Mine field early warning area division method and related equipment

Abstract

The embodiment of the invention provides a mine field early warning area division method and related equipment, and the method comprises the steps: obtaining monitoring data at a plurality of preset monitoring points, the monitoring data comprising position data and corresponding physical monitoring data; constructing a spatial distribution diagram based on the position data on the plurality of preset monitoring point positions and the corresponding physical monitoring data; identifying a plurality of abnormal monitoring points in the spatial distribution diagram through an early warning safety model; determining an early warning area boundary based on the plurality of abnormal monitoring points; and generating a corresponding visual partition result in the spatial distribution diagram based on the early warning region boundary. Through the steps of the method, the areas with risks in the mine field can be identified based on the three-dimensional space information and the physical monitoring data of the monitoring points, dynamic early warning division of area levels is realized, the space distribution condition of the mine field risks is reflected, and the safety management efficiency of the mine is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of mining development, and in particular to a mine early warning area division method and device, an electronic device and a storage medium thereof. BACKGROUND

[0002] With the increasing intensity of mineral resources exploitation, the roof stability and surrounding rock safety problems of the mine are increasingly prominent. The existing early warning technology mainly relies on single-point monitoring data, such as roof separation displacement, anchor rod stress or borehole stress, etc. parameters, and usually only through threshold comparison to judge the local risk. However, in the actual complex geological environment and mining conditions, single-point data cannot fully reflect the overall risk pattern of the mine, resulting in one-sidedness and lag of the early warning information, and it is difficult to provide comprehensive and effective guidance for mine safety production in time.

[0003] In addition, the existing method lacks spatial processing of monitoring data, often ignoring the spatial correlation between different monitoring points, making it difficult to accurately delineate abnormal areas. Once a large-scale risk spreads, it is difficult to lock the potential dangerous area in time by relying on single-point alarm, increasing the safety hazards of mine work.

[0004] Therefore, the existing mine early warning area division method has the problem of being unable to identify abnormal points and delineate the boundary of the early warning area based on the spatial distribution characteristics of the monitoring data. SUMMARY

[0005] The embodiments of the present application provide a mine early warning area division method to solve the problem that the existing mine early warning area division method cannot identify abnormal points and delineate the boundary of the early warning area based on the spatial distribution characteristics of the monitoring data.

[0006] In a first aspect, the embodiments of the present application provide a mine early warning area division method, which comprises the following steps: obtaining monitoring data at a plurality of preset monitoring points, the monitoring data comprising position data and corresponding physical monitoring data; constructing a spatial distribution map based on the position data and corresponding physical monitoring data at the plurality of preset monitoring points; identifying a plurality of abnormal monitoring points in the spatial distribution map through an early warning safety model; determining the boundary of the early warning area based on the plurality of abnormal monitoring points; generating a corresponding visual partition result in the spatial distribution map based on the boundary of the early warning area.

[0007] Optionally, the obtaining of the monitoring data at the plurality of preset monitoring points comprises: determining a preset layout interval of the optical fiber sensor based on the geological properties, mining layout and roof type data of the target mine. determine position data of the plurality of optical fiber sensors based on the preset arrangement interval; Collecting and demodulating the inner layer displacement data and stress data of the roof by the optical fiber sensors arranged at the preset monitoring points, and obtaining the corresponding physical monitoring data through the optical fiber demodulation host.

[0008] Optionally, the space distribution map is constructed based on the position data and the corresponding physical monitoring data of the plurality of preset monitoring points, comprising: determining three-dimensional coordinates corresponding to the preset monitoring points based on the position data; associating the three-dimensional coordinates with the corresponding physical monitoring data to construct a three-dimensional mapping relationship; generating a space distribution map corresponding to the target mine field based on the three-dimensional mapping relationship, wherein the space distribution map is used to describe the distribution of the physical monitoring data of the plurality of preset monitoring points in three-dimensional space.

[0009] Optionally, the plurality of abnormal monitoring points are identified in the space distribution map through a pre-warning safety model, comprising: comparing the physical monitoring data at each preset monitoring point with the corresponding preset safety threshold to obtain a first abnormal monitoring value; determining monitoring trend data at each preset monitoring point within a preset detection period; comparing the monitoring trend data with the corresponding preset trend threshold data to obtain a second abnormal monitoring value; determining a plurality of target abnormal monitoring points by weighting the first abnormal monitoring value and the second abnormal monitoring value through a preset weighting algorithm.

[0010] Optionally, the plurality of target abnormal monitoring points are determined by weighting the first abnormal monitoring value and the second abnormal monitoring value through a preset weighting algorithm, comprising: determining a first abnormal intensity value of the first abnormal monitoring value and a second abnormal intensity value of the second abnormal monitoring value; calculating the first abnormal intensity value and the second abnormal intensity value according to a preset weight proportion to obtain a target abnormal comprehensive value, wherein the target abnormal comprehensive value is used to determine the current state of the optical fiber sensor at the current preset monitoring point; comparing the target abnormal comprehensive value with a preset abnormal comprehensive threshold, and determining that the corresponding preset monitoring point is a target abnormal monitoring point when the target abnormal comprehensive value is greater than or equal to the preset abnormal comprehensive threshold.

[0011] Optionally, the warning area boundary is determined based on the plurality of abnormal monitoring points, comprising: Obtain three-dimensional coordinate information corresponding to a plurality of the abnormal monitoring points; Determine a corresponding abnormal monitoring point distribution set based on a plurality of the three-dimensional coordinate information; Perform spatial boundary extraction processing on the abnormal monitoring point distribution set to determine a spatial envelope covering a plurality of the abnormal monitoring points; Take the spatial envelope as the early warning area boundary.

[0012] Optionally, based on the early warning area boundary, generate a corresponding visual partition result in the spatial distribution map, including: Map the early warning area boundary to a corresponding three-dimensional coordinate system in the spatial distribution map to obtain a spatial profile of the early warning area; According to a preset risk level rule, perform hierarchical coloring annotation on the area within the spatial profile to obtain an early warning partition with risk level identification; Render the early warning partition with risk level identification to generate a three-dimensional visual partition map for display.

