A laser radar combined with meteorological early warning coal mine geological disaster monitoring method and system

Abstract

This invention belongs to the field of early warning technology for coal mine mining, and discloses a method and system for monitoring geological disasters in coal mines using lidar combined with meteorological early warning. The method deploys lidar combined with meteorological early warning geological disaster monitoring equipment in the three upper zones of the above-ground mining area, and collects the current motion frequencies of the three upper zones in real time to obtain motion frequency curves. The three upper zones include bending subsidence zones, fracture zones, and caving zones. Beidou GNSS is deployed in the three upper zones of the above-ground mining area to smooth the acquired motion frequency curves and eliminate the influence of atmospheric delay errors. The motion frequency curves, after eliminating atmospheric delay errors and smoothing, are applied to actual mining operations in the three upper zones of the above-ground mining area to obtain deformation information generated at a certain moment during actual mining operations. This invention achieves high-precision dynamic coupling monitoring of surface geological disaster deformation during coal mining activities.

Description

Technical Field

[0001] This invention belongs to the field of early warning technology for coal mining, and in particular relates to a method and system for monitoring geological disasters in coal mines by combining lidar with meteorological early warning. Background Technology

[0002] The field of geological hazard analysis technology is an interdisciplinary field focused on identifying, assessing, and predicting the likelihood of geological hazards. This field combines knowledge and methods from multiple disciplines, including geology, geophysics, geographic information systems (GIS), remote sensing, computer science, statistics, and engineering.

[0003] The goal of the field of geological hazard analysis technology is to improve our understanding of geological hazards, reduce the risk of disasters, and enable effective response and rescue efforts when disasters occur. This field is of great significance for protecting people's lives and property and promoting sustainable social development.

[0004] The existing invention patent, "A Method and Device for Monitoring and Early Warning of Geological Disasters in Coal Mines" (Publication No. CN118629165A, Publication Date 2024.09.10), discloses:

[0005] This invention uses sensors to monitor environmental parameters inside the mine in real time and assess the mine's current safety based on these parameters, determining whether a collapse anomaly exists. These environmental parameters include temperature, humidity, gas concentration, and vibration. When a collapse anomaly is detected, the current environmental parameters of each passage within the mine are acquired, and the risk of each passage in this collapse anomaly is analyzed based on its location and the distance between passages. Based on the risk analysis results for each passage, safe escape routes are assessed. When all passages are impassable, areas without collapse risk are identified, and safe routes to these areas are assessed and synchronized to lighting circuits for marking. Once personnel reach an area without collapse risk, sensors acquire the current physical properties of the rock strata in that area, and a geological model is built to identify areas suitable for drilling and ventilation, as well as areas suitable for excavation and rescue, which are then marked in the geological model. This invention not only relies on advanced technology but also on its ability to flexibly adjust and optimize according to actual conditions, ensuring optimal solutions in various complex situations.

[0006] Furthermore, during mining operations, monitoring the subsidence of goaf areas is a crucial step in ensuring safety. Failure to monitor goaf subsidence can lead to mining disasters and surface collapses. Therefore, monitoring goaf subsidence is essential to guarantee safety during the mining process.

[0007] The accuracy and real-time nature of settlement monitoring data are crucial for the management and safety of goaf areas. To understand the settlement situation in goaf areas in real time and take timely measures, regular monitoring of goaf settlement is necessary. However, currently, the data collection frequency for goaf settlement monitoring relies solely on pre-set time intervals. This single data collection frequency affects the accuracy and real-time nature of the monitoring. Too high a frequency leads to data redundancy and increases data processing costs; too low a frequency may miss crucial settlement velocity changes, thus affecting the accuracy of the monitoring. Therefore, the key question is how to dynamically set the collection frequency based on the actual conditions of mining operations to improve the accuracy of the monitoring data.

