Distributed water regimen monitoring method and system for underground coal mine working face

Abstract

The invention provides a distributed water regimen monitoring method and system for an underground coal mine working face, and relates to the field of coal mine safety monitoring. The method comprises the following steps: acquiring water regimen time sequence data; constructing a water regimen time sequence data vector according to a preset rule based on the water regimen time sequence data; the water regimen time sequence data vector comprises a value of water regimen time sequence data and a category of the water regimen time sequence data; the value of the water regimen time sequence data vector is compared with a preset threshold value of the corresponding category, if the value of the water regimen time sequence data vector is larger than or equal to the preset threshold value of the corresponding category, the water regimen time sequence data vector is marked as a target item, and the number of the target items is counted; comparing the number of the target items with a preset number threshold to obtain a comparison result, executing a corresponding data analysis operation according to the comparison result, and identifying a water regimen abnormal result; and performing corresponding early warning according to the water regimen abnormity result. The method is used in the distributed water regimen monitoring process of the coal mine underground working face, and solves the technical problems of lag and misjudgment in coal mine underground water disaster prediction in the prior art.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of coal mine safety monitoring, and in particular to a coal mine underground working face distributed water regime monitoring method and system. BACKGROUND

[0002] Coal mine underground water disaster is one of the main disaster types affecting coal mine safety production. Especially in the process of coal mining working face mining, affected by factors such as complex geological structure, variable hydrogeological conditions and mining disturbance, water inrush and water gushing accidents are easily induced, which poses a serious threat to the life safety of underground workers and the mine production system. Therefore, continuous and accurate monitoring of the water regime state of the coal mine underground working face and timely early warning in the early stage of water regime anomaly are important technical means to ensure the safety of coal mine production.

[0003] The existing coal mine underground water regime monitoring technology usually takes a single or a few hydrological parameters as the monitoring object, such as monitoring water pressure, water level or water inflow through piezometers, water level meters or flow meters. This kind of method can reflect the change of underground water regime to some extent, but it is difficult to fully characterize the water regime evolution process, especially for progressive water regime anomalies caused by hidden faults, collapse columns or fracture development zones, there is a problem of recognition lag. Therefore, it is urgent to develop a method that can integrate multi-source water regime monitoring data and multi-wave seismic detection information to accurately identify and review the water regime anomaly of the coal mine underground working face, and solve the problems of lag and misjudgment in the existing technology for predicting coal mine underground water disasters. SUMMARY

[0004] The present application provides a coal mine underground working face distributed water regime monitoring method and system, which solves the problem of lag and misjudgment in the existing technology for predicting coal mine underground water disasters.

[0005] To achieve the above-mentioned purpose, the present application adopts the following technical scheme: In a first aspect, a coal mine underground working face distributed water regime monitoring method is provided, comprising: acquiring water regime time series data, including vibration time series data, water pressure time series data, water quality turbidity time series data, and rock stratum micro-seepage flow velocity time series data; based on the water regime time series data, constructing a water regime time series data vector according to a preset rule; the water regime time series data vector includes the value of the water regime time series data and the category of the water regime time series data; comparing the value of the water regime time series data vector with the preset threshold value of the corresponding category, if the value of the water regime time series data vector is greater than or equal to the preset threshold value of the corresponding category, marking it as a target item, and counting the number of target items; comparing the number of target items with a preset number threshold to obtain a comparison result, and performing corresponding data analysis operations according to the comparison result to identify a water regime anomaly result; and performing corresponding early warning according to the water regime anomaly result.

[0006] In conjunction with the first aspect mentioned above, in one possible implementation, after identifying and issuing warnings for abnormal water conditions, the distributed water condition monitoring method for underground coal mine working faces further includes: acquiring multi-wave seismic data, including P-wave, S-wave, and channel wave seismic data; extracting the P-wave propagation velocity, S-wave propagation velocity, and channel wave energy attenuation characteristic parameters from the multi-wave seismic data; calculating the P-wave and S-wave velocity ratio and Poisson's ratio parameters of the coal seam and surrounding rock within the area of ​​abnormal water conditions based on the P-wave and S-wave propagation velocities; performing joint inversion on the P-wave, S-wave, and channel wave seismic data using the P-wave and S-wave velocity ratio and Poisson's ratio parameters as constraints to obtain the three-dimensional wave velocity distribution and energy attenuation distribution results of the coal seam and surrounding rock within the area of ​​abnormal water conditions; identifying structurally abnormal areas such as faults, collapse columns, or fracture development zones based on the three-dimensional wave velocity distribution and energy attenuation distribution results, and verifying the water condition anomaly warning results; and upgrading the warning level or triggering a joint warning when structural anomalies and water condition anomalies coexist.

[0007] In conjunction with the first aspect mentioned above, in one possible implementation, the number of target items is compared with a preset quantity threshold to obtain a comparison result. Based on the comparison result, corresponding data analysis operations are performed to identify abnormal water conditions, including: when the number of target items is zero, a first data analysis operation is performed; when the number of target items is greater than zero and less than the preset quantity threshold, a second data analysis operation is performed; when the number of target items is greater than or equal to the preset quantity threshold, a third data analysis operation is performed; and based on the first data analysis operation and / or the second data analysis operation and / or the third data analysis operation, abnormal water conditions are identified.

[0008] In conjunction with the first aspect mentioned above, in one possible implementation, when the number of target items is zero, a first data analysis operation is performed, including: calculating the mean of each data item in the hydrological time series data vector to obtain the corresponding data item mean; obtaining the data item mean obtained in the first five calculations and sorting the first five data item mean values ​​according to time sequence; calculating the difference between the currently calculated data item mean and the mean of the first sorted data item to obtain the mean difference; when the mean difference is positive and greater than a set first mean difference threshold and less than or equal to a set second mean difference threshold, adjusting the acquisition frequency corresponding to the data item and shortening the acquisition frequency to two-thirds of the original acquisition frequency; when the mean difference is positive and greater than the second mean difference threshold, a second data analysis operation is performed.

[0009] In conjunction with the first aspect mentioned above, in one possible implementation, when the number of target items is greater than zero and less than a set threshold, a second data analysis operation is performed, including: substituting the hydrological time-series data vector into a linear regression model, outputting the predicted value corresponding to each data item in the hydrological time-series data vector, wherein the linear regression model includes regression coefficients and intercept parameters; setting multiple judgment conditions related to hydrological anomalies, and assigning corresponding weights to each judgment condition, including whether the water pressure exceeds different pressure thresholds and whether it belongs to a key monitoring node; sequentially matching the data items in the hydrological time-series data vector with multiple judgment conditions, counting the number of data items that meet the conditions under each judgment condition, and obtaining the condition compliance number; performing a weighted conversion and summing of the condition compliance numbers to obtain the condition compliance value; substituting the hydrological time-series data vector and the condition compliance value into the XGBoost model, and outputting the result value corresponding to the hydrological time-series data vector, wherein the loss function of the XGBoost model introduces a regularization term to constrain the number of judgment conditions; the XGBoost model satisfies the following formula:

[0010] Among them, For loss function, This represents the last data item collected in the hydrological time-series data vector. For predicted values ​​of hydrological time series data items; For regularization terms, To determine the penalty strength for the number of conditions T, λ represents the smoothness of the weights corresponding to the conditions. The condition is met; when the result value is greater than the preset result threshold, a water situation anomaly command is generated; when the result value is less than or equal to the result threshold, the collection frequency of the corresponding data item is adjusted, and the collection frequency is shortened to one-third of the original collection frequency until the mean of the data item is within the preset range within the preset time, and the original collection frequency of the data item is restored.

[0011] In conjunction with the first aspect mentioned above, in one possible implementation, when the number of target items is greater than or equal to a set quantity threshold, a third data analysis operation is performed, including: performing a second data analysis operation on all hydrological time series data vectors respectively to obtain multiple corresponding hydrological time series data vector result values; weighting the multiple corresponding hydrological time series data vector result values ​​according to preset weight parameters to obtain a comprehensive result; and issuing an early warning when the comprehensive result is within a first preset range.

[0012] In conjunction with the first aspect mentioned above, in one possible implementation, the P-wave and S-wave velocity ratio and Poisson's ratio parameters of the coal seam and surrounding rock in the area of ​​abnormal water conditions are calculated based on the P-wave propagation velocity and the S-wave propagation velocity. This includes: calculating the P-wave and S-wave velocity ratio based on the P-wave propagation velocity and the S-wave propagation velocity; and calculating the Poisson's ratio parameters of the coal seam and surrounding rock based on the elastic wave propagation relationship, wherein the Poisson's ratio parameters are determined by the P-wave and S-wave velocity ratio.

[0013] In conjunction with the first aspect mentioned above, in one possible implementation, the P-wave, S-wave, and channel wave seismic data are jointly inverted using the P-wave / S-wave velocity ratio and Poisson's ratio parameters to obtain the three-dimensional wave velocity distribution and energy attenuation distribution results of the coal seam and surrounding rock within the area of ​​hydrological anomaly. This includes: applying joint inversion constraints to the P-wave, S-wave, and channel wave seismic data based on the P-wave / S-wave velocity ratio and Poisson's ratio parameters to generate an initial wave velocity model, including the three-dimensional P-wave and S-wave velocity distribution results of the coal seam and surrounding rock within the area of ​​hydrological anomaly; using a tomographic inversion method to iteratively update the initial wave velocity model to obtain the three-dimensional wave velocity distribution results of the coal seam and surrounding rock within the area of ​​hydrological anomaly; and performing attenuation inversion on the initial wave velocity model based on the energy attenuation characteristics of the channel wave, combined with the three-dimensional P-wave and S-wave velocity distribution results, to obtain the energy attenuation distribution results of the coal seam and surrounding rock within the area of ​​hydrological anomaly.

[0014] In conjunction with the first aspect mentioned above, in one possible implementation, based on the three-dimensional wave velocity distribution results and energy attenuation distribution results, structural anomaly areas such as faults, collapse columns, or fracture development zones are identified, and the early warning results for hydrological anomalies are verified. This includes: identifying low-velocity anomaly areas with a significant decrease in wave velocity relative to the surrounding area in the three-dimensional wave velocity distribution results, as candidate areas for structural anomalies; identifying high-energy attenuation areas spatially corresponding to the low-velocity anomaly areas in the energy attenuation distribution results; performing spatial overlay analysis on the low-velocity anomaly areas and high-energy attenuation areas to determine structural anomaly areas within the coal seam and surrounding rock; classifying structural anomaly areas into faults, collapse columns, or fracture development zones based on their spatial morphological characteristics, wave velocity reduction magnitude, and energy attenuation characteristics; and performing spatial matching analysis between structural anomaly areas and areas where hydrological anomalies occur to verify the early warning results for hydrological anomalies.

[0015] Secondly, a distributed hydrological monitoring system for underground coal mine working faces is provided, comprising: a sensor module, a monitoring module, and a verification monitoring module; wherein, the sensor module includes several sensor nodes distributedly located at the underground coal mine working face, used to collect time-series hydrological data and transmit the time-series data to the monitoring module; the time-series hydrological data includes vibration time-series data, water pressure time-series data, water turbidity time-series data, and rock strata micro-seepage velocity time-series data; the monitoring module includes at least one monitoring substation, used to receive the time-series hydrological data transmitted by the sensor module, and preprocess the time-series data to construct a hydrological time-series data vector; The hydrological time-series data vector is compared with the preset threshold of the corresponding category to count the number of target items, and corresponding data analysis operations are performed based on the number of target items to identify hydrological anomalies. The host computer communicates with the monitoring module to perform early warning processing based on hydrological anomalies. After receiving a hydrological anomaly early warning, multi-wave seismic data is acquired, and P-wave, S-wave, and channel wave seismic data are jointly inverted to obtain the three-dimensional wave velocity distribution and energy attenuation distribution of coal seams and surrounding rocks in the area where hydrological anomalies occur. Based on the three-dimensional wave velocity distribution and energy attenuation distribution, structural anomaly areas are identified, and the hydrological anomaly early warning results are reviewed or the early warning level is upgraded.

[0016] This application provides a distributed hydrological monitoring method and system for underground coal mine working faces. By simultaneously acquiring time-series data of water pressure, water turbidity, and rock micro-seepage velocity, a hydrological time-series data vector containing data values ​​and data categories is constructed. This enables a multi-dimensional comprehensive characterization of underground hydrological conditions, avoiding the information insufficiency problem caused by monitoring a single hydrological parameter and improving the comprehensiveness and accuracy of hydrological anomaly identification. By comparing the hydrological time-series data vector with preset thresholds for corresponding categories, target items are marked and their numbers are counted. Different data analysis operations are then performed based on the comparison results between the number of target items and preset thresholds, enabling hierarchical judgment of hydrological conditions. This allows for the differentiation of different hydrological conditions such as normal fluctuations, gradual anomalies, and significant anomalies, improving the sensitivity and reliability of hydrological anomaly identification. Performing corresponding data analysis operations under different target item counts effectively considers both short-term fluctuation characteristics and medium- to long-term trends in hydrological data, avoiding false alarms or missed alarms caused by relying solely on single threshold judgments. This facilitates early identification and stable warning of hydrological anomalies. Based on the identified water anomalies, corresponding early warnings are issued to match the warning strategy with the degree of water anomaly, and early warning information is issued in a timely manner at the initial stage of water anomalies, thus solving the problems of lag and misjudgment in the prediction of water hazards in coal mines by existing technologies.

[0017] It should be understood that the descriptions of technical features, technical solutions, beneficial effects, or similar language in this application do not imply that all features and advantages can be achieved in any single embodiment. Rather, it is understood that the description of a feature or beneficial effect means that a specific technical feature, technical solution, or beneficial effect is included in at least one embodiment. Therefore, the descriptions of technical features, technical solutions, or beneficial effects in this specification do not necessarily refer to the same embodiment. Furthermore, the technical features, technical solutions, and beneficial effects described in this embodiment can be combined in any suitable manner. Those skilled in the art will understand that embodiments can be implemented without one or more specific technical features, technical solutions, or beneficial effects of a particular embodiment. In other embodiments, additional technical features and beneficial effects may be identified in specific embodiments that do not embody all embodiments. Attached Figure Description

[0018] Figure 1 A system architecture diagram of a distributed hydrological monitoring system for underground coal mine working faces provided in this application embodiment; Figure 2 A flowchart illustrating a distributed hydrological monitoring method for underground coal mine working faces, provided as an embodiment of this application; Figure 3 A flowchart illustrating another distributed hydrological monitoring method for underground coal mine working faces provided in this application embodiment; Figure 4 A flowchart illustrating another distributed hydrological monitoring method for underground coal mine working faces provided in this application embodiment; Figure 5 A flowchart illustrating another distributed hydrological monitoring method for underground coal mine working faces provided in this application embodiment; Figure 6 This is a flowchart illustrating another distributed hydrological monitoring method for underground coal mine working faces, provided as an embodiment of this application. Detailed Implementation

[0019] In the description of this application, unless otherwise stated, " / " means "or," for example, A / B can mean A or B. The "and / or" in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone. Furthermore, "at least one" means one or more, and "multiple" means two or more. The terms "first," "second," etc., do not limit the quantity or order of execution, and "first," "second," etc., do not necessarily imply differences.

[0020] It should be noted that, in this application, the terms "exemplary" or "for example" are used to indicate that something is being described as an example, illustration, or illustration. Any embodiment or design described as "exemplary" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or design solutions. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0021] The distributed hydrological monitoring method for underground coal mine working faces provided in this application embodiment can be applied to, for example... Figure 1 In the distributed hydrological monitoring system shown for underground coal mine working faces, such as Figure 1 As shown, the system includes: sensor module 101, monitoring module 102, and verification monitoring module 103.

[0022] The sensor module 101 includes several distributed sensor nodes located in the underground working face of the coal mine, which are used to collect water condition time series data in the coal mine and transmit the water condition time series data to the monitoring module. The water condition time series data includes vibration time series data, water pressure time series data, water quality turbidity time series data, and rock stratum micro-seepage velocity time series data.

[0023] In one possible implementation, the sensor module further includes an optical fiber and a wireless communication module. The communication unit transmits hydrological information to the monitoring station module via the optical fiber or the wireless communication module. Specifically, it performs a continuity test on the optical fiber; if the test passes, transmission occurs through the optical fiber; if the test fails, transmission is switched to the wireless communication module, and a corresponding fault command for the optical fiber is generated. The wireless communication module includes a backup power supply to power both the sensor and the wireless communication module. This prevents data transmission interruptions due to optical fiber failure or damage, which would hinder monitoring of the mine.

[0024] The monitoring module 102 includes at least one monitoring substation, which is used to receive water condition time series data sent by the sensor module, preprocess the water condition time series data, construct a water condition time series data vector, compare the water condition time series data vector with the preset threshold of the corresponding category, count the number of target items, and perform corresponding data analysis operations according to the number of target items to identify abnormal water condition results. The verification monitoring module 103 is connected to the monitoring module and is used to perform early warning processing based on the results of water anomalies. After receiving the water anomaly early warning, it acquires multi-wave seismic data, performs joint inversion on the seismic data of P-wave, S-wave and channel wave to obtain the three-dimensional wave velocity distribution and energy attenuation distribution results of coal seam and surrounding rock in the area where the water anomaly occurs, and identifies the structural anomaly area based on the three-dimensional wave velocity distribution and energy attenuation distribution results, and verifies or upgrades the early warning level of the water anomaly.

[0025] To address the issues of lag and misjudgment in existing technologies for predicting water hazards in coal mines, this application provides a distributed water situation monitoring method for underground coal mine working faces. The method includes: acquiring water situation time-series data, including water pressure time-series data, water turbidity time-series data, and rock strata micro-seepage velocity time-series data; constructing a water situation time-series data vector based on the water situation time-series data according to preset rules; the water situation time-series data vector includes the value and category of the water situation time-series data; comparing the value of the water situation time-series data vector with a preset threshold for the corresponding category; if the value of the water situation time-series data vector is greater than or equal to the preset threshold for the corresponding category, it is marked as a target item, and the number of target items is counted; comparing the number of target items with a preset quantity threshold to obtain a comparison result, and performing corresponding data analysis operations based on the comparison result to identify abnormal water situation results; and issuing corresponding early warnings based on the abnormal water situation results.

[0026] Figure 2 This is a flowchart illustrating the distributed hydrological monitoring method for underground coal mine working faces provided in an embodiment of this application, as shown below. Figure 2 As shown, the method includes: S201. Acquire hydrological time-series data, including vibration time-series data, water pressure time-series data, water turbidity time-series data, and rock strata micro-seepage velocity time-series data.

[0027] In one possible implementation, microseismic sensors, fiber optic piezometers, laser turbidimeters, and millimeter-wave radar are distributed underground in the coal mine. The microseismic sensors collect vibration data corresponding to the sensor nodes; the fiber optic piezometers sense and collect water pressure data corresponding to the sensor nodes; the laser turbidimeters detect water turbidity data corresponding to the sensor nodes; and the millimeter-wave radar scans the sensor nodes and identifies the flow velocity data of micro-seepage in the rock strata. The data collected by the microseismic sensors, fiber optic piezometers, laser turbidimeters, and millimeter-wave radar are labeled as hydrological time-series data.

[0028] It should be noted that the collection frequency of different types of hydrological time series data is set according to monitoring needs, and various types of data can be time-aligned through a synchronization mechanism during the collection process to ensure the effectiveness of subsequent analysis.

[0029] S202. Based on hydrological time series data, construct hydrological time series data vectors according to preset rules.

[0030] The hydrological time series data vector includes the values ​​and categories of the hydrological time series data.

[0031] In one possible implementation, hydrological time-series data is converted into text in numerical form to facilitate analysis and processing by monitoring substations; then, the timestamps corresponding to the hydrological time-series data are obtained, and the corresponding data items within the hydrological information are sorted according to the timestamps to construct a hydrological time-series data vector, i.e., {X}.i1 X i2 ..., X in}, i represents the category of the data item (vibration data, water pressure data, water turbidity data, etc.), and n represents the total number of data items.

[0032] As an example, in the embodiments of this application, i=1 represents the data item corresponding to vibration data, i=2 represents the data item corresponding to water pressure data, i=3 represents the data item corresponding to water turbidity data, and i=4 represents the data item corresponding to flow velocity data.

[0033] S203. Compare the value of the hydrological time series data vector with the preset threshold of the corresponding category. If the value of the hydrological time series data vector is greater than or equal to the preset threshold of the corresponding category, it is marked as a target item, and the number of target items is counted.

[0034] In one possible implementation, the data items in the hydrological time series data vector are judged one by one against the threshold corresponding to the data item category. If a data item is greater than or equal to the threshold, the data item is marked as a target item, and the number of target items is counted.

[0035] As an example, in this embodiment of the application, different thresholds are set for vibration, water pressure, water turbidity and rock micro-seepage velocity, and each data item in the hydrological time series data vector is compared with the corresponding threshold.

[0036] S204. Compare the number of target items with the preset quantity threshold to obtain the comparison result, and perform the corresponding data analysis operation based on the comparison result to identify abnormal water conditions.

[0037] In one possible implementation, when the number of target items is zero, a first data analysis operation is performed; when the number of target items is greater than zero and less than a set quantity threshold, a second data analysis operation is performed; when the number of target items is greater than or equal to the set quantity threshold, a third data analysis operation is performed; based on the first data analysis operation and / or the second data analysis operation and / or the third data analysis operation, abnormal water conditions are identified.

[0038] Based on the above steps, this department uses a tiered approach to assess the number of target items to achieve differentiated analysis of water condition status, thereby enhancing the accuracy and stability of water condition anomaly identification.

[0039] S205. Issue corresponding early warnings based on abnormal water conditions.

[0040] Among them, the abnormal water condition result refers to the judgment result obtained through data analysis operations, which reflects whether there is an abnormality in the current underground water condition of the coal mine and the degree of abnormality.

[0041] In one possible implementation, different levels of early warning information are triggered based on the level or type of abnormal water conditions, and the information is output through a display terminal, an audible and visual alarm device, or a communication terminal. The early warning information is then transmitted to a verification monitoring module to verify stress changes and abnormal water conditions at the coal mine working face.

[0042] It should be noted that the early warning method can be configured according to the actual needs of the coal mine site, and the early warning information can be sent to both the underground and surface monitoring systems at the same time.

[0043] This application embodiment comprehensively acquires various types of water condition time-series data, including vibration, water pressure, water turbidity, and micro-seepage velocity in rock strata. Based on preset rules, it constructs a water condition time-series data vector to achieve a multi-dimensional unified representation of the water condition status of underground coal mine working faces. By comparing the water condition time-series data vector with preset thresholds for corresponding categories and counting the number of target items, and performing differentiated data analysis operations based on the comparison results of the number of target items and preset thresholds, it can promptly and effectively distinguish between normal fluctuations and abnormal changes in water conditions, improving the accuracy, stability, and timeliness of water condition anomaly identification. Furthermore, based on the identified water condition anomaly results, it provides graded early warnings, which is conducive to timely perception and response to underground coal mine water condition anomalies, reducing the risk of false alarms and missed alarms, and solving the problems of lag and misjudgment in existing technologies for predicting underground coal mine water hazards.

[0044] In one possible implementation of the embodiments of this application, combined with Figure 2 ,like Figure 3 As shown, the above S204 can be specifically implemented through the following S301 to S304, which are explained in detail below: S301. When the number of target items is zero, perform the first data analysis operation.

[0045] In one possible implementation, when the number of target items is zero, the mean of each data item in the hydrological time series data vector is calculated to obtain the mean of the corresponding data item; the mean of the data item obtained in the first five calculations is obtained, and the mean of the first five data items is sorted according to the time sequence; the difference between the mean of the currently calculated data item and the mean of the first sorted data item is calculated to obtain the mean difference; when the mean difference is positive and greater than the set first mean difference threshold and less than or equal to the set second mean difference threshold, the acquisition frequency corresponding to the data item is adjusted, and the acquisition frequency is shortened to two-thirds of the original acquisition frequency; when the mean difference is positive and greater than the second mean difference threshold, the second data analysis operation is performed.

[0046] It should be noted that the first data analysis operation focuses on identifying subtle changes in hydrological data to determine whether there is a trend of hydrological conditions evolving from a normal state to an abnormal state.

[0047] Based on the above steps, this step, with zero target items, achieves continuous monitoring of potential changes in water conditions through the first data analysis operation, thereby improving the sensitivity to changes in water conditions.

[0048] S302. When the number of target items is greater than zero and less than the set number threshold, execute the second data analysis operation.

[0049] In one possible implementation, the hydrological time-series data vector is substituted into a linear regression model to output the predicted value corresponding to each data item in the hydrological time-series data vector. The linear regression model includes regression coefficients and intercept parameters. Multiple judgment conditions related to hydrological anomalies are set, and a corresponding weight is assigned to each judgment condition. Judgment conditions include whether the water pressure exceeds different pressure thresholds and whether it belongs to a critical monitoring node. The data items in the hydrological time-series data vector are sequentially matched with the multiple judgment conditions, and the number of data items that meet each judgment condition is counted to obtain the condition compliance number. The condition compliance number is then further analyzed. The weighted average is calculated and summed to obtain the condition compliance value. The hydrological time series data vector and the condition compliance value are substituted into the XGBoost model to output the result value corresponding to the hydrological time series data vector. A regularization term is introduced into the loss function of the XGBoost model to constrain the number of judgment conditions. When the result value is greater than the preset result threshold, a hydrological anomaly command is generated. When the result value is less than or equal to the result threshold, the acquisition frequency of the corresponding data item is adjusted, and the acquisition frequency is shortened to one-third of the original acquisition frequency until the mean of the data item is within the preset range within the preset time. The original acquisition frequency of the data item is then restored.

[0050] As an example, in an embodiment of this application, the XGBoost model satisfies the following formula:

[0051] Among them, For loss function, This represents the last data item collected in the hydrological time-series data vector. For predicted values ​​of hydrological time series data items; For regularization terms, To determine the penalty strength for the number of conditions T, λ represents the smoothness of the weights corresponding to the conditions. For values ​​that meet the conditions, The weights are the T judgment conditions corresponding to the hydrological time series data vector.

[0052] Based on the above steps, this step improves the precision of anomaly identification by using a second data analysis operation when initial abnormal signs appear in the water situation.

[0053] S303. When the number of target items is greater than or equal to the set quantity threshold, execute the third data analysis operation.

[0054] In one possible implementation, the second data analysis operation is performed on all hydrological time series data vectors to obtain multiple corresponding hydrological time series data vector result values; the multiple corresponding hydrological time series data vector result values ​​are weighted according to preset weight parameters to obtain a comprehensive result; when the comprehensive result is within the first preset range, an early warning is issued.

[0055] It should be noted that the third data analysis operation focuses on the overall judgment of water situation anomalies, and is used to confirm whether the water situation has entered a high-risk state.

[0056] Based on the above steps, when there are a large number of target items, a third data analysis operation can be used to reliably identify significant hydrological anomalies.

[0057] S304. Based on the first data analysis operation and / or the second data analysis operation and / or the third data analysis operation, identify abnormal water conditions.

[0058] Among them, the abnormal water situation results refer to the analytical conclusions output by combining different data analysis operations, which are used to reflect whether the current water situation is abnormal and the degree of abnormality.

[0059] In one possible implementation, the water situation is comprehensively judged based on the type of data analysis operation performed and its analysis results, and corresponding water situation anomaly results are generated.

[0060] It should be noted that different data analysis operations can be used independently or in combination to adapt to the anomaly identification needs under different water condition change scenarios.

[0061] Based on the above steps, a unified output of hydrological anomaly results can be achieved, enhancing the completeness and consistency of hydrological anomaly identification results.

[0062] This application embodiment achieves differentiated analysis and comprehensive judgment of different water conditions by classifying the number of target items and performing corresponding data analysis operations. Through the dynamic sampling frequency adjustment mechanism of the first data analysis operation, the sampling density is automatically increased in the early stage of abnormal data trends. Through the combination of linear regression model and XGBoost model of the second data analysis operation, the gradual anomalies of water information are identified, thereby enabling early prediction. This avoids the problems of monitoring failing to capture trend changes and response delays leading to delayed early warnings, reduces the risk of misjudgment caused by a single judgment method, enhances the timeliness and reliability of underground water condition monitoring in coal mines, and solves the problem of lagging monitoring of abnormal underground water conditions in existing technologies.

[0063] In one possible implementation, combiningFigure 2 ,like Figure 4 As shown, after S205, the distributed hydrological monitoring method for underground coal mine working faces provided in this application embodiment further includes the following S401 to S406: S401. Acquire multi-wave seismic data, including P-wave, S-wave, and tungsten-wave seismic data.

[0064] Among them, multi-wave seismic data refers to the seismic wave response data of different types obtained by seismic excitation and receiving devices in the underground working area of ​​coal mines. Different wave types have different sensitivities to coal seams and surrounding rock structures.

[0065] In one possible implementation, after identifying water anomalies and issuing an early warning, a seismic source and geophone array are deployed in the target area where the water anomaly occurs. Seismic waves are excited by artificial seismic sources or vibration sources, and P-waves, S-waves, and channel waves propagating along the coal seam are collected simultaneously. The collected data are then uniformly time-calibrated and stored.

[0066] It should be noted that multi-wave seismic data can be acquired after an anomaly warning is triggered, or it can be periodically collected and analyzed before the warning to improve emergency response efficiency.

[0067] Based on the above steps, this step acquires multi-wave seismic data to provide data support for subsequent extraction of propagation characteristics of different wave types and joint inversion.

[0068] S402. Extract the P-wave propagation velocity, S-wave propagation velocity, and channel wave energy attenuation characteristic parameters from multi-wave seismic data.

[0069] Among them, the P-wave propagation velocity and S-wave propagation velocity are used to reflect the elastic properties of the coal seam and surrounding rock medium, while the channel wave energy attenuation characteristic parameter is used to characterize the internal structural integrity and fracture development of the coal seam.

[0070] In one possible implementation, the acquired multi-wave seismic data is preprocessed, including denoising, time window truncation, and waveform recognition. The arrival times of the first P-wave and the S-wave are extracted and their corresponding propagation velocities are calculated. At the same time, based on the variation of the trough wave amplitude with the propagation distance, the characteristic parameters of trough wave energy attenuation are calculated.

[0071] As an example, in an embodiment of this application, the P-wave propagation velocity satisfies The following formula:

[0072] in, ρ is the propagation velocity of seismic P-waves in the rock; ρ is the density of the rock; δ is the Poisson's ratio of the rock; E is the Young's modulus of the rock; G and K are the shear modulus and volumetric modulus of the rock, respectively.

[0073] It should be noted that for most rocks, δ is approximately 0.25, i.e. Based on this, the propagation speed of the P-wave satisfies Approximate the following formula:

[0074] The meanings in the formula are the same as those described above, and will not be repeated here in the embodiments of this application.

[0075] As an example, in an embodiment of this application, the S-wave propagation speed Satisfy the following formula:

[0076] in, ρ is the propagation velocity of seismic shear waves in the rock; δ is the density of the rock; E is the Poisson's ratio of the rock; G is the Young's modulus of the rock; and G is the shear modulus of the rock.

[0077] It should be noted that the characteristic parameters of channel wave energy attenuation can be expressed in the form of energy attenuation coefficient, amplitude attenuation rate or equivalent attenuation index, and the specific form can be set according to the mining area conditions.

[0078] As an example, in an embodiment of this application, a 1.5m×1m×0.5m physical model was constructed in a coal mine experiment, with a coal seam thickness of 30cm, a fault displacement amplitude of 10cm, and a collapse column diameter of 15cm. CT scans were used to obtain baseline data of the model's internal structure. The propagation characteristics of seismic waves under different geological conditions were simulated. Exciters, hammer-driven seismic sources, and electromagnetic sources were used to excite P-waves, S-waves, and channel waves of different frequencies. High-density geophones (5cm spacing) were installed on the top and sides of the model to ensure comprehensive capture of seismic wave signals. A high sampling rate (10 kHz) was set to continuously record the seismic wave propagation process. The diffraction, reflection, and attenuation phenomena of P-waves, S-waves, and channel waves in different structures were observed. Typical seismic response characteristics of anomalous structural zones were extracted.

[0079] Based on the above steps, this step extracts the propagation velocities of P-waves and S-waves and the energy attenuation characteristics of channel waves to achieve quantitative characterization of the key physical features of multi-wave seismic data.

[0080] S403. Based on the P-wave propagation velocity and S-wave propagation velocity, calculate the P-wave to S-wave velocity ratio and Poisson's ratio parameters of the coal seam and surrounding rock in the area where the water condition is abnormal.

[0081] In one possible implementation, after determining the spatial range of the abnormal water condition area, the P-wave to S-wave velocity ratio is calculated within this area based on the P-wave propagation velocity and the S-wave propagation velocity; based on the P-wave propagation velocity and the S-wave propagation velocity, the Poisson's ratio parameter of the coal seam and surrounding rock is calculated according to the elastic wave propagation relationship, wherein the Poisson's ratio parameter is determined by the P-wave to S-wave velocity ratio.

[0082] It should be noted that the P-wave velocity ratio and Poisson's ratio parameters can be introduced as constraints into the subsequent joint inversion process to limit the physical rationality of the inversion results.

[0083] As an example, in an embodiment of this application, the P-wave and S-wave velocities are... Satisfy the following formula:

[0084] Where δ is the Poisson's ratio of the rock; E is the Young's modulus of the rock; and G and K are the shear modulus and volumetric modulus of the rock.

[0085] Based on the above steps, this step calculates the ratio of longitudinal and transverse wave velocities and Poisson's ratio to achieve a quantitative characterization of the mechanical state of coal seams and surrounding rocks in areas with abnormal water conditions.

[0086] S404. Using the P-wave velocity ratio and Poisson's ratio as constraints, the seismic data of P-wave, S-wave and Cao-wave are jointly inverted to obtain the three-dimensional wave velocity distribution and energy attenuation distribution of coal seam and surrounding rock in the area where water anomalies occur.

[0087] In one possible implementation, based on the P-wave / S-wave velocity ratio and Poisson's ratio parameters, joint inversion constraints are applied to the seismic data of P-waves, S-waves, and trough waves to generate an initial wave velocity model, including the three-dimensional P-wave velocity distribution results and the three-dimensional S-wave velocity distribution results of the coal seam and surrounding rock in the area of ​​the hydrological anomaly. The initial wave velocity model is iteratively updated using a tomographic inversion method to obtain the three-dimensional wave velocity distribution results of the coal seam and surrounding rock in the area of ​​the hydrological anomaly. Based on the energy attenuation characteristics of the trough wave, combined with the three-dimensional P-wave velocity distribution results and the three-dimensional S-wave velocity distribution results, the initial wave velocity model is attenuated and inverted to obtain the energy attenuation distribution results of the coal seam and surrounding rock in the area of ​​the hydrological anomaly.

[0088] It should be noted that the three-dimensional wave velocity distribution results and energy attenuation distribution results correspond to each other in space and can jointly reflect the spatial location and degree of structural anomalies in the coal seam and surrounding rock.

[0089] Based on the above steps, this step obtains three-dimensional wave velocity distribution and energy attenuation distribution results through multi-wave joint inversion, thereby improving the ability to identify the internal structural features of areas with abnormal water conditions.

[0090] S405. Based on the three-dimensional wave velocity distribution results and energy attenuation distribution results, identify structurally abnormal areas such as faults, collapse columns, or fracture development zones, and verify the early warning results of abnormal water conditions.

[0091] In one possible implementation, low-velocity anomaly regions with a significant decrease in velocity relative to the surrounding area are identified in the three-dimensional wave velocity distribution results as candidate regions for structural anomalies. High-energy-decrease regions corresponding to the low-velocity anomaly regions in spatial location are identified in the energy attenuation distribution results. Spatial overlay analysis of the low-velocity anomaly regions and high-energy-decrease regions is performed to determine structural anomaly regions within the coal seam and surrounding rock. Based on the spatial morphological characteristics, wave velocity reduction magnitude, and energy attenuation characteristics of the structural anomaly regions, their types are identified, classifying them as faults, collapse columns, or fracture development zones. Spatial matching analysis is performed between the structural anomaly regions and the areas where hydrological anomalies occur to verify the early warning results for hydrological anomalies.

[0092] As an example, in an embodiment of this application, in a certain mining area, the P-wave velocity is 3800-4200 m / s, the S-wave velocity is 2200-2600 m / s, and the Vp / Vs value is around 1.7. However, it decreases by 1.4 in the fault zone area, indicating that there is a fracture development zone in this area. The boundary can be further refined by combining the trough wave data.

[0093] It should be noted that in the embodiments of this application, in the collapse column area, the propagation of shear waves is hindered due to loose filling material, and the Poisson's ratio is usually >0.35; in the fault fracture zone, the development of fractures is caused by high stress concentration, and the Poisson's ratio is <0.25. The elastic modulus of the coal seam and surrounding rock is calculated using the generalized Hooke's law, the inversion results are constrained, and the strength parameters of the anomalous structure are optimized by combining the measured in-situ stress data. Through inversion calculation, it is found that if Vp / Vs=1.35 in the collapse column area, the Poisson's ratio is as high as 0.38, which is consistent with the measured results, indicating that the method can effectively identify concealed structures.

[0094] Based on the above steps, this step combines the three-dimensional wave velocity distribution results and energy attenuation distribution results to achieve structural verification of the water situation anomaly early warning results.

[0095] S406. When structural anomalies and hydrological anomalies coexist, the warning level shall be raised or a joint warning shall be triggered.

[0096] Joint early warning refers to comprehensive early warning information issued simultaneously based on the results of water anomaly determination and tectonic anomaly identification.

[0097] In one possible implementation, when the verification results indicate the presence of faults, collapse columns, or fracture development zones within the area of ​​abnormal hydrological conditions, the corresponding hydrological anomaly warning level will be upgraded from a regular warning to a high-level warning, or a joint warning message containing both hydrological and tectonic risks will be triggered.

[0098] It should be noted that the joint early warning can be simultaneously sent to the underground personnel terminal and the ground monitoring system so that corresponding safety measures can be taken in a timely manner.

[0099] Based on the above steps, this step improves the reliability and relevance of the early warning results by jointly determining hydrological anomalies and tectonic anomalies.

[0100] This application's embodiments introduce a multi-wave seismic data acquisition and analysis mechanism. Following a hydrological anomaly warning, P-wave, S-wave, and channel wave seismic data are further acquired, and corresponding propagation velocity and energy attenuation characteristic parameters are extracted. This expands the hydrological anomaly judgment from a single hydrological parameter analysis to a comprehensive analysis process incorporating information on the underground medium structure. Based on the propagation velocities of P-waves and S-waves, the P-wave / S-wave velocity ratio and Poisson's ratio parameters are calculated and used as constraints in multi-wave joint inversion. This effectively improves the physical rationality and stability of the inversion results, enabling the obtained three-dimensional wave velocity distribution and energy attenuation distribution results to more realistically reflect the spatial structural characteristics of the coal seam and surrounding rock. Through comprehensive analysis of the three-dimensional wave velocity distribution and energy attenuation distribution results, structural anomaly areas highly correlated with water inrush risk, such as faults, collapse columns, or fracture development zones, can be identified. This achieves structural verification of the hydrological anomaly warning results, reducing the probability of misjudgment caused by fluctuations in a single hydrological indicator. When structural anomalies and hydrological anomalies coexist, by raising the warning level or triggering joint warnings, key alerts can be provided for high-risk areas, improving the relevance and reliability of warning results, solving the problem of false alarms about hydrological anomalies, and identifying the causes of hydrological anomalies.

[0101] In one possible implementation of the embodiments of this application, combined with Figure 4 ,like Figure 5 As shown, the above S404 can be specifically implemented through the following S501 to S503, which are explained in detail below: S501. Based on the P-wave / S-wave velocity ratio and Poisson's ratio parameters, joint inversion constraints are applied to the seismic data of P-wave, S-wave, and trough wave to generate an initial wave velocity model.

[0102] In this embodiment, the initial wave velocity model includes the three-dimensional P-wave velocity distribution results and the three-dimensional S-wave velocity distribution results of the coal seam and surrounding rock within the area of ​​hydrological anomalies. Joint inversion constraints refer to the introduction of P-wave / S-wave velocity ratio and Poisson's ratio parameters during the inversion process to impose physical property consistency constraints on the P-wave and S-wave velocity inversion results, thereby preventing inversion results from being inconsistent with the physical properties of the coal seam and surrounding rock.

[0103] In one possible implementation, based on the P-wave and S-wave propagation velocities extracted from the area where the water condition anomaly occurs, the P-wave and S-wave velocity ratios and Poisson's ratio parameters at the corresponding locations are calculated and introduced as constraints into the joint inversion process of P-wave, S-wave, and channel wave to generate an initial wave velocity model that includes the three-dimensional P-wave velocity distribution results and the three-dimensional S-wave velocity distribution results.

[0104] It should be noted that the initial wave velocity model is used to describe the spatial distribution of wave velocity in the coal seam and surrounding rock in the early stage of inversion, and its accuracy will directly affect the stability of subsequent tomographic inversion and attenuation inversion.

[0105] As an example, taking a certain mining area as an example, assuming the coal seam thickness is 3-6m, the fault displacement amplitude reaches 20m, and the surrounding rock is mainly sandstone (Vp≈4500m / s, ρ≈2.5g / cm³), a three-dimensional geological model is established for this mining area, ensuring that the fault zone has low-velocity characteristics (Vp reduced by 10%). Forward modeling of seismic wave propagation is carried out; the high-order finite difference method (FDTD) is used to simulate the propagation characteristics of P-waves, S-waves, and channel waves in the coal seam; then an anisotropic medium model is selected to accurately simulate the anisotropic wave propagation behavior of the coal seam; finally, a wave field is set. Simulation parameters, such as: source parameters: excitation frequency 10–50 Hz, simulating the influence of different frequency components on tectonic response; simulation duration: 200 ms–500 ms, covering the propagation process of the main seismic waves; calculation area: 800 m × 800 m × 300 m, with absorbing boundary conditions to avoid reflection interference; further analysis of the influence of different structures on seismic waves; the simulation found that when seismic waves propagate to the fault, P-waves exhibit significant diffraction, while S-waves show significant energy attenuation in low-velocity fault zones; these phenomena can be used to identify concealed faults.

[0106] Based on the above steps, this step generates an initial wave velocity model that conforms to the physical properties of the coal seam and surrounding rock by introducing constraints on the P-wave velocity ratio and Poisson's ratio during the joint inversion process.

[0107] S502. Using the tomographic inversion method, the initial wave velocity model is iteratively updated to obtain the three-dimensional wave velocity distribution results of the coal seam and surrounding rock in the area where the water condition is abnormal.

[0108] In one possible implementation, an initial wave velocity model is used as the starting model. The propagation paths of P-waves and S-waves are inverted and calculated using tomographic inversion. By iteratively updating the wave velocity parameters multiple times, the initial wave velocity model is gradually corrected to obtain the three-dimensional wave velocity distribution results of the coal seam and surrounding rock in the area where the water condition is abnormal.

[0109] It should be noted that during the iteration process, the iteration step size or convergence condition should be dynamically adjusted according to the magnitude of the inversion residual to avoid overfitting or divergence in the inversion results.

[0110] As an example, in this embodiment of the application, the long-distance propagation characteristics of the channel wave are utilized to quickly delineate the low-velocity anomaly zone and preliminarily identify the spatial distribution range of structures such as faults and collapse columns; the Tikhonov regularization method is used to constrain the channel wave velocity model and avoid overfitting.

[0111] Based on the above steps, this step iteratively updates the initial wave velocity model to obtain a more refined and stable three-dimensional wave velocity distribution result, so that the internal structural characteristics of the coal seam and surrounding rock can be more accurately reflected.

[0112] S503. Based on the energy attenuation characteristics of the channel wave, and combined with the three-dimensional P-wave velocity distribution results and the three-dimensional S-wave velocity distribution results, the initial wave velocity model is attenuated and inverted to obtain the energy attenuation distribution results of the coal seam and surrounding rock in the area where the water condition is abnormal.

[0113] Among them, attenuation inversion refers to the process of inverting and analyzing the internal structure and fracture development of a medium based on the energy attenuation characteristics of seismic waves during propagation.

[0114] In one possible implementation, the energy attenuation characteristics of the channel wave are extracted by taking advantage of its high sensitivity to fractures and water-bearing structures when propagating along the coal seam. Combined with the obtained three-dimensional P-wave velocity distribution results and three-dimensional S-wave velocity distribution results, the attenuation inversion calculation of the initial wave velocity model is performed to obtain the energy attenuation distribution results of the coal seam and surrounding rock in the area where the water condition is abnormal.

[0115] It should be noted that the energy attenuation distribution results and the three-dimensional wave velocity distribution results have a spatial correspondence, and the two can mutually verify the location and range of structural anomalies in the coal seam and surrounding rock.

[0116] Based on the above steps, this step combines the energy attenuation characteristics of the channel wave with the three-dimensional P-wave and S-wave velocity distribution results to perform attenuation inversion, thereby achieving a further characterization of the coal seam and surrounding rock structure anomalies.

[0117] This application's embodiments construct an initial wave velocity model under the constraints of the P-wave / S-wave velocity ratio and Poisson's ratio parameters, and iteratively update the initial wave velocity model using a tomographic inversion method. Simultaneously, it combines the energy attenuation characteristics of channel waves to perform attenuation inversion. This enables the simultaneous acquisition of three-dimensional wave velocity distribution and energy attenuation distribution results for the coal seam and surrounding rock within the underground working face of a coal mine experiencing hydrological anomalies. This achieves multi-parameter collaborative characterization of coal seam and surrounding rock structural anomalies and water-bearing characteristics. Compared to inversion methods based solely on a single wave velocity or a single seismic wave type, this application, through the combination of joint inversion and attenuation inversion, improves the spatial resolution and consistency of the inversion results for fractured areas and water-bearing structural areas, which helps reduce inversion instability and improve the accuracy of spatial identification results for hydrological anomalies.

[0118] In one possible implementation of the embodiments of this application, combined with Figure 4 ,like Figure 6 As shown, the above S405 can be specifically implemented through the following S601 to S605, which are explained in detail below: S601. In the three-dimensional wave velocity distribution results, identify low-velocity anomalous regions that show a significant decrease in wave velocity relative to the surrounding region, and use them as candidate regions for constructing anomalous regions.

[0119] Among them, the low-velocity anomaly region refers to the spatial region in which the wave velocity value shows a continuous decrease compared to the adjacent spatial region in the three-dimensional wave velocity distribution results. This region usually reflects changes in the structure of the coal seam and surrounding rock medium.

[0120] In one possible implementation, the three-dimensional wave velocity distribution results are voxelized, and the average wave velocity of adjacent voxels is used as a reference. Regions with wave velocities lower than the reference value and meeting a preset continuous volume threshold are clustered and labeled to obtain low-velocity anomaly regions.

[0121] It should be noted that the identification of low-velocity anomaly areas focuses on spatial relative variation characteristics rather than a single absolute wave velocity threshold, in order to avoid misjudgment caused by differences in wave velocity benchmarks under different strata conditions.

[0122] Based on the above steps, this step can screen out potential anomalous regions related to structural changes at a three-dimensional scale, providing a candidate range for further determination of structural anomalies.

[0123] S602. In the energy decay distribution results, identify the high-energy decay region that corresponds to the low-speed anomaly region in spatial location.

[0124] Among them, the high energy attenuation region refers to the spatial region in which the energy loss during the propagation of seismic waves is significantly higher than that of the surrounding area in the energy attenuation distribution results.

[0125] In one possible implementation, the energy attenuation distribution result is mapped to a spatial coordinate system consistent with the three-dimensional wave velocity distribution result, and the energy attenuation value is extracted at the corresponding position in the low-velocity anomaly region to determine whether it exceeds the preset attenuation identification threshold.

[0126] It should be noted that the energy attenuation characteristics mainly reflect the internal fissures, water content, and structural fragmentation of the medium, and are complementary to the wave velocity characteristics.

[0127] Based on the above steps, this step uses spatial correspondence to filter out high-energy decay regions that match low-speed anomaly regions, thereby improving the targeting of anomaly region identification.

[0128] S603. Perform spatial overlay analysis on the low-velocity anomaly region and the high-energy decay region to determine the structural anomaly region within the coal seam and surrounding rock.

[0129] Spatial overlay analysis refers to the analytical process of determining the coincidence relationship between inversion results of different parameters under the same spatial coordinate system.

[0130] In one possible implementation, a three-dimensional Boolean superposition operation is performed on the low-velocity anomaly region and the high-energy attenuation region to extract the overlapping region that simultaneously satisfies the conditions of reduced wave velocity and enhanced energy attenuation, which is then used as the constructed anomaly region.

[0131] It should be noted that the corresponding region is only identified as a structural anomaly region when the low-speed anomaly and the high-energy decay have a significant spatial overlap, in order to reduce the probability of misjudgment caused by a single parameter anomaly.

[0132] Based on the above steps, this step realizes the comprehensive utilization of multi-parameter anomaly information, making the identification results of the constructed anomaly region more accurate.

[0133] S604. Based on the spatial morphological characteristics, wave velocity reduction magnitude, and energy attenuation characteristics of the tectonic anomaly region, the tectonic anomaly region is identified as a fault, collapse column, or fracture development zone.

[0134] Among them, spatial morphological characteristics include the extension direction, size, and geometric features of the structural anomaly region.

[0135] In one possible implementation, the spatial distribution characteristics of the structural anomaly region, the distribution of wave velocity reduction amplitude, and the difference in energy attenuation intensity are combined to classify and judge the structural anomaly region using a preset identification rule.

[0136] It should be noted that different types of tectonic anomalies differ in wave velocity variation amplitude, attenuation distribution characteristics, and spatial morphology. The accuracy of classification can be improved by joint identification of multiple features.

[0137] As an example, in the embodiments of this application, an abnormal region that extends in a band and has obvious abrupt changes in wave velocity can be identified as a fault, while an abnormal region that is columnar or locally concentrated can be identified as a collapse column.

[0138] Based on the above steps, this step enables the differentiation of structural anomaly area types, providing more targeted structural information for hydrological risk analysis.

[0139] S605. Spatial matching analysis is performed between the structural anomaly area and the area where the hydrological anomaly occurs, which is used to verify the early warning results of the hydrological anomaly.

[0140] Spatial matching analysis refers to determining the spatial correspondence between areas of structural anomalies and areas of hydrological anomalies.

[0141] In one possible implementation, the anomaly region and the hydrological anomaly region are mapped to a unified coordinate system, and the spatial overlap ratio or minimum spatial distance between the two is calculated to determine their correlation.

[0142] It should be noted that when the areas of structural anomalies and the areas of hydrological anomalies are highly matched in space, it indicates that the hydrological anomalies have clear geological structural indicative significance.

[0143] As an example, in this embodiment of the application, when the spatial overlap ratio exceeds a preset threshold, the original water condition anomaly warning result can be confirmed or the warning level can be upgraded.

[0144] Based on the above steps, this step introduces structural information to verify the early warning results of abnormal water conditions, thereby reducing the misjudgment of the early warning results.

[0145] This application's embodiments identify low-velocity anomaly regions with significantly reduced wave velocity relative to the surrounding area in the three-dimensional wave velocity distribution results. This is then combined with overlay analysis of corresponding high-energy attenuation regions in the energy attenuation distribution results. This effectively filters out structural anomaly regions related to structural fracturing and water-bearing characteristics within coal seams and surrounding rock, reducing the uncertainty caused by relying solely on a single inversion result. Furthermore, based on the spatial morphological characteristics, wave velocity reduction magnitude, and energy attenuation characteristics of the structural anomaly regions, the types of structural anomaly regions are identified, enabling the differentiation of faults, collapse columns, or fracture development zones, thus improving the specificity and interpretability of the structural anomaly identification results. By performing spatial matching analysis between the identified structural anomaly regions and the areas where hydrological anomalies occur, the hydrological anomaly early warning results are verified. This helps determine whether the hydrological anomalies are related to potential water-conducting structures, thereby improving the reliability of the hydrological anomaly early warning results and reducing the probability of false alarms or missed alarms.

[0146] The above primarily describes the solutions of the embodiments of this application from the perspective of device implementation. It is understood that each device, such as a distributed hydrological monitoring system for underground coal mine working faces, includes at least one of the hardware structures and software modules corresponding to the execution of each function in order to achieve the aforementioned functions. Those skilled in the art should readily recognize that, in conjunction with the units and algorithm steps of the various examples described in the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed by hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0147] This application embodiment can divide the distributed hydrological monitoring system for underground coal mine working faces into functional units based on the above method example. For example, each function can be divided into its own functional units, or two or more functions can be integrated into one processing unit. The integrated unit can be implemented in hardware or software. It should be noted that the unit division in this application embodiment is illustrative and only represents one logical functional division; other division methods may be used in actual implementation.

[0148] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented using software programs, implementation can be, in whole or in part, in the form of a computer program product. This computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this application is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device containing one or more servers, data centers, etc., that can be integrated with the medium. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state disks (SSDs)).

[0149] Although this application has been described herein in conjunction with various embodiments, those skilled in the art, by reviewing the accompanying drawings, disclosure, and appended claims, will understand and implement other variations of the disclosed embodiments in carrying out the claimed application. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "an" does not exclude multiple instances. A single processor or other unit can implement several functions listed in the claims. While different dependent claims may recite certain measures, this does not mean that these measures cannot be combined to produce good results.

[0150] Although this application has been described in conjunction with specific features and embodiments, it is obvious that various modifications and combinations can be made thereto without departing from the spirit and scope of this application. Accordingly, this specification and drawings are merely exemplary illustrations of this application as defined by the appended claims, and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from the spirit and scope of this application. Thus, if such modifications and modifications of this application fall within the scope of the claims of this application and their equivalents, this application is also intended to include such modifications and modifications.

Claims

1. A distributed hydrological monitoring method for underground coal mine working faces, characterized in that, include: Acquire hydrological time-series data, including vibration time-series data, water pressure time-series data, water turbidity time-series data, and rock strata micro-seepage velocity time-series data; Based on the hydrological time-series data, a hydrological time-series data vector is constructed according to preset rules; the hydrological time-series data vector includes the values ​​and categories of the hydrological time-series data. The value of the hydrological time series data vector is compared with a preset threshold for the corresponding category. If the value of the hydrological time series data vector is greater than or equal to the preset threshold for the corresponding category, it is marked as a target item, and the number of target items is counted. The number of the target items is compared with a preset number threshold to obtain the comparison result, and the corresponding data analysis operation is performed based on the comparison result to identify abnormal water conditions. Based on the abnormal water conditions, corresponding early warnings will be issued.

2. The distributed hydrological monitoring method for underground coal mine working faces according to claim 1, characterized in that, After identifying and issuing warnings about abnormal water conditions, the distributed water condition monitoring method for underground coal mine working faces also includes: Acquire multi-wave seismic data, including P-wave, S-wave, and tsunami seismic data; Extract the P-wave propagation velocity, S-wave propagation velocity, and groove wave energy attenuation characteristic parameters from the multi-wave seismic data; Based on the P-wave propagation velocity and S-wave propagation velocity, the P-wave velocity ratio and Poisson's ratio parameters of the coal seam and surrounding rock in the area where the water condition is abnormal are calculated. Using the P-wave velocity ratio and Poisson's ratio parameters as constraints, the seismic data of P-wave, S-wave and Cao-wave are jointly inverted to obtain the three-dimensional wave velocity distribution and energy attenuation distribution of coal seam and surrounding rock in the area where water anomalies occur. Based on the three-dimensional wave velocity distribution results and energy attenuation distribution results, the structurally abnormal areas of faults, collapse columns or fracture development zones are identified, and the early warning results of abnormal water conditions are reviewed. When structural anomalies and hydrological anomalies coexist, the warning level should be raised or a joint warning should be triggered.

3. The distributed hydrological monitoring method for underground coal mine working faces according to claim 1, characterized in that, The step of comparing the number of the target items with a preset quantity threshold to obtain a comparison result, and performing corresponding data analysis operations based on the comparison result to identify abnormal water conditions, includes: When the number of target items is zero, perform the first data analysis operation; When the number of target items is greater than zero and less than the set number threshold, perform the second data analysis operation; When the number of target items is greater than or equal to the set number threshold, execute the third data analysis operation; Based on the first data analysis operation and / or the second data analysis operation and / or the third data analysis operation, identify abnormal water conditions.

4. The distributed hydrological monitoring method for underground coal mine working faces according to claim 3, characterized in that, When the number of target items is equal to zero, the first data analysis operation is performed, including: The mean of each data item in the hydrological time series data vector is calculated to obtain the mean of the corresponding data item. Obtain the average value of the data item obtained in the first five calculations, and sort the average values ​​of the first five data items according to the chronological order. The difference between the mean of the currently calculated data items and the mean of the first sorted data items is calculated to obtain the mean difference. When the mean difference is positive and is greater than the set first mean difference threshold and less than or equal to the set second mean difference threshold, the sampling frequency corresponding to the data item is adjusted to shorten the sampling frequency to two-thirds of the original sampling frequency. When the mean difference is positive and greater than the second mean difference threshold, the second data analysis operation is performed.

5. The distributed hydrological monitoring method for underground coal mine working faces according to claim 4, characterized in that, When the number of target items is greater than zero and less than a set threshold, a second data analysis operation is performed, including: Substitute the hydrological time series data vector into the linear regression model to output the predicted value corresponding to each data item in the hydrological time series data vector. The linear regression model includes regression coefficients and intercept parameters. Multiple judgment conditions related to water condition anomalies are set, and a corresponding weight is assigned to each judgment condition. The judgment conditions include whether the water pressure exceeds different pressure thresholds and whether it belongs to a key monitoring node. The data items in the hydrological time series data vector are matched and judged sequentially with the multiple judgment conditions, and the number of data items that meet the conditions under each judgment condition is counted to obtain the condition compliance number; The condition compliance numbers are weighted, converted, and summed to obtain the condition compliance value; The hydrological time-series data vector and the condition compliance values ​​are substituted into the XGBoost model to output the result value corresponding to the hydrological time-series data vector. The loss function of the XGBoost model includes a regularization term to constrain the number of judgment conditions. The XGBoost model satisfies the following formula: Among them, For loss function, This represents the last data item collected in the hydrological time-series data vector. For predicted values ​​of hydrological time series data items; For regularization terms, To determine the penalty strength for the number of conditions T, λ represents the smoothness of the weights corresponding to the conditions. Values ​​that meet the conditions; When the result value is greater than the preset result threshold, a water situation anomaly command is generated; When the result value is less than or equal to the result threshold, the collection frequency of the corresponding data item is adjusted, and the collection frequency is shortened to one-third of the original collection frequency until the mean of the data item is within a preset range within a preset time, and the original collection frequency of the data item is restored.

6. The distributed hydrological monitoring method for underground coal mine working faces according to claim 5, characterized in that, When the number of target items is greater than or equal to a set threshold, a third data analysis operation is performed, including: Perform the second data analysis operation on all hydrological time series data vectors respectively to obtain multiple corresponding hydrological time series data vector result values; The results of the multiple corresponding hydrological time series data vectors are weighted according to preset weight parameters to obtain a comprehensive result; An early warning is issued when the overall result falls within a first preset range.

7. The distributed hydrological monitoring method for underground coal mine working faces according to claim 2, characterized in that, The calculation of the P-wave and S-wave propagation velocities, and the Poisson's ratio parameters of the coal seam and surrounding rock within the area of ​​abnormal water conditions, based on the P-wave and S-wave propagation velocities, includes: Based on the P-wave propagation velocity and the S-wave propagation velocity, the P-wave to S-wave velocity ratio is calculated. Based on the propagation velocity of the P-wave and the propagation velocity of the S-wave, the Poisson's ratio parameter of the coal seam and surrounding rock is calculated according to the elastic wave propagation relationship, wherein the Poisson's ratio parameter is determined by the ratio of the longitudinal and transverse wave velocities.

8. The distributed hydrological monitoring method for underground coal mine working faces according to claim 2, characterized in that, The method involves jointly inverting P-wave, S-wave, and Cao-wave seismic data using the P-wave / S-wave velocity ratio and Poisson's ratio parameters as constraints to obtain the three-dimensional wave velocity distribution and energy attenuation distribution of coal seams and surrounding rocks within the area of ​​hydrological anomalies. This includes: Based on the P-wave velocity ratio and Poisson's ratio parameters, joint inversion constraints are applied to the seismic data of P-wave, S-wave and channel wave to generate an initial wave velocity model, including the three-dimensional P-wave velocity distribution results and the three-dimensional S-wave velocity distribution results of coal seam and surrounding rock in the area where water anomalies occur. The initial wave velocity model was iteratively updated using the tomographic inversion method to obtain the three-dimensional wave velocity distribution results of the coal seam and surrounding rock in the area where the water condition anomaly occurred. Based on the energy attenuation characteristics of the channel wave, and combined with the three-dimensional P-wave velocity distribution results and the three-dimensional S-wave velocity distribution results, the initial wave velocity model is subjected to attenuation inversion to obtain the energy attenuation distribution results of the coal seam and surrounding rock in the area where the water condition is abnormal.

9. The distributed hydrological monitoring method for underground coal mine working faces according to claim 2, characterized in that, Based on the three-dimensional wave velocity distribution results and energy attenuation distribution results, the identification of structurally anomalous areas such as faults, collapse columns, or fracture development zones, and the verification of hydrological anomaly early warning results, including: In the three-dimensional wave velocity distribution results, low-velocity anomalous regions that show a significant decrease in wave velocity relative to the surrounding region are identified as candidate regions for constructing anomalous regions. In the energy decay distribution results, identify the high energy decay region that corresponds to the low-speed anomaly region in spatial location; Spatial overlay analysis of the low-velocity anomaly region and the high-energy decay region is performed to determine the structural anomaly region within the coal seam and surrounding rock. Based on the spatial morphological characteristics, wave velocity reduction magnitude, and energy attenuation characteristics of the structural anomaly region, the structural anomaly region is identified as a fault, collapse column, or fracture development zone. Spatial matching analysis is performed between the structurally abnormal region and the region where the water situation anomaly occurs to verify the water situation anomaly early warning results.

10. A distributed hydrological monitoring system for underground coal mine working faces, used to implement the distributed hydrological monitoring method for underground coal mine working faces as described in any one of claims 1-9, characterized in that, The distributed hydrological monitoring system for underground coal mine working faces includes: a sensor module, a monitoring module, and a verification monitoring module; The sensor module includes multiple sensor nodes distributed in the underground working face of the coal mine, used to collect water condition time-series data in the coal mine and transmit the water condition time-series data to the monitoring module; the water condition time-series data includes vibration time-series data, water pressure time-series data, water turbidity time-series data, and rock strata micro-seepage velocity time-series data. The monitoring module includes at least one monitoring substation, which is used to receive water condition time-series data sent by the sensor module, preprocess the water condition time-series data to construct a water condition time-series data vector, compare the water condition time-series data vector with a preset threshold of the corresponding category, count the number of target items, and perform corresponding data analysis operations based on the number of target items to identify abnormal water condition results. The verification and monitoring module is used to perform early warning processing based on the abnormal water conditions; and after receiving the abnormal water conditions early warning, it acquires multi-wave seismic data, performs joint inversion on the seismic data of P-wave, S-wave and channel waves to obtain the three-dimensional wave velocity distribution and energy attenuation distribution of coal seams and surrounding rocks in the area where the abnormal water conditions occur, and identifies structurally abnormal areas based on the three-dimensional wave velocity distribution and energy attenuation distribution results, and verifies or upgrades the early warning level of the abnormal water conditions early warning results.

Images