[0013] In a second aspect, the embodiments of the present application further provide a mine early warning area division device, the mine early warning area division device comprising: A first obtaining module is configured to obtain monitoring data at a plurality of preset monitoring points, the monitoring data including position data and corresponding physical monitoring data; A first constructing module is configured to construct a spatial distribution map based on the position data and corresponding physical monitoring data at the plurality of preset monitoring points; A first identifying module is configured to identify a plurality of abnormal monitoring points in the spatial distribution map through an early warning safety model; A first determining module is configured to determine an early warning area boundary based on a plurality of the abnormal monitoring points; A first generating module is configured to generate a corresponding visual partition result in the spatial distribution map based on the early warning area boundary.

[0014] In a third aspect, the embodiments of the present application provide an electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the mine early warning area division method provided by the embodiments of the present application.

[0015] In a fourth aspect, the embodiments of the present application provide a computer readable storage medium, the computer readable storage medium storing a computer program, wherein the computer program is executed by a processor to implement the steps of the mine early warning area division method provided by the embodiments of the present application.

[0016] In the embodiment of the present application, monitoring data on a plurality of preset monitoring points is acquired, the monitoring data comprising position data and corresponding physical monitoring data; a spatial distribution map is constructed based on the position data and corresponding physical monitoring data on the plurality of preset monitoring points; a plurality of abnormal monitoring points are identified in the spatial distribution map through a pre-warning safety model; a pre-warning region boundary is determined based on the plurality of abnormal monitoring points; and corresponding visual partition results are generated in the spatial distribution map based on the pre-warning region boundary. Through the above method steps, the region at risk in a mine field can be identified based on the three-dimensional spatial information and physical monitoring data of the monitoring points, dynamic pre-warning division at the region level is realized, the spatial distribution of the risks in the mine field is reflected, and the safety management efficiency of the mine is improved. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0018] Figure 1 is a flowchart of a mine pre-warning region division method provided by the embodiment of the present application; Figure 2 is a structural schematic diagram of another mine pre-warning region division device provided by the embodiment of the present application; Figure 3 is a structural schematic diagram of an electronic device provided by the embodiment of the present application. DETAILED DESCRIPTION

[0019] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0020] As Figure 1 shown, Figure 1 is a flowchart of a mine pre-warning region division method provided by the embodiment of the present application, and the mine pre-warning region division method comprises the following steps: 101. Acquire monitoring data on a plurality of preset monitoring points.

[0021] In this embodiment of the invention, the above-mentioned mine early warning area division method can be applied to a mine early warning area division platform. The mine early warning area division platform has functions such as early warning area division data processing, early warning area division data transmission and reception, and early warning area division data memory storage. It can be built based on a server or server cluster. The server or server cluster can be an electronic device with early warning area division data capability.

[0022] The aforementioned preset monitoring points can be planned in advance and fixed in the geographical locations of corresponding sensors based on factors such as the geological conditions, mining layout, and roof type of the target mine. The aforementioned corresponding sensors can include, but are not limited to, any sensors capable of wireless transmission such as fiber optic sensors and signal sensors.

[0023] Specifically, each of the aforementioned preset monitoring points can contain a unique three-dimensional coordinate information and a sensor number, which is used to establish a mapping relationship of physical monitoring data in the spatial distribution map.

[0024] The aforementioned monitoring data may refer to comprehensive recorded data obtained by specific collection at a certain preset monitoring point, including but not limited to location data and corresponding physical monitoring data.

[0025] The aforementioned location data can be the spatial location used to uniquely determine the corresponding preset monitoring point, typically represented in three-dimensional coordinates (X, Y, Z), where X / Y correspond to the planar coordinates of the mining area or working face, and Z corresponds to the burial depth or elevation. Specifically, the location data may also include the installation attributes of the point, such as its placement on the tunnel arch, roof borehole, or anchor bolt tray, as well as information such as the spacing and inclination angle.

[0026] The aforementioned physical monitoring data can be various physical quantities obtained by directly collecting data from the aforementioned sensors and processing them through the fiber optic conditioning host, including but not limited to displacement data of roof delamination, force data of anchor bolts or anchor cables, and borehole stress or surrounding rock stress data.

[0027] In one possible embodiment, the aforementioned mine early warning area division platform interacts with the sensor network and demodulation equipment deployed underground to periodically acquire monitoring data from multiple preset monitoring points.

[0028] 102. Based on the location data of multiple preset monitoring points and the corresponding physical monitoring data, construct a spatial distribution map.

[0029] In this embodiment of the invention, the aforementioned spatial distribution map can refer to a three-dimensional graphical interface that maps and intuitively presents the spatial locations of the multiple preset monitoring points and their corresponding physical monitoring data in a three-dimensional coordinate system. Specifically, in the process of constructing the aforementioned spatial distribution map, the aforementioned mine early warning area division platform can first normalize the location data of the multiple preset monitoring points and bind them with the corresponding physical monitoring data. Through interpolation calculation, the discrete monitoring point data is converted into a continuous spatial field distribution result, which is then rendered to obtain a three-dimensional layer that reflects the changes in physical quantities at different preset monitoring points.

[0030] 103. Through the early warning safety model, multiple abnormal monitoring points were identified in the spatial distribution map.

[0031] In this embodiment of the invention, the above-mentioned early warning security model can be used as a set of algorithms for determining the security status of the above-mentioned detection data. Specifically, the above-mentioned early warning security model can be used for threshold anomaly determination, trend anomaly determination, and weighted fusion processing of the two. In the above-mentioned spatial distribution map, based on the processing results, abnormal monitoring points are identified among multiple preset monitoring points.

[0032] In one possible embodiment, the above-mentioned mine early warning area division platform can perform a judgment on each monitoring point according to the above-mentioned early warning safety model. For example, it can calculate the threshold abnormality index and trend abnormality index for each monitoring point, and obtain the comprehensive abnormality intensity according to the weighting rules. Then, it can compare the intensity with the abnormality judgment threshold to obtain the corresponding identification result. The corresponding identification result can be the display result of classifying the monitoring points as "abnormal / non-abnormal" and marking or displaying the abnormal points in the spatial distribution map.

[0033] The aforementioned abnormal monitoring points refer to locations that exhibit significant exceedances or abnormal trends during monitoring. These points often reflect a potentially unstable state of the roof, anchor bolts, or surrounding rock. For example, when the roof delamination displacement exceeds a preset threshold, the anchor bolt stress increases sharply, or the borehole stress changes rapidly within a short period of time, the corresponding monitoring point will be identified as an abnormal monitoring point.

[0034] In another possible embodiment, the above-mentioned mine early warning area division platform first performs quality verification and time alignment on the physical monitoring data of each monitoring point, then calculates the threshold anomaly index and trend anomaly index respectively, and performs weighted fusion according to preset weights to obtain the comprehensive anomaly intensity. The comprehensive anomaly intensity is compared with the anomaly judgment threshold, and anomaly markers are generated for monitoring points that meet the conditions, and are highlighted with symbols or colors on the spatial distribution map.

[0035] 104. Determine the boundary of the early warning area based on multiple anomaly monitoring points.

[0036] In this embodiment of the invention, the aforementioned warning area boundary can refer to a closed boundary obtained by spatial geometric calculation based on the distribution of abnormal monitoring points. It is used to reflect the spatial outline description of potential dangerous areas in the target mine. It is understood that the aforementioned warning area boundary can not only cover all identified abnormal monitoring points, but also reflect the range and shape of the aforementioned dangerous areas in the aforementioned spatial distribution map.

[0037] In one possible embodiment, the above-mentioned mine early warning area division platform can construct corresponding boundaries based on the connection relationship between multiple identified abnormal monitoring points, connect these boundaries, and thus calculate the minimum spatial envelope that can cover all abnormal monitoring points. It is understood that the minimum spatial envelope, after fitting and contouring, serves as the final early warning area boundary for subsequent risk classification and visualization.

[0038] 105. Based on the boundaries of the warning area, generate corresponding visual partitioning results in the spatial distribution map.

[0039] In this embodiment of the invention, the above-mentioned visualized zoning result can refer to the three-dimensional display result generated after the risk level of the area defined by the warning area boundary is marked and graphically presented on the spatial distribution map. Specifically, it includes transforming the abstract calculation results into intuitive display results such as color blocks, outlines and markers, which can be used to distinguish different risk levels in terms of spatial location, range and intensity, and provide a visualized execution operation reference for on-site early warning linkage, emergency dispatch and decision execution.

[0040] In one possible embodiment, the aforementioned mine early warning area division platform maps the boundary of the early warning area to the three-dimensional coordinate system corresponding to the spatial distribution map to obtain the spatial outline of the early warning area. Based on the preset risk level rules (e.g., divided into low, medium, and high levels according to the abnormal intensity range), the area within the outline is graded and colored, and the markers and numerical labels of the target abnormal monitoring points are superimposed when necessary. The rendering output forms a three-dimensional display layer that can be directly used for monitoring and command, and supports view interaction such as scaling, rotation, and sectioning.

[0041] In this embodiment of the invention, monitoring data from multiple preset monitoring points are acquired. The monitoring data includes location data and corresponding physical monitoring data. Based on the location data and corresponding physical monitoring data from the multiple preset monitoring points, a spatial distribution map is constructed. Through an early warning safety model, multiple abnormal monitoring points are identified in the spatial distribution map. Based on the multiple abnormal monitoring points, the boundaries of the early warning area are determined. Based on the boundaries of the early warning area, corresponding visual partitioning results are generated in the spatial distribution map. Through the above method steps, areas with risks in the mine can be identified based on the three-dimensional spatial information and physical monitoring data of the monitoring points, achieving dynamic early warning division at the regional level, reflecting the spatial distribution of mine risks, and improving the efficiency of mine safety management.

[0042] Optionally, in the step of acquiring monitoring data at multiple preset monitoring points, the preset spacing of fiber optic sensors can be determined based on the geological attributes, mining layout, and roof type data of the target mine; the position data of multiple fiber optic sensors can be determined based on the preset spacing; and the inner layer displacement data and stress data of the roof can be collected by the fiber optic sensors deployed at the preset monitoring points and demodulated by the fiber optic demodulation host to obtain the corresponding physical monitoring data.

[0043] In this embodiment of the invention, the target mine can refer to the specific mining area of ​​the mine early warning area division platform application, which is used as the object of monitoring and early warning. Specifically, the target mine may include multiple mining areas, mining faces or roadway systems.

[0044] The aforementioned geological attributes can refer to a set of geological information that affects the stability of the roof and the mechanical behavior of the surrounding rock, including but not limited to the lithological combination of the surrounding rock, the thickness and interlayer structure of the rock strata, the development of joints and fissures, and structural characteristic attribute data such as faults and folds. In the process of dividing the aforementioned mine early warning areas, the aforementioned mine early warning area division platform can parameterize the aforementioned geological attributes, for example, by inputting values ​​such as "lithological hardness coefficient", "joint spacing" and "thickness of weak interlayers", to determine the density of sensor deployment and the key monitoring areas.

[0045] The aforementioned mining layout can refer to the spatial distribution pattern of production organization within the mine, including but not limited to the orientation of the mining face, the direction of advancement, the layout of roadways, the cross-sectional dimensions, the support method, and the location of the mining cut and transport roadways. Generally speaking, the aforementioned mine early warning area division platform can determine the monitoring coverage rules in the orientation and dip directions based on the mining layout, and densely deploy sensors in key stress areas or complex intersections.