[0008] The invention patent "Method and System for Dynamic Coupling Monitoring of Coal Mine Goaf Deformation Based on Multi-Source Data" (Publication No. CN119064929A, Publication Date 2024.12.03) discloses a method for dynamic coupling monitoring of coal mine goaf deformation based on multi-source data. The method includes: S1, monitoring mine subsidence based on the fusion technology of BeiDou GNSS and D-InSAR, establishing a network of continuous GNSS observation stations in the surface mining area, constructing a regional water vapor model and an atmospheric delay error correction model, and completing the fusion processing of the time domain and spatial domain fusion model and algorithm; using the double-interpolation double-estimation (DIDP) algorithm to encrypt the GNSS and D-InSAR monitoring data, reducing atmospheric delay errors. Impact; S2, for the mining area subsidence monitoring information after the acquisition of reduced atmospheric delay error, for the decoherence caused by the large gradient deformation in the mining area subsidence region, the deformation monitoring method of mining area based on logarithmic logic model and SBAS-InSAR and GNSS coupling technology is used to calculate the deformation information generated by mining activities at any time; S3, electrical resistivity system and microseismic monitoring system are deployed to monitor the combined stress change of underground resistivity and microseismic forces, realizing the delineation of large gradient anomalies in the underground mining area; combined with the subsidence deformation monitoring information of the surface mining area, and combined with the combined stress change monitoring of underground resistivity and microseismic forces, collaborative monitoring is carried out to complete the collaborative dynamic coupling monitoring of the deformation process of the goaf. This invention provides collaborative dynamic coupling monitoring of the deformation process of the three zones (bending subsidence zone, fracture zone, and caving zone) in the goaf.

[0009] However, existing methods for monitoring geological hazards in coal mines may only focus on a single factor or a local area, lacking a comprehensive consideration of the entire mine system. During the deformation process of the three zones above the goaf (bending and subsidence zone, fracture zone, and caving zone), they cannot effectively utilize lidar in conjunction with meteorological early warning, and the frequency of data collection and reporting cannot be dynamically coupled for monitoring. This results in low accuracy of dynamic coupling monitoring of deformation above the goaf, and the effectiveness of monitoring geological hazards in coal mines needs further improvement. Summary of the Invention

[0010] To overcome the problems existing in related technologies, the present invention discloses an embodiment of a method and system for monitoring geological disasters in coal mines using lidar combined with meteorological early warning, specifically involving a method and system for monitoring the frequency of data collection and reporting by lidar combined with meteorological early warning geological disaster monitoring equipment.

[0011] The technical solution is as follows: A method for monitoring geological disasters in coal mines using lidar combined with meteorological early warning, comprising the following steps:

[0012] S1, deploy lidar combined with meteorological early warning and geological disaster monitoring equipment in the upper three zones of the mining area above ground, and collect the current motion frequency of the upper three zones in real time to obtain motion frequency curves; the upper three zones include: bending subsidence zone, fracture zone and caving zone;

[0013] S2, deploying BeiDou GNSS in the upper three zones of the mining area above ground, smoothing the acquired motion frequency curves and eliminating the influence of atmospheric delay errors;

[0014] S3, which eliminates the influence of atmospheric delay error and smooths the motion frequency curve, is applied to the actual operation of mining activities in the upper three zones of the surface mining area. It obtains deformation information generated at a certain moment in the actual operation of mining activities, and realizes high-precision dynamic coupling monitoring of surface geological disaster deformation in coal mining activities.

[0015] In step S1, the motion frequency curve is obtained, including:

[0016] (1) Considering the different maximum early warning geological disaster allowable value and the ideal early warning geological disaster allowable value area ratio K1, the traditional default is that the allowable value is less than 0.25%H, where H is the height of the upper three zones at each level. At this time, the current upper three zones movement state reaches normal deformation.

[0017] (2) Establish a rectangular coordinate system with the outer edge of the ideal early warning geological hazard allowable value as the origin, along the axial x and radial y directions. E0 is the product of the ideal upper three-zone deformation early warning geological hazard allowable value. h E represents the permissible area for geological disaster warnings in the upper three zones, where h is the deformation length of the upper three zones; and E represents the permissible area for geological disaster warnings at a certain point in the deformation of the upper three zones. c The subscript 'c' represents the distance between the allowable value for this geological hazard warning and the ideal allowable value for this geological hazard warning. The outer edge of the maximum allowable value for the upper three zones of geological hazard warning is based on G. h The change is determined by the change in the curve, and the other endpoint of the three-zone deformation is designed as a shape function e(c), which has the characteristic of continuous monotonically increasing.

[0018] Furthermore, the calculation method for the ratio of the maximum allowable area of ​​a geological hazard warning to the ideal allowable area of ​​a geological hazard warning, K1, to be greater than 1 includes:

[0019] The frequency of motion (2a+1) is optimized to ensure that the cross-sectional area ratio is at least greater than 1 / 2a. Furthermore, the larger the cross-sectional area ratio, the greater the warning level for optimized motion frequency, and different curve shapes can be designed under different cross-sectional area ratios.

[0020] Furthermore, the mathematical model for the motion frequency of the three-zone deformation on the curve is obtained as follows:

[0021]

[0022] In the formula, γ c γc represents the electromagnetic saturation of the lidar on the three-zone deformation at a distance c from the ideal early warning geological hazard allowable value; γ0 represents the lidar electromagnetic saturation at the ideal early warning geological hazard allowable value, initially 0 without lidar electromagnetic input, with a maximum value of γc. 0max =(G h -1)π;o h For the fundamental current of the lidar, F has a given value. t0 The electromagnetic induction intensity of the lidar at the critical saturation point of the ideal early warning geological disaster is o (2a+1) Here, C represents the named value of the frequency current during the (2a+1)th motion, and C is the number of each layer in the upper three bands. Let be the electromagnetic emissivity of the vacuum lidar, and a be the a-th lidar band.

[0023] In step S2, BeiDou GNSS is deployed in the upper three zones of the surface mining area, and the acquired motion frequency curves are smoothed, including:

[0024] Input real-time acquired motion frequency curve data and process it using an exponential smoothing formula, the expression of which is:

[0025] A0(I)=χm0(I)+(1-χ)A0(I-1)

[0026] In the formula, A0(I) is the smoothing sequence, χ is the smoothing coefficient, I is a node value of the motion frequency curve, m0(I) is the initial motion frequency curve data sequence, and A0(I-1) is the smoothing sequence of node I-1 of the motion frequency curve.

[0027] In step S3, deformation information generated at a certain moment during the actual mining operation is obtained, including:

[0028] The motion frequency feature vector is reduced in dimensionality using principal feature analysis, and a feature classifier is used to identify the deformation of the upper three zones of the LiDAR radiation mining area at a certain moment.

[0029] By linearly projecting the original motion frequency variable to form a new variable, the principal feature of the feature is calculated, and the expression is:

[0030]

[0031] In the formula, η is the principal characteristic, and ζ is the principal characteristic. T Let covariance matrix be the variance matrix. For features that need dimensionality reduction The feature mean of the training samples;

[0032] covariance matrix ζ T The calculation formula is:

[0033]

[0034] In the formula, B is the number of training samples. The T-order derivative is calculated for the deviation between the reduced features and the mean features of the training samples.

[0035] Furthermore, the feature classifier employs a kernel function to map the motion frequency feature vector R from the input space to a high-dimensional feature space, and then searches for a generalized optimal classification surface in the high-dimensional space, expressed as:

[0036]

[0037] In the formula, θ(η) is the generalized optimal classification surface vector found in the high-dimensional space after the principal feature mapping, and Γ is the classification coefficient. This represents the mapping deviation.

[0038] The greater the distance to the nearest motion frequency sample from the classification surface, the less likely the motion frequency detection sample will be misclassified. The motion frequency feature sample point is (k g ,τ h The motion frequency sample category is identified as τ. h ={-1,+1}, the expression is:

[0039]

[0040] When ||Γ|| is minimized, the classification margin is maximized, which is equivalent to minimizing ||Γ||. 2 / 2 is the minimum.

[0041] Another objective of this invention is to provide a lidar-based meteorological early warning coal mine geological disaster monitoring system, which implements the lidar-based meteorological early warning coal mine geological disaster monitoring method. The system includes:

[0042] The motion frequency curve acquisition module is used to deploy lidar combined with meteorological early warning and geological disaster monitoring equipment in the upper three zones of the surface mining area, and to collect the current motion frequency of the upper three zones in real time to obtain the motion frequency curve; the upper three zones include: bending subsidence zone, fracture zone and caving zone;

[0043] The smoothing module is used to deploy BeiDou GNSS in the upper three zones of the surface mining area, smooth the acquired motion frequency curves, and eliminate the influence of atmospheric delay errors.

[0044] The deformation information acquisition module is used to eliminate the influence of atmospheric delay error and smooth the motion frequency curve. It is applied to the actual operation of mining activities in the upper three zones of the surface mining area to obtain the deformation information generated at a certain moment in the actual operation of mining activities, so as to realize high-precision dynamic coupling monitoring of surface geological disaster deformation in coal mining activities.

[0045] Furthermore, the lidar combined with meteorological early warning coal mine geological disaster monitoring system is mounted on a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it can realize the functions of the lidar combined with meteorological early warning coal mine geological disaster monitoring system.

[0046] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to perform the lidar combined with meteorological early warning coal mine geological disaster monitoring method.

[0047] Combining all the above technical solutions, the beneficial effects of this invention are as follows: This invention employs surface lidar combined with meteorological early warning technology to perform coordinated dynamic coupling monitoring of the deformation process of the three zones (bending and subsidence zone, fracture zone, and caving zone) in the goaf. It leverages the spatiotemporal complementarity and process synergy of multiple methods, and deploys BeiDou GNSS at appropriate locations on-site to eliminate the influence of atmospheric delay errors, thereby achieving high-precision dynamic coupling monitoring of deformation in the coal mine goaf. Attached Figure Description

[0048] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure;

[0049] Figure 1 This is a flowchart of a method for monitoring coal mine geological disasters using lidar combined with meteorological early warning, provided in an embodiment of the present invention.

[0050] Figure 2 This is a motion frequency curve provided in an embodiment of the present invention;

[0051] Figure 3 This is a diagram of a lidar combined with meteorological early warning and coal mine geological disaster monitoring system provided in an embodiment of the present invention;

[0052] Figure 4 This is a graph showing the relationship between the motion frequency of the upper three zones detected by the lidar at 10kHz and the geological disaster deformation warning value of the meteorological early warning geological disaster monitoring equipment, provided in an embodiment of the present invention.

[0053] Figure 5 This is a graph showing the relationship between the motion frequency of the upper three zones detected by the lidar at 130kHz and the geological disaster deformation warning value of the meteorological early warning geological disaster monitoring equipment, provided in an embodiment of the present invention.

[0054] In the diagram: 1. Motion frequency curve acquisition module; 2. Smoothing module; 3. Deformation information acquisition module. Detailed Implementation

[0055] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Many specific details are set forth in the following description to provide a thorough understanding of the present invention. However, the present invention can be practiced in many other ways different from those described herein, and those skilled in the art can make similar modifications without departing from the spirit of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0056] Example 1, such as Figure 1 As shown in the embodiment of the present invention, the method for monitoring geological disasters in coal mines by combining lidar with meteorological early warning includes:

[0057] S1, deploy lidar combined with meteorological early warning and geological disaster monitoring equipment in the upper three zones of the mining area above ground, and collect the current motion frequency of the upper three zones in real time to obtain motion frequency curves; the upper three zones include: bending subsidence zone, fracture zone and caving zone;

[0058] S2, deploying BeiDou GNSS in the upper three zones of the mining area above ground, smoothing the acquired motion frequency curves and eliminating the influence of atmospheric delay errors;

[0059] S3, which eliminates the influence of atmospheric delay error and smooths the motion frequency curve, is applied to the actual operation of mining activities in the upper three zones of the surface mining area. It obtains deformation information generated at a certain moment in the actual operation of mining activities, and realizes high-precision dynamic coupling monitoring of surface geological disaster deformation in coal mining activities.

[0060] For example, in step S1, obtaining the motion frequency curve includes:

[0061] (1) Considering different maximum early warning geological disaster allowable values ​​and ideal early warning geological disaster allowable values ​​area ratio K1, the traditional default is that the allowable value is less than 0.25%H (H is the height of each level of the upper three zones). At this time, the current upper three zones can reach normal deformation. In the process of optimization design, this invention can consider different area ratios. The area of ​​the ideal early warning geological disaster allowable value of 0.01%H is "1" part, and the maximum early warning geological disaster allowable value area is tentatively set to be greater than 1 and less than 25.

[0062] (2) Establish a rectangular coordinate system along the axial and radial directions with the outer edge of the ideal early warning geological hazard allowable value as the origin, as shown in the figure. E0 is the product of the ideal upper three-zone deformation early warning geological hazard allowable value. h Let E be the area (micro-element) of the allowable value for geological hazards in the upper three zones, and h be the deformation length of the upper three zones. The allowable area (micro-element) of a certain location within the deformation of the upper three zones is E. c The subscript 'c' represents the distance between the allowable value for this geological hazard warning and the ideal allowable value for this geological hazard warning. The outer edge of the maximum allowable value for the upper three zones of geological hazard warning is based on G. h The change determines the shape of the three-zone deformation at the other endpoint of the curve, which is designed as a shape function e(c), characterized by continuous monotonically increasing characteristics. The shape function e(c), as... Figure 2 The motion frequency curve is shown below;

[0063] The calculation method for the ratio of the area of ​​the maximum allowable value for early warning geological disasters to the area of ​​the ideal allowable value for early warning geological disasters, K1, is greater than 1 includes:

[0064] When optimizing the (2a+1)th motion frequency (3rd, 5th, 7th... motion frequencies), the cross-sectional area ratio must be at least greater than Furthermore, the larger the cross-sectional area ratio, the greater the warning effect of optimized motion frequency. Different curve shapes are designed under different cross-sectional area ratios.

[0065] Based on the above differences, we can obtain a mathematical model for the motion frequency of the three-zone deformation on the curve:

[0066]

[0067] In the formula, γ c γc represents the electromagnetic saturation of the lidar on the three-zone deformation at a distance c from the ideal early warning geological hazard allowable value; γ0 represents the lidar electromagnetic saturation at the ideal early warning geological hazard allowable value, initially 0 without lidar electromagnetic input, with a maximum value of γc. 0max =(G h -1)π;o h For the fundamental current of the lidar, F has a given value. t0 The electromagnetic induction intensity of the lidar at the critical saturation point of the ideal early warning geological disaster is o (2a+1) Here, C represents the named value of the frequency current during the (2a+1)th motion, and C is the number of each layer in the upper three bands. Let be the electromagnetic emissivity of the vacuum lidar, and a be the a-th lidar band.

[0068] For example, in step S2, BeiDou GNSS is deployed in the upper three zones of the surface mining area to smooth the acquired motion frequency curve and eliminate the influence of atmospheric delay error;

[0069] Input the real-time acquired motion frequency curve data and apply the exponential smoothing formula:

[0070] A0(I)=χm0(I)+(1-χ)A0(I-1)

[0071] In the formula, A0(I) is the smoothed sequence, χ is the smoothing coefficient, I is a node value of the motion frequency curve, and the motion frequency curve data with random fluctuations is smoothed to improve the smoothness of the sequence, weaken its randomness, and make it closer to the deformation development trend of the upper three zones of the mining area; m0(I) is the initial motion frequency curve data sequence, and A0(I-1) is the smoothed sequence of the I-1 node of the motion frequency curve.

[0072] For example, a classic method to eliminate the influence of atmospheric delay error can be adopted, which involves using the error propagation law to quantitatively analyze the impact of atmospheric delay error on elevation measurement and deformation measurement (two-track method, three-track method and four-track method), plotting the error propagation curve, and obtaining the influence law of atmospheric delay error on the acquired motion frequency measurement, that is, the influence law of deformation measurement in the three zones of the mining area.

[0073] In step S3, the method for obtaining deformation information generated at a certain moment during the actual operation of mining activities includes:

[0074] The motion frequency feature vector is reduced in dimensionality using principal feature analysis, and a feature classifier is used to identify the deformation of the upper three zones of the LiDAR radiation mining area at a certain moment.

[0075] By linearly projecting the original motion frequency variable to form a new variable, the principal features of the feature are calculated:

[0076]

[0077] In the formula, η is the principal characteristic, and ζ is the principal characteristic. T Let covariance matrix be the variance matrix. For features that need dimensionality reduction The feature mean of the training samples;

[0078] covariance matrix ζ T The calculation formula is:

[0079]

[0080] In the formula, B is the number of training samples. The T-order derivative is calculated for the deviation between the reduced features and the mean features of the training samples.

[0081] For example, the feature classifier uses a kernel function to map the motion frequency feature vector Y in the input space to a high-dimensional feature space, and then searches for a generalized optimal classification surface in the high-dimensional space, which generally takes the form:

[0082]

[0083] In the formula, θ(η) is the generalized optimal classification surface vector found in the high-dimensional space after the principal feature mapping, and Γ is the classification coefficient. This represents the mapping deviation.

[0084] The optimal classification surface requires that the distance to the nearest motion frequency sample is as large as possible, and the motion frequency feature sample points (k g ,τ h ), motion frequency sample category identifier τ h If the value is {-1, +1}, then the probability of the motion frequency detection sample being misclassified will be smaller: the expression is:

[0085]

[0086] When ||Γ|| is minimized, the classification margin is maximized, which is equivalent to minimizing ||Γ||. 2 / 2 is the minimum.

[0087] As can be seen from the above embodiments, the present invention improves the accuracy of dynamic coupling monitoring of surface geological disaster deformation in coal mining activities from 87.26% to approximately 95.23%.

[0088] Example 2, as Figure 3 As shown in the figure, the lidar combined with meteorological early warning coal mine geological disaster monitoring system provided in this embodiment of the invention includes:

[0089] The motion frequency curve acquisition module 1 is used to deploy lidar combined with meteorological early warning and geological disaster monitoring equipment in the upper three zones of the surface mining area, and to collect the current motion frequency of the upper three zones in real time to obtain the motion frequency curve; the upper three zones include: bending subsidence zone, fracture zone and caving zone;

[0090] Smoothing module 2 is used to deploy BeiDou GNSS in the upper three zones of the surface mining area, smooth the acquired motion frequency curves, and eliminate the influence of atmospheric delay errors.

[0091] The deformation information acquisition module 3 is used to eliminate the influence of atmospheric delay error and smooth the motion frequency curve. It is applied to the actual operation of mining activities in the upper three zones of the surface mining area to obtain the deformation information generated at a certain moment in the actual operation of mining activities, so as to realize high-precision dynamic coupling monitoring of surface geological disaster deformation in coal mining activities.

[0092] like Figure 4 , Figure 5As shown, A0-A6 represent the development trend subsequences of motion frequency; the horizontal axis represents the motion frequency of the upper three zones detected by the lidar, and the vertical axