

[0104] 1. Layout of microseismic sensors: On the outside of the coal pillar dam of the underground reservoir, according to the pre-divided grids (in the low water pressure area, the length of the grid is 2m and the height is 1m; in the high water pressure area, the length of the grid is 4m and the height is 2m), drill holes in the center of each grid. The depth of the drilling hole must ensure that the buried position of the microseismic sensor is at least more than the second position of W / 3 to ensure that the sensor can monitor the microseismic signal in the lowest area of ​​the dam.

[0105] 2. Sensor burial: The microseismic sensor is buried in the borehole to ensure that its depth exceeds the second position, which is 1 / 3 of the width of the coal pillar dam. Such a burial depth can make the sensor closer to the core area of ​​​​fracture activity and capture more accurate microseismic data.

[0106] 3. Data collection and analysis: The data collected by the microseismic sensors are transmitted to the data acquisition system in real time and then transmitted to the artificial intelligence system for analysis through the transmission line. The analysis system will match the percolation prediction model based on the depth position of the sensor and the working parameters of the dam body to evaluate the safety level of the dam body.

[0107] For example, if the width of the coal pillar dam is 6m, the second position is set at a depth of 2m. In actual operation, the buried depth of the sensor will be at least 2m to ensure that it is located in an area with frequent fracture activity and can capture microseismic signals for subsequent analysis.

[0108] In order to ensure the safety of the coal pillar dam, in an optional implementation, the above step S205 includes:

[0109] Step S2051, when the target stress state is less than the crack initiation stress, the safety level of the coal pillar dam is determined to be the first safety level;

[0110] Specifically, determining the target percolation model includes: by collecting and analyzing microseismic data and using the trained percolation prediction model, the distribution of fracture clusters and the percolation model of the current coal pillar dam can be obtained. This model describes the connectivity of fracture clusters under the current working conditions, providing a basis for subsequent safety assessments and reinforcement decisions. Safety level assessment: Based on the connectivity of fracture clusters in the target percolation model and the current microseismic characteristic signals, the system will assess the safety level of the coal pillar dam. The division of safety levels is based on the relationship between the target stress state and the known fracture initiation stress and fracture damage stress: if the target stress state is lower than the fracture initiation stress, it indicates that the dam is in a stable state, the fractures have not yet initiated, and the safety level is determined to be the first level.

[0111] Step S2052, when the target stress state is greater than or equal to the fracture initiation stress and less than or equal to the fracture damage stress, the safety level of the coal pillar dam is determined to be the second safety level;

[0112] Specifically, if the target stress state is between the crack initiation stress and the crack damage stress, it means that the crack has initiated but has not yet caused serious damage, and the safety level is determined to be the second level.

[0113] Step S2053, when the target stress state is greater than the fracture damage stress, the safety level of the coal pillar dam is determined to be the third safety level;

[0114] Specifically, if the target stress state is higher than the fracture damage stress, it means that the connectivity of fracture clusters has posed a threat to the stability of the dam body, and the safety level is determined to be the third level.

[0115] Step S2054, when the coal pillar dam is at the third safety level, the connection points of the fracture clusters in the coal pillar dam are determined based on the target percolation model, and grouting reinforcement is performed at the connection points.

[0116] Specifically, the grouting reinforcement decision includes: when the safety level of the coal pillar dam is rated as level 3, it indicates that the current fracture connectivity state poses a direct threat to the safety of the dam. At this time, reinforcement measures need to be taken immediately. The system will accurately locate the connection points of the fracture clusters according to the target percolation model, that is, the key positions in the percolation model showing the interconnection of the fracture network. Grouting reinforcement includes: after determining the connection points, grouting reinforcement is implemented at these key positions. Grouting reinforcement enhances the mechanical properties of the rock at the fracture by injecting high-strength materials into the fractures, preventing the fractures from further expanding, thereby stabilizing the dam structure and reducing safety risks.

[0117] In the specific implementation, it is assumed that in the monitoring of the coal pillar dam of a coal mine underground reservoir, the data collected by the microseismic sensor shows that the target stress state has reached above the fracture damage stress. This means that according to the analysis of the percolation prediction model, the connectivity of the fracture clusters inside the dam has become so serious that it may cause damage to the dam structure, and the safety level is determined to be the third level.

[0118] Next, based on the target percolation model, the technical team identified several key connection points in the fracture clusters. These connection points were marked as priority locations for reinforcement because they are the "bridges" that connect the fractures in the fracture network and have a significant impact on the expansion of the fractures.

[0119] Subsequently, grouting reinforcement was immediately carried out at the marked connection points. The selection of grouting materials was based on the characteristics of the cracks and the material of the dam body to ensure the reinforcement effect. During the grouting process, the key connection points of the crack clusters were accurately located by drilling, and high-strength grouting materials were poured in. After the reinforcement was completed, the microseismic monitoring system collected data again to analyze the stress state of the dam body and the connectivity of the crack clusters to confirm whether the reinforcement effect had achieved the expected effect, that is, to reduce the safety level of the dam body to a state below the crack initiation stress.

[0120] This process demonstrates how to conduct real-time safety monitoring and maintenance of the coal pillar dam through microseismic data and artificial intelligence analysis, combined with structural reinforcement technology, to ensure the safe operation of the reservoir while also reducing potential safety risks and maintenance costs. This technical solution provides innovative monitoring and maintenance tools for mine ecological restoration and underground reservoir operations.

[0121] In order to enable those skilled in the art to more clearly understand the technical solution of the present application, the implementation process of the method for coal pillar dam safety monitoring based on acoustic events and microseismic events of the present application will be described in detail below in combination with specific embodiments.

[0122] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0123] The embodiment of the present application also provides a coal pillar dam safety monitoring device based on acoustic events and microseismic events. It should be noted that the coal pillar dam safety monitoring device based on acoustic events and microseismic events in the embodiment of the present application can be used to execute the coal pillar dam safety monitoring method based on acoustic events and microseismic events provided in the embodiment of the present application. The device is used to implement the above-mentioned embodiments and preferred implementation modes, and those that have been explained will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware for a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.

[0124] The following is an introduction to the coal pillar dam body safety monitoring device based on acoustic events and microseismic events provided in an embodiment of the present application.

[0125] Figure 4 is a structural block diagram of a coal pillar dam body safety monitoring device based on acoustic events and microseismic events according to an embodiment of the present application. Figure 4 As shown, the device comprises:

[0126] The simulation unit 10 is used to perform environmental simulation based on different working condition parameter groups, and to perform mechanical tests under the simulated environment, and to monitor the sound signals of the coal rock samples during the crack evolution process by means of acoustic emission monitoring technology to obtain acoustic print characteristic signals, wherein the coal rock samples are rock samples collected from the rock layer where the coal rock dam of the underground reservoir is located;

[0127] A first determination unit 20 is used to analyze the above-mentioned voiceprint characteristic signal to determine the percolation threshold of the fracture cluster connectivity, and to construct a percolation model based on the above-mentioned voiceprint characteristic signal and the above-mentioned percolation threshold, wherein the above-mentioned percolation model is used to describe the connectivity of the fracture cluster under different above-mentioned working condition parameter groups;

[0128] A training unit 30, configured to learn based on the voiceprint characteristic signal, the crack evolution process and the percolation model to obtain a percolation prediction model, wherein the percolation prediction model is used to predict the corresponding prediction model according to the number of the voiceprint characteristic signal, and determine the stress state according to the percolation model;

[0129] A second determination unit 40 is used to obtain microseismic data through a microseismic sensor, and determine the distribution of microseismic events according to the microseismic data to obtain a microseismic characteristic signal;

[0130] The first calculation unit 50 is used to input the above-mentioned microseismic characteristic signal into the above-mentioned percolation prediction model to obtain a target percolation model and a target stress state, perform safety level evaluation based on the target stress state and the above-mentioned target percolation model, and perform grouting reinforcement based on the safety level evaluation.

[0131] Through this embodiment, the simulation unit performs environmental simulation based on different operating parameter groups, and performs mechanical tests under the simulated environment, and monitors the sound signals of coal rock samples during the crack evolution process through acoustic emission monitoring technology to obtain soundprint characteristic signals, and the coal rock samples are rock samples collected from the rock layer where the coal rock dam of the underground reservoir is located; the first determination unit performs analysis based on the soundprint characteristic signals to determine the percolation threshold of the connectivity of the crack clusters, and constructs a percolation model based on the soundprint characteristic signals and the percolation threshold, and the percolation model is used to describe the connectivity of the crack clusters under different operating parameter groups; the training unit performs soundprint characteristic signal ... under different operating parameter groups; the training unit performs soundprint characteristic signal analysis based on the soundprint characteristic signals to determine the percolation threshold of the connectivity of the crack clusters The percolation prediction model is learned by learning the acoustic wave characteristic signal, the crack evolution process and the percolation model, and the percolation prediction model is obtained. The percolation prediction model is used to predict the corresponding prediction model according to the number of acoustic wave characteristic signals, and the stress state is determined according to the percolation model; the second determination unit obtains microseismic data through the microseismic sensor, and determines the distribution of microseismic events according to the microseismic data to obtain the microseismic characteristic signal; the first calculation unit inputs the microseismic characteristic signal into the percolation prediction model to obtain the target percolation model and the target stress state, and performs the safety level evaluation based on the target stress state and the target percolation model, and performs grouting reinforcement based on the safety level evaluation. This application can more accurately predict and evaluate the safety status of the coal pillar dam by combining the acoustic emission monitoring technology and the microseismic monitoring technology. By constructing the percolation model and the percolation prediction model, the connectivity of the crack clusters can be effectively predicted, and then the stress state and safety level of the coal pillar dam can be judged, and the grouting reinforcement measures can be taken in time to prevent the leakage or damage of the dam body caused by the connection of the cracks, which significantly improves the safety and stability of the underground reservoir and provides technical support for the long-term safe operation of the underground reservoir. Moreover, through the combination of measured data and simulation tests, the accuracy and reliability of monitoring are improved. It is possible to monitor microseismic events and acoustic detection events of the coal pillar dam in real time, promptly discover potential safety hazards, and effectively prevent and control leakage of underground reservoirs and dam damage, which has significant practical application value and economic benefits.

[0132] In order to obtain the above voiceprint characteristic signal, in an optional implementation, the above simulation unit includes:

[0133] A first acquisition module is used to acquire a plurality of preset saturations, a plurality of dry-wet cycle times, and a plurality of preset water pressures, and obtain a plurality of the above-mentioned operating condition parameter groups by combining the above-mentioned preset saturations, the above-mentioned dry-wet cycle times, and the above-mentioned preset water pressures;

[0134] A first control module is used to load the test axial pressure and the test confining pressure to be consistent with the existing stress state of the coal pillar dam body to obtain a first state;

[0135] A second control module is used to increase the test axial pressure and the test confining pressure at a first preset rate based on the first state until the coal-rock sample is destroyed to obtain a second state;

[0136] The third control module is used to monitor the sound signal of the coal rock sample entering the second state to obtain the voiceprint characteristic signal.