[0046] The aforementioned roof type data can be information selected based on lithology, thickness, integrity, and stratification, such as hard and thick roofs, composite roofs, and weak roofs. Different types of roofs exhibit different load-bearing and failure modes; for example, hard and thick roofs may collapse entirely, while weak roofs are more prone to delamination. The aforementioned mine early warning zone delineation platform can set different monitoring thresholds and deployment spacing based on roof type, such as denser deployment in weak roof areas and deep-hole sensors in hard and thick roof areas.

[0047] The aforementioned preset deployment spacing can be the recommended interval for sensor deployment after the mining early warning area division platform calculates and analyzes the geological attributes, mining layout, and roof type data. It can generally include data such as strike spacing, dip spacing, and burial depth spacing. For example, in areas with good surrounding rock integrity, a strike spacing of 20m can be used; in fault fracture zones, it can be shortened to 10m or even less.

[0048] The aforementioned delamination displacement data can refer to the relative displacement when interlayer separation occurs in the roof strata. In one possible embodiment, it can also be measured by a delamination meter installed in the roof borehole or between key strata to reflect roof stratification activity and potential collapse trends.

[0049] The stress data mentioned above can be the mechanical and physical data of the surrounding rock or support components around the aforementioned preset monitoring points, including but not limited to the axial force of anchor bolts or anchor cables, the stress of the surrounding rock in the borehole or the stress of the roof, etc., used to determine the local stress concentration.

[0050] The aforementioned fiber optic demodulation host can be a device that converts the optical signal returned by the sensor into a quantifiable physical quantity. It typically has multi-channel access, sampling clock, real-time demodulation, and data buffering functions, and can perform temperature compensation and channel calibration during demodulation. In this embodiment, the aforementioned fiber optic demodulation host can demodulate the optical signal sent by the sensor according to four steps: signal demodulation, temperature compensation, linear correction, and anomaly identification, to obtain the corresponding physical monitoring data, which is then uploaded to the aforementioned mine early warning area division platform.

[0051] In this embodiment of the invention, the above-mentioned mine early warning area division platform can analyze the actual situation of the target mine and determine the deployment parameters and data acquisition scheme of the monitoring points based on the analysis results. That is, the above-mentioned mine early warning area division platform combines the geological attributes, mining layout and roof type data of the target mine to calculate the preset deployment spacing of the fiber optic sensors, and sets the corresponding sensors according to the preset deployment spacing, and collects and acquires the physical monitoring data of the current location in real time based on the sensors.

[0052] By using the above methods and steps, the distribution of monitoring points can be made to better match the actual structural characteristics of the mine, ensuring the integrity and representativeness of the monitoring data coverage. The location data calculated using this layout spacing can form a balanced and reasonable monitoring grid in the spatial distribution map, avoiding monitoring blind spots.

[0053] Optionally, the step of constructing a spatial distribution map based on location data and corresponding physical monitoring data at multiple preset monitoring points may further include determining the three-dimensional coordinates corresponding to the preset monitoring points based on the location data; associating the three-dimensional coordinates with the corresponding physical monitoring data to construct a three-dimensional mapping relationship; and generating a spatial distribution map corresponding to the target mine based on the three-dimensional mapping relationship.

[0054] In this embodiment of the invention, a record that can be retrieved and rendered can be formed by binding the three-dimensional coordinates of the same monitoring point at the same time with its physical monitoring data.

[0055] Alternatively, multiple "coordinate-value" records can be used as input, collected, sorted, time-aligned, and formatted to form a data set that can be used for spatial representation, thus obtaining the corresponding three-dimensional mapping relationship.

[0056] The aforementioned three-dimensional mapping relationship can refer to the one-to-one correspondence between three-dimensional coordinates and physical monitoring data, that is, mapping the physical monitoring value of each monitoring point at (X,Y,Z) to the attribute of that spatial location.

[0057] The aforementioned spatial distribution map is used to describe the distribution of physical monitoring data of multiple preset monitoring points in three-dimensional space. It can present the coordinates and measured values ​​of multiple monitoring points in the form of points, color levels, isosurfaces, or voxels, so that the differences and transitions of physical quantities in different areas are spatially represented.

[0058] The aforementioned distribution can refer to the relative size, spatial gradient, and range and shape of high (or low) value areas of the aforementioned physical monitoring data in three-dimensional space, including numerical differences between different monitoring points, transition zones from low to high, and spatial locations of local anomaly clusters.

[0059] In one possible embodiment, the above-mentioned mine early warning area division platform determines the three-dimensional coordinates corresponding to each preset monitoring point based on the above-mentioned location data, associates the three-dimensional coordinates with the physical monitoring data at the same time to form a three-dimensional mapping relationship of "location-value", organizes and renders the mapped discrete point set, and generates a spatial distribution map corresponding to the target mine, which is used to describe the distribution of physical monitoring data of multiple preset monitoring points in three-dimensional space.

[0060] Optionally, in the step of identifying multiple abnormal monitoring points in the spatial distribution map through the early warning safety model, the method further includes comparing the physical monitoring data at each preset monitoring point with the corresponding preset safety threshold to obtain a first abnormal monitoring value; determining the monitoring trend data at each preset monitoring point within a preset detection period; comparing the monitoring trend data with the corresponding preset trend threshold data to obtain a second abnormal monitoring value; and weighting the first abnormal monitoring value and the second abnormal monitoring value using a preset weighting algorithm to determine multiple target abnormal monitoring points.

[0061] In this embodiment of the invention, the aforementioned preset safety threshold can be a safety limit value set for the aforementioned physical monitoring data, used to determine whether a single measurement value is within a safe range. It is understood that this judgment and detection process is continuous and cyclical.

[0062] The aforementioned first abnormal monitoring value can refer to the abnormality measure obtained by comparing the physical monitoring data at a certain moment with the corresponding preset safety threshold, which is used to reflect the result of "whether the instantaneous value exceeds the limit".

[0063] The aforementioned preset detection period can refer to a fixed window selected on the time axis for trend determination, such as the last 5 minutes, the last 30 minutes, or the last 2 hours. The aforementioned preset detection period can be used to calculate the change characteristics of monitoring data in the short term.

[0064] The aforementioned monitoring trend data can refer to the change characteristics calculated from continuous measurements at the same monitoring point within the aforementioned preset detection period, such as growth rate, slope, moving average difference, fitting residual, or fluctuation amplitude.

[0065] The aforementioned preset trend threshold data can refer to the judgment threshold corresponding to the monitored trend data, used to define whether the trend change has reached an abnormal level. For example, setting an upper limit for the growth rate and setting an allowable range for the fluctuation amplitude can serve as a benchmark for judging dynamic anomalies.

[0066] The aforementioned second anomaly monitoring value can refer to the anomaly measure obtained by comparing the monitoring trend data with the preset trend threshold data, which is used to reflect the result of "whether there are significant abnormal changes in the time dimension".

[0067] The aforementioned preset weighted algorithm can refer to the method by which the mining early warning area division platform uses set weights and combination rules to fuse the first abnormal monitoring value and the second abnormal monitoring value. The corresponding weights can be set based on historical mining data and on-site experience.

[0068] In this embodiment, the above-mentioned mine early warning area division platform can comprehensively calculate the first abnormal monitoring value and the second abnormal monitoring value according to a preset weighted algorithm to form a single abnormal measurement result, namely, the comprehensive abnormal value. When the comprehensive abnormal value reaches or exceeds the abnormal judgment threshold, it is considered that the overall risk of the point has reached the alarm standard.

[0069] The aforementioned target anomaly monitoring points can refer to monitoring points that meet the anomaly standard after the comprehensive anomaly result is obtained through the above weighted processing. They can be regarded as high-risk "seed points" in the spatial distribution map and serve as direct inputs for subsequent determination of the warning area boundary and risk classification display.

[0070] Optionally, the step of determining multiple target anomaly monitoring points by weighting the first anomaly monitoring value and the second anomaly monitoring value using a preset weighting algorithm further includes determining a first anomaly intensity value of the first anomaly monitoring value and a second anomaly intensity value of the second anomaly monitoring value; calculating the first anomaly intensity value and the second anomaly intensity value according to a preset weight ratio to obtain a target anomaly comprehensive value; comparing the target anomaly comprehensive value with a preset anomaly comprehensive threshold, and determining the corresponding preset monitoring point as the target anomaly monitoring point when the target anomaly comprehensive value is greater than or equal to the preset anomaly comprehensive threshold.

[0071] In this embodiment of the invention, the first abnormal intensity value can refer to the degree of deviation of the first abnormal monitoring value from the corresponding preset safety threshold. Generally speaking, the higher the first abnormal intensity value, the greater the gap between the physical monitoring data corresponding to the first abnormal monitoring value and the preset safety threshold.

[0072] Similarly, the second anomaly intensity value mentioned above can refer to the degree of deviation of the second anomaly monitoring value from the corresponding preset trend threshold. Generally speaking, the higher the second anomaly intensity value, the greater the deviation between the monitoring trend data corresponding to the second anomaly monitoring value and the preset trend threshold. For example, it can be manifested in large fluctuations in the rate of change.

[0073] The aforementioned preset weight ratio can refer to the set of weight coefficients set when the above two types of abnormal intensity values ​​are fused and calculated. It is used to reflect the relative importance of static over-limit and dynamic trend under different working conditions, different sensor types or different mining area backgrounds. It can be understood that the historical sample statistics of the target mine can be analyzed and the corresponding adjustable parameters can be configured in the above mine early warning area division platform.

[0074] The aforementioned target anomaly comprehensive value can refer to a single measurement result after weighting the first anomaly intensity value and the second anomaly intensity value according to a preset weight ratio. It is used to uniformly characterize the overall anomaly degree of the monitoring point. Generally speaking, the larger the value, the higher the overall anomaly risk. The aforementioned target anomaly comprehensive value can also be used to determine the current status of the fiber optic sensor at the current preset monitoring point.

[0075] The aforementioned current status may refer to the status labeling result made by the mining early warning area division platform for the monitoring point within the current time window based on the comprehensive value of the target anomaly, such as the level of "normal / attention / alarm / serious alarm", or the binary judgment of "abnormal / non-abnormal".

[0076] The aforementioned preset anomaly comprehensive threshold can refer to the judgment threshold corresponding to the aforementioned target anomaly comprehensive value, used to determine whether to trigger an anomaly marker. Specifically, when the aforementioned target anomaly comprehensive value is greater than or equal to the threshold, the aforementioned mine early warning area division platform will determine the corresponding preset monitoring point as the target anomaly monitoring point; otherwise, it will maintain or restore the non-abnormal state.

[0077] It is understandable that the above-mentioned preset comprehensive abnormal threshold can be set according to the target mine, the operating condition of the development equipment or the sensor type, and supports calibration and tiered settings during operation (such as different handling strategies corresponding to different threshold levels).

[0078] In one possible embodiment, the above-mentioned mine early warning area division platform calculates the intensity quantification of the first abnormal monitoring value and the second abnormal monitoring value for each preset monitoring point based on the judgment results within the same time window, and then performs weighted fusion according to the preset weight ratio to obtain the target abnormal comprehensive value for comprehensive judgment.

[0079] Through the above methods and steps, the weights and thresholds can be configured and calibrated for different mining areas and different sensor types, which facilitates scene self-adaptation and hierarchical handling, thereby improving the accuracy, interpretability and executability of target anomaly monitoring point judgment. In terms of data processing, the two types of information, static over-limit and dynamic trend, are unified into a target anomaly comprehensive value, and the judgment and status update are performed with a preset anomaly comprehensive threshold, which can improve the sensitivity and robustness of anomaly identification.

[0080] Optionally, the step of determining the boundary of the warning area based on multiple anomaly monitoring points further includes obtaining the three-dimensional coordinate information corresponding to the multiple anomaly monitoring points; determining the corresponding distribution set of anomaly monitoring points based on the multiple three-dimensional coordinate information; performing spatial boundary extraction processing on the distribution set of anomaly monitoring points to determine the spatial envelope covering the multiple anomaly monitoring points; and using the spatial envelope as the boundary of the warning area.

[0081] In this embodiment of the invention, the above-mentioned abnormal monitoring point distribution set can refer to a spatial point set composed of the three-dimensional coordinates of multiple abnormal monitoring points and their necessary attributes (such as abnormal intensity and time identifier), which can be used to characterize the overall distribution state of abnormalities in three-dimensional space. In this embodiment, it can be used as a direct input when performing boundary calculations and region division.

[0082] In one possible embodiment, the above-mentioned mine early warning area division platform performs spatial geometric operations based on the above-mentioned abnormal monitoring point distribution set, and automatically generates the external boundary from the discrete point set. Specifically, it can use convex hull, α shape, voxel envelope or deep learning-based neural network to extract the spatial boundary, and combine the geometric and geological attributes of the target mine to perform smoothing and topological correction, thereby obtaining the complete spatial envelope shape.

[0083] The aforementioned spatial envelope can refer to the closed three-dimensional geometric shell or surface obtained after the above spatial boundary extraction process. It is used to describe the spatial range occupied by the anomaly monitoring point as a whole. It can be understood that the aforementioned spatial envelope can be the minimum coverage of the anomaly distribution and also a visual representation of the boundary of the warning area in three-dimensional space. It can be directly used for risk level allocation, visualization rendering, and the definition of the scope of emergency response.

[0084] In another possible embodiment, after obtaining the three-dimensional coordinate information corresponding to each abnormal point, the above-mentioned mine early warning area division platform summarizes these coordinates according to the same time window to form an abnormal monitoring point distribution set. Then, it performs spatial boundary extraction processing based on the abnormal monitoring point distribution set, calculates the minimum spatial envelope that can cover all abnormal monitoring points, and determines the early warning area boundary at this moment.

[0085] By using the above methods and steps, the scope of anomalies can be defined in complex mining environments, avoiding the omission of potential risk points and improving the accuracy and reliability of early warning area division. The calculation and generation of the spatial envelope can also facilitate subsequent risk classification and visualization, providing a reference for mining safety monitoring and emergency decision-making.

[0086] Optionally, in the step of generating corresponding visualized partitioning results in the spatial distribution map based on the boundary of the warning area, the boundary of the warning area can be mapped to the corresponding three-dimensional coordinate system in the spatial distribution map to obtain the spatial outline of the warning area; according to the preset risk level rules, the area within the spatial outline is graded and colored to obtain the warning partition with risk level identification; the warning partition with risk level identification is rendered to generate a three-dimensional visualized partitioning map for display.

[0087] In this embodiment of the invention, the spatial outline of the warning area can refer to the closed geometric outline formed by projecting and aligning the boundary of the warning area to the three-dimensional coordinate system used in the spatial distribution map, which is used to clarify the location, range and shape of the warning area in three-dimensional space.

[0088] The aforementioned preset risk level rules may refer to the judgment and segmentation standards adopted for classifying risks in the aforementioned warning area, including the number of levels (such as Level I / II / III or Low / Medium / High), the corresponding threshold range (such as the comprehensive abnormal value range), and the necessary priority and handling suggestion mapping, which are used to uniformly generate risk level identifiers.

[0089] The aforementioned graded coloring labeling can refer to assigning different colors or symbol codes (including transparency, boundary line type, etc.) to the area within the spatial outline of the aforementioned warning area according to the aforementioned preset risk level rules, so that different risk levels can be clearly distinguished in space and are easy to read.

[0090] The aforementioned 3D visualization zoning map refers to the display result obtained by 3D rendering of the warning area after the completion of graded coloring and labeling. It intuitively presents the spatial distribution and boundaries of each risk level. It can overlay layers such as anomaly points, tunnel models and isosurfaces to provide a visual reference for monitoring, scheduling and disposal.

[0091] like Figure 2 As shown, this embodiment of the invention also provides a mine early warning area division device 200, which includes: The first acquisition module 201 is used to acquire monitoring data at multiple preset monitoring points, the monitoring data including location data and corresponding physical monitoring data; The first construction module 202 is used to construct a spatial distribution map based on the location data of the multiple preset monitoring points and the corresponding physical monitoring data; The first identification module 203 is used to identify multiple abnormal monitoring points in the spatial distribution map through the early warning security model; The first determining module 204 is used to determine the boundary of the early warning area based on multiple anomaly monitoring points; The first generation module 205 is used to generate corresponding visual partitioning results in the spatial distribution map based on the boundary of the warning area.

[0092] Optionally, the first acquisition module 201 mentioned above includes: The first determination submodule is used to determine the preset deployment spacing of fiber optic sensors based on the geological attributes, mining layout, and roof type data of the target mine. The second determining submodule is used to determine the position data of multiple fiber optic sensors based on the preset deployment spacing; The demodulation submodule is used to collect displacement and stress data of the inner layer of the top plate through fiber optic sensors deployed at preset monitoring points, and then demodulate the data by the fiber optic demodulation host to obtain the corresponding physical monitoring data.

[0093] Optionally, the first building module 202 mentioned above includes: The third determining submodule is used to determine the three-dimensional coordinates corresponding to the preset monitoring point based on the location data; A submodule is constructed to associate the three-dimensional coordinates with the corresponding physical monitoring data to build a three-dimensional mapping relationship; The generation submodule is used to generate a spatial distribution map corresponding to the target mine based on the three-dimensional mapping relationship. The spatial distribution map is used to describe the distribution of physical monitoring data of multiple preset monitoring points in three-dimensional space.

[0094] Optionally, the first identification module 203 mentioned above includes: The first processing submodule is used to compare the physical monitoring data at each preset monitoring point with the corresponding preset safety threshold to obtain the first abnormal monitoring value. The fourth determination submodule is used to determine the monitoring trend data at each preset monitoring point within a preset detection period. The second processing submodule is used to compare the monitored trend data with the corresponding preset trend threshold data to obtain the second abnormal monitoring value. The third processing submodule is used to perform weighted processing on the first abnormal monitoring value and the second abnormal monitoring value using a preset weighted algorithm to determine multiple target abnormal monitoring points.

[0095] Optionally, the third processing submodule mentioned above includes: The first determining unit is used to determine the first abnormality intensity value of the first abnormality monitoring value and the second abnormality intensity value of the second abnormality monitoring value; The calculation unit is used to calculate the first anomaly intensity value and the second anomaly intensity value according to the preset weight ratio to obtain the target anomaly comprehensive value. The target anomaly comprehensive value is used to determine the current state of the fiber optic sensor at the current preset monitoring point. The second determining unit is used to compare the target anomaly comprehensive value with a preset anomaly comprehensive threshold. When the target anomaly comprehensive value is greater than or equal to the preset anomaly comprehensive threshold, the corresponding preset monitoring point is determined as the target anomaly monitoring point.

[0096] Optionally, the first determining module 204 mentioned above includes: The first acquisition submodule is used to acquire the three-dimensional coordinate information corresponding to multiple anomaly monitoring points; The fifth determination submodule is used to determine the corresponding set of anomaly monitoring point distributions based on multiple sets of the three-dimensional coordinate information. The sixth determination submodule is used to perform spatial boundary extraction processing on the distribution set of abnormal monitoring points to determine the spatial envelope covering multiple abnormal monitoring points; A sub-module is used to use the spatial envelope as the boundary of the early warning area.

[0097] Optionally, the first generation module 205 mentioned above includes: The second acquisition submodule is used to map the boundary of the warning area to the corresponding three-dimensional coordinate system in the spatial distribution map to obtain the spatial outline of the warning area; The labeling submodule is used to perform hierarchical coloring labeling of the area within the spatial outline according to the preset risk level rules, so as to obtain the warning zone with risk level identification. The generation submodule is used to render the warning zones with risk level identifiers and generate a three-dimensional visualization zone map for display.

[0098] like Figure 3 As shown, this embodiment of the invention also provides an electronic device 300, including a processor, which can execute any of the above-mentioned mining early warning area division methods.

[0099] Specifically, it includes a processor 301 and a memory 302, as well as a computer program stored in the memory 302 and capable of running on the processor 301, which executes the method for dividing the mining area into early warning zones, wherein: The processor 301 executes the calculator program for the mine early warning zone division method stored in the memory 302, and performs the following steps: Acquire monitoring data from multiple preset monitoring points, the monitoring data including location data and corresponding physical monitoring data; Based on the location data of the multiple preset monitoring points and the corresponding physical monitoring data, a spatial distribution map is constructed. The early warning security model identifies multiple abnormal monitoring points in the spatial distribution map. Based on multiple anomaly monitoring points, the boundary of the early warning area is determined; Based on the boundaries of the warning area, corresponding visual partitioning results are generated in the spatial distribution map.

[0100] Optionally, the processor 301 performs the acquisition of monitoring data at multiple preset monitoring points, including: Based on the geological attributes, mining layout, and roof type data of the target mine, the preset deployment spacing of the fiber optic sensors is determined. Based on the preset deployment spacing, the position data of multiple fiber optic sensors are determined; By deploying fiber optic sensors at preset monitoring points, the displacement and stress data of the inner layer of the top plate are collected and demodulated by the fiber optic demodulation host to obtain the corresponding physical monitoring data.

[0101] Optionally, the processor 301 executes the step of constructing a spatial distribution map based on the location data and corresponding physical monitoring data at the plurality of preset monitoring points, including: Based on the location data, determine the three-dimensional coordinates corresponding to the preset monitoring point; The three-dimensional coordinates are associated with the corresponding physical monitoring data to construct a three-dimensional mapping relationship; Based on the three-dimensional mapping relationship, a spatial distribution map corresponding to the target mine is generated. The spatial distribution map is used to describe the distribution of physical monitoring data of multiple preset monitoring points in three-dimensional space.

[0102] Optionally, the processor 301 executes the pre-warning security model to identify multiple abnormal monitoring points in the spatial distribution map, including: The physical monitoring data at each preset monitoring point is compared with the corresponding preset safety threshold to obtain the first abnormal monitoring value. Within the preset detection period, determine the monitoring trend data at each preset monitoring point; The monitored trend data is compared with the corresponding preset trend threshold data to obtain the second abnormal monitoring value; Multiple target anomaly monitoring points are determined by weighting the first anomaly monitoring value and the second anomaly monitoring value using a preset weighting algorithm.

[0103] Optionally, the processor 301 further performs the weighting processing of the first anomaly monitoring value and the second anomaly monitoring value using a preset weighting algorithm to determine multiple target anomaly monitoring points, including: Determine the first anomaly intensity value of the first anomaly monitoring value and the second anomaly intensity value of the second anomaly monitoring value; Based on the preset weight ratio, the first anomaly intensity value and the second anomaly intensity value are calculated to obtain the target anomaly comprehensive value. The target anomaly comprehensive value is used to determine the current state of the fiber optic sensor at the current preset monitoring point. The target anomaly comprehensive value is compared with the preset anomaly comprehensive threshold. When the target anomaly comprehensive value is greater than or equal to the preset anomaly comprehensive threshold, the corresponding preset monitoring point is determined as the target anomaly monitoring point.

[0104] Optionally, the processor 301 further performs the function of determining the boundary of the warning area based on multiple anomaly monitoring points, including: Obtain the three-dimensional coordinate information corresponding to multiple anomaly monitoring points; Based on the multiple sets of three-dimensional coordinate information, the corresponding set of anomaly monitoring point distribution is determined; Spatial boundary extraction processing is performed on the distribution set of abnormal monitoring points to determine the spatial envelope covering multiple abnormal monitoring points; The spatial envelope is used as the boundary of the early warning area.

[0105] Optionally, the processor 301 performs the step of generating corresponding visual partitioning results in the spatial distribution map based on the warning area boundary, including: The boundary of the warning area is mapped to the corresponding three-dimensional coordinate system in the spatial distribution map to obtain the spatial outline of the warning area; According to the preset risk level rules, the area within the spatial outline is graded and colored to obtain a warning zone with risk level identification. The warning zones with risk level identifiers are rendered to generate a three-dimensional visualization zone map for display.

[0106] This invention also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the various processes of the mine early warning area division method or the application-side mine early warning area division method provided in this invention, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0107] Those skilled in the art will understand that implementing all or part of the processes in the above embodiments can be done by a computer program instructing related hardware, and can be stored in a computer-readable storage medium. When executed, the program can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0108] The above description discloses only preferred embodiments of the present invention and should not be construed as limiting the scope of the present invention. Therefore, equivalent variations made in accordance with the claims of the present invention are still within the scope of the present invention.

Claims

1. A method for delineating early warning zones in a mining area, characterized in that, include: Acquire monitoring data from multiple preset monitoring points, the monitoring data including location data and corresponding physical monitoring data; Based on the location data of the multiple preset monitoring points and the corresponding physical monitoring data, a spatial distribution map is constructed. A set of algorithms for determining the security status of detection data through an early warning security model is used for threshold anomaly determination, trend anomaly determination, and weighted fusion of the two. Based on the processing results, multiple abnormal monitoring points are identified in multiple preset monitoring points in the spatial distribution map. Based on multiple anomaly monitoring points, the boundary of the early warning area is determined; Based on the boundaries of the warning area, corresponding visual partitioning results are generated in the spatial distribution map.

2. The method for dividing mine early warning areas as described in claim 1, characterized in that, The acquisition of monitoring data at multiple preset monitoring points includes: Based on the geological attributes, mining layout, and roof type data of the target mine, the preset deployment spacing of the fiber optic sensors is determined. Based on the preset deployment spacing, the position data of multiple fiber optic sensors are determined; By deploying fiber optic sensors at preset monitoring points, the displacement and stress data of the inner layer of the top plate are collected and demodulated by the fiber optic demodulation host to obtain the corresponding physical monitoring data.

3. The method for dividing mine early warning areas as described in claim 1, characterized in that, The construction of a spatial distribution map based on the location data of the multiple preset monitoring points and the corresponding physical monitoring data includes: Based on the location data, determine the three-dimensional coordinates corresponding to the preset monitoring point; The three-dimensional coordinates are associated with the corresponding physical monitoring data to construct a three-dimensional mapping relationship; Based on the three-dimensional mapping relationship, a spatial distribution map corresponding to the target mine is generated. The spatial distribution map is used to describe the distribution of physical monitoring data of multiple preset monitoring points in three-dimensional space.

4. The method for dividing mine early warning areas as described in claim 3, characterized in that, The aforementioned early warning security model identifies multiple abnormal monitoring points in the spatial distribution map, including: The physical monitoring data at each preset monitoring point is compared with the corresponding preset safety threshold to obtain the first abnormal monitoring value. Within the preset detection period, determine the monitoring trend data at each preset monitoring point; The monitored trend data is compared with the corresponding preset trend threshold data to obtain the second abnormal monitoring value; Multiple target anomaly monitoring points are determined by weighting the first anomaly monitoring value and the second anomaly monitoring value using a preset weighting algorithm.

5. The method for dividing mine early warning areas as described in claim 4, characterized in that, The step involves weighting the first anomaly monitoring value and the second anomaly monitoring value using a preset weighting algorithm to determine multiple target anomaly monitoring points, including: Determine the first anomaly intensity value of the first anomaly monitoring value and the second anomaly intensity value of the second anomaly monitoring value; Based on the preset weight ratio, the first anomaly intensity value and the second anomaly intensity value are calculated to obtain the target anomaly comprehensive value. The target anomaly comprehensive value is used to determine the current state of the fiber optic sensor at the current preset monitoring point. The target anomaly comprehensive value is compared with the preset anomaly comprehensive threshold. When the target anomaly comprehensive value is greater than or equal to the preset anomaly comprehensive threshold, the corresponding preset monitoring point is determined as the target anomaly monitoring point.

6. The method for dividing mine early warning areas as described in claim 1, characterized in that, The determination of the early warning area boundary based on multiple anomaly monitoring points includes: Obtain the three-dimensional coordinate information corresponding to multiple anomaly monitoring points; Based on the multiple sets of three-dimensional coordinate information, the corresponding set of anomaly monitoring point distribution is determined; Spatial boundary extraction processing is performed on the distribution set of abnormal monitoring points to determine the spatial envelope covering multiple abnormal monitoring points; The spatial envelope is used as the boundary of the early warning area.

7. The method for dividing mine early warning areas as described in claim 6, characterized in that, The step of generating corresponding visual partitioning results on the spatial distribution map based on the boundary of the warning area includes: The boundary of the warning area is mapped to the corresponding three-dimensional coordinate system in the spatial distribution map to obtain the spatial outline of the warning area; According to the preset risk level rules, the area within the spatial outline is graded and colored to obtain a warning zone with risk level identification. The warning zones with risk level identifiers are rendered to generate a three-dimensional visualization zone map for display.

8. A mine early warning zone delineation device, characterized in that, include: The first acquisition module is used to acquire monitoring data at multiple preset monitoring points, the monitoring data including location data and corresponding physical monitoring data; The first construction module is used to construct a spatial distribution map based on the location data of the multiple preset monitoring points and the corresponding physical monitoring data; The first identification module is used to identify multiple abnormal monitoring points in the spatial distribution map through the early warning security model; The first determining module is used to determine the boundary of the early warning area based on multiple anomaly monitoring points; The first generation module is used to generate corresponding visual partitioning results in the spatial distribution map based on the boundary of the warning area.

9. An electronic device, characterized in that, include: The system includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the steps in the mine early warning zone delineation method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps in the mine early warning area delineation method as described in any one of claims 1 to 7.

Images