[0137] In order to determine the percolation model, in an optional implementation, the first determining unit includes:

[0138] A first processing module is used to locate and mark the location based on the voiceprint feature signal, where the location where the acoustic emission event exists is marked with the first identification information, and where the location where the acoustic emission event does not exist is marked with the second identification information;

[0139] A construction module, used for constructing squares of different lengths to cover the first identification information, wherein the squares do not completely overlap with each other;

[0140] A first determination module is used to determine that the squares are in the same crack cluster when any two of the squares are in contact with each other;

[0141] A second determination module is used to determine the fracture network under the current grid length as a percolation state if the fracture clusters are connected in any one of the x, y and z directions when the coal rock sample enters the second state;

[0142] A third determination module is used to scale the grid length in the percolation state based on a dichotomy method until the crack clusters corresponding to the grid are not connected in the x, y and z directions, and determine the grid length as the percolation threshold;

[0143] The fourth determination module is used to determine the above-mentioned crack cluster corresponding to the above-mentioned grid length as the above-mentioned percolation model.

[0144] In order to obtain the above percolation prediction model, in an optional implementation, the above training unit includes:

[0145] A second acquisition module is used to acquire the evolution data of the above-mentioned crack clusters under different working condition parameter groups, and to mark the above-mentioned evolution data based on different stress stages;

[0146] The second processing module is used to select the crack clusters corresponding to the crack initiation stress, the crack damage stress and the peak stress in the annotated evolution data, annotate them again, and use the evolution data after two updates as the first training data set;

[0147] A training module is used to train the model based on the first training data set, the voiceprint feature signal and the percolation model to obtain the percolation prediction model.

[0148] In order to determine the layout of the microseismic sensors, in an optional implementation, the apparatus further includes:

[0149] An acquisition unit, used for acquiring the height of the coal pillar dam before acquiring the microseismic data through the microseismic sensor, and calibrating the first position on the coal pillar dam with a preset ratio and the height;

[0150] A third determining unit is used to divide the portion of the coal pillar dam body below the first position into grids of a first preset specification, and bury a microseismic sensor in the center of the grid;

[0151] The fourth determining unit is used to divide the portion of the coal pillar dam body higher than the first position into a grid of a second preset specification, and bury the microseismic sensor in the center of the grid.

[0152] In the above embodiment, in order to ensure that the microseismic sensor can effectively monitor the dynamic changes of the cracks inside the coal pillar dam, the buried depth requirement of the sensor is specially set. Specifically, the buried position of the sensor needs to go deep into the dam, and the depth must at least exceed the second position calibrated on the width of the coal pillar dam by a preset ratio.

[0153] In order to ensure the safety of the coal pillar dam, in an optional implementation manner, the first calculation unit includes:

[0154] A fifth determination module, configured to determine the safety level of the coal pillar dam body as the first safety level when the target stress state is less than the fracture initiation stress;

[0155] A sixth determination module, configured to determine the safety level of the coal pillar dam body as the second safety level when the target stress state is greater than or equal to the crack initiation stress and less than or equal to the crack damage stress;

[0156] a seventh determination module, configured to determine the safety level of the coal pillar dam body as a third safety level when the target stress state is greater than the fracture damage stress;

[0157] The fourth control module is used to determine the connection points of the above-mentioned fracture clusters in the above-mentioned coal pillar dam body based on the above-mentioned target percolation model when the above-mentioned coal pillar dam body is at the above-mentioned third safety level, and perform grouting reinforcement at the above-mentioned connection points.

[0158] The above-mentioned coal pillar dam body safety monitoring device based on acoustic detection events and microseismic events includes a processor and a memory, and the above-mentioned simulation unit, the first determination unit, the training unit, the second determination unit and the first calculation unit are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to realize the corresponding functions. The above-mentioned modules are all located in the same processor; or, the above-mentioned modules are located in different processors in the form of any combination.

[0159] The processor includes a kernel, which calls the corresponding program unit from the memory. One or more kernels can be set, and the efficiency of coal pillar dam monitoring can be improved by adjusting kernel parameters.

[0160] The memory may include non-permanent memory in a computer-readable medium, 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.

[0161] An embodiment of the present invention provides a computer-readable storage medium, which includes a stored program, wherein when the program is running, the device where the computer-readable storage medium is located is controlled to execute the coal pillar dam safety monitoring method based on acoustic events and microseismic events.

[0162] An embodiment of the present invention provides a processor, and the processor is used to run a program, wherein the program, when running, executes the coal pillar dam body safety monitoring method based on acoustic events and microseismic events.

[0163] An embodiment of the present invention provides a coal pillar dam monitoring system, 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 at least the steps of the above-mentioned coal pillar dam safety monitoring method based on acoustic events and microseismic events.

[0164] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program that initializes at least the steps of the above-mentioned coal pillar dam safety monitoring method based on acoustic events and microseismic events.

[0165] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0166] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0167] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0168] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0169] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0170] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0171] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0172] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules 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 technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0173] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0174] From the above description, it can be seen that the above embodiments of the present application achieve the following technical effects:

[0175] 1) The coal pillar dam safety monitoring method based on acoustic events and microseismic events of the present application firstly performs environmental simulation based on different working condition parameter groups, and conducts mechanical tests under the simulated environment, and monitors the sound signals of coal rock samples during the crack evolution process through acoustic emission monitoring technology to obtain soundprint characteristic signals, where the coal rock samples are rock samples collected from the rock layer where the coal rock dam of the underground reservoir is located; then, an analysis is performed based on the soundprint characteristic signals to determine the percolation threshold of the connection of the crack clusters, and a percolation model is constructed based on the soundprint characteristic signals and the percolation threshold, and the percolation model is used to describe the crack clusters under different working condition parameter groups. The connectivity of the cluster is determined by the acoustic emission characteristic signal, the crack evolution process and the percolation model. The percolation prediction model is used to predict the corresponding prediction model according to the number of acoustic emission characteristic signals, and the stress state is determined according to the percolation model. After that, the microseismic data is obtained through the microseismic sensor, and the distribution of microseismic events is determined according to the microseismic data to obtain the microseismic characteristic signal. Finally, the microseismic characteristic signal is input into the percolation prediction model to obtain the target percolation model and the target stress state. The safety level is evaluated based on the target stress state and the target percolation model, and grouting reinforcement is performed based on the safety level evaluation. This application can more accurately predict and evaluate the safety status of the coal pillar dam by combining acoustic emission monitoring technology and microseismic monitoring technology. By constructing a percolation model and a percolation prediction model, the connectivity of the fracture clusters can be effectively predicted, and then the stress state and safety level of the coal pillar dam can be judged, and grouting reinforcement measures can be taken in time to prevent leakage or damage to the dam body caused by the connection of fractures, which significantly improves the safety and stability of the underground reservoir and provides technical support for the long-term safe operation of the underground reservoir. Moreover, through the combination of measured data and simulation tests, the accuracy and reliability of monitoring are improved. It is possible to monitor microseismic events and acoustic detection events of the coal pillar dam in real time, promptly discover potential safety hazards, and effectively prevent and control leakage of underground reservoirs and dam damage, which has significant practical application value and economic benefits.

[0176] 2) The coal pillar dam safety monitoring device based on acoustic events and microseismic events of the present application, the simulation unit performs environmental simulation based on different operating parameter groups, and performs mechanical tests in the simulated environment, and monitors the sound signals of coal rock samples during the evolution of cracks through acoustic emission monitoring technology to obtain soundprint characteristic signals, and the coal rock samples are rock samples collected from the rock layer where the coal rock dam of the underground reservoir is located; the first determination unit performs analysis based on the soundprint characteristic signal to determine the percolation threshold of the connection between the crack clusters, and constructs a percolation model based on the soundprint characteristic signal and the percolation threshold, and the percolation model is used to describe the crack clusters under different operating parameter groups. Connectivity; the training unit learns based on the acoustic signature signal, the crack evolution process and the percolation model to obtain a percolation prediction model, which is used to predict the corresponding prediction model according to the number of acoustic signature signals, and determine the stress state according to the percolation model; the second determination unit obtains microseismic data through the microseismic sensor, and determines the distribution of microseismic events according to the microseismic data to obtain a microseismic signature signal; the first calculation unit inputs the microseismic signature signal into the percolation prediction model to obtain a target percolation model and a target stress state, performs a safety level evaluation based on the target stress state and the target percolation model, and performs grouting reinforcement based on the safety level evaluation. This application can more accurately predict and evaluate the safety status of the coal pillar dam by combining acoustic emission monitoring technology and microseismic monitoring technology. By constructing a percolation model and a percolation prediction model, the connectivity of the fracture clusters can be effectively predicted, and then the stress state and safety level of the coal pillar dam can be judged, and grouting reinforcement measures can be taken in time to prevent leakage or damage to the dam body caused by fracture connectivity, which significantly improves the safety and stability of the underground reservoir and provides technical support for the long-term safe operation of the underground reservoir. Moreover, through the combination of measured data and simulation tests, the accuracy and reliability of monitoring are improved. It is possible to monitor microseismic events and acoustic detection events of the coal pillar dam in real time, promptly discover potential safety hazards, and effectively prevent and control leakage of underground reservoirs and dam damage, which has significant practical application value and economic benefits.

[0177] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for monitoring coal pillar dam safety based on acoustic events and microseismic events, characterized in that: include: Environmental simulation is performed based on different working condition parameter groups, and mechanical tests are carried out in the simulated environment. The acoustic signals of coal rock samples during the crack evolution process are monitored by acoustic emission monitoring technology to obtain acoustic print characteristic signals. The coal rock samples are rock samples collected from the rock stratum where the coal rock dam of the underground reservoir is located; Performing analysis based on the voiceprint characteristic signal to determine the percolation threshold of the connectivity of the fracture clusters, and constructing a percolation model based on the voiceprint characteristic signal and the percolation threshold, wherein the percolation model is used to describe the connectivity of the fracture clusters under different operating parameter groups; Based on the voiceprint characteristic signal, the crack evolution process and the percolation model, learning is performed to obtain a percolation prediction model, wherein the percolation prediction model is used to predict the corresponding prediction model according to the number of the voiceprint characteristic signal, and determine the stress state according to the percolation model; Acquiring microseismic data through a microseismic sensor, and determining the distribution of microseismic events based on the microseismic data to obtain a microseismic characteristic signal; The microseismic characteristic signal is input into the percolation prediction model to obtain a target percolation model and a target stress state, a safety level evaluation is performed based on the target stress state and the target percolation model, and grouting reinforcement is performed based on the safety level evaluation.

2. The method according to claim 1, characterized in that Based on different working condition parameter groups, environmental simulation is carried out, and mechanical tests are carried out in the simulated environment. The acoustic signals of the coal and rock samples during the crack evolution process are monitored by acoustic emission monitoring technology to obtain acoustic print characteristic signals, including: Acquire a plurality of preset saturations, a plurality of dry-wet cycle times, and a plurality of preset water pressures, and obtain a plurality of the operating condition parameter groups by combining the preset saturations, the dry-wet cycle times, and the preset water pressures; The test axial pressure and the test confining pressure are loaded to be consistent with the existing stress state of the coal pillar dam body to obtain a first state; Taking the first state as a reference, increasing the test axial pressure and the test confining pressure at a first preset rate until the coal-rock sample is destroyed, thereby obtaining a second state; The sound signal of the coal rock sample entering the second state is monitored to obtain the voiceprint characteristic signal.

3. The method according to claim 2, characterized in that An analysis is performed based on the voiceprint characteristic signal to determine a percolation threshold for connecting the crack clusters, and a percolation model is constructed based on the voiceprint characteristic signal and the percolation threshold, including: Positioning and marking based on the voiceprint characteristic signal, marking the location where the acoustic emission event exists with the first identification information, and marking the location where the acoustic emission event does not exist with the second identification information; Constructing squares of different lengths to cover the first identification information, wherein the squares do not completely overlap with each other; In the case where any two of the squares are in contact with each other, the squares are determined to be in the same crack cluster; If the fracture clusters are connected in any one of the x, y and z directions when the coal rock sample enters the second state, the fracture network under the current grid length is determined to be in a percolation state; Scaling the grid length in the percolation state based on a dichotomy method until the crack clusters corresponding to the grid are not connected in the x, y and z directions, and determining the grid length as the percolation threshold; The crack cluster corresponding to the grid length is determined as the percolation model.

4. The method according to claim 3, characterized in that Based on the voiceprint feature signal, the crack evolution process and the percolation model, learning is performed to obtain a percolation prediction model, including: Acquire the evolution data of the crack cluster under different operating parameter groups, and mark the evolution data based on different stress stages; Selecting the crack clusters corresponding to the crack initiation stress, the crack damage stress and the peak stress in the annotated evolution data, annotating them again, and using the evolution data after two updates as the first training data set; The model is trained based on the first training data set, the voiceprint feature signal and the percolation model to obtain the percolation prediction model.

5. The method according to claim 1, characterized in that Before acquiring microseismic data through the microseismic sensor, the method further includes: Obtaining the height of the coal pillar dam, and calibrating a first position on the coal pillar dam using a preset ratio and the height; Dividing the portion of the coal pillar dam below the first position into grids of a first preset specification, and burying microseismic sensors in the center of the grids; The portion of the coal pillar dam body higher than the first position is divided into a grid of a second preset specification, and the microseismic sensor is buried in the center of the grid.

6. The method according to claim 5, characterized in that The buried depth of the microseismic sensor is at least greater than the second position, and the second position is obtained by calibrating the width of the coal pillar dam body according to the preset ratio.

7. The method according to claim 1, characterized in that At least based on the target percolation model, grouting reinforcement is performed on the connection points of the coal pillar dam body, including: When the target stress state is less than the crack initiation stress, the safety level of the coal pillar dam is determined to be the first safety level; When the target stress state is greater than or equal to the fracture initiation stress and less than or equal to the fracture damage stress, the safety level of the coal pillar dam is determined to be the second safety level; When the target stress state is greater than the fracture damage stress, the safety level of the coal pillar dam is determined to be the third safety level; When the coal pillar dam is at the third safety level, the connection points of the fracture clusters in the coal pillar dam are determined based on the target percolation model, and grouting reinforcement is performed at the connection points.

8. A coal pillar dam safety monitoring device based on acoustic events and microseismic events, characterized in that: The device comprises: A simulation unit is used to perform environmental simulation based on different working condition parameter groups, and to perform mechanical tests under the simulated environment, and to monitor the sound signals of coal rock samples during the crack evolution process through acoustic emission monitoring technology to obtain soundprint characteristic signals, wherein the coal rock samples are rock samples collected from the rock layer where the coal rock dam of the underground reservoir is located; A first determining unit is used to analyze the voiceprint characteristic signal to determine a percolation threshold for connectivity of fracture clusters, and to construct a percolation model based on the voiceprint characteristic signal and the percolation threshold, wherein the percolation model is used to describe connectivity of fracture clusters under different operating parameter groups; A training unit, configured to learn based on the voiceprint characteristic signal, the crack evolution process and the percolation model to obtain a percolation prediction model, wherein the percolation prediction model is used to predict the corresponding prediction model according to the number of the voiceprint characteristic signal, and determine the stress state according to the percolation model; A second determination unit is used to obtain microseismic data through a microseismic sensor, and determine the distribution of microseismic events according to the microseismic data to obtain a microseismic characteristic signal; The first calculation unit is used to input the microseismic characteristic signal into the percolation prediction model to obtain a target percolation model and a target stress state, perform a safety level evaluation based on the target stress state and the target percolation model, and perform grouting reinforcement based on the safety level evaluation.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the method according to any one of claims 1 to 7.

10. A coal pillar dam monitoring system, 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 are configured to be executed by the one or more processors, and the one or more programs include methods for executing any one of claims 1 to 7.

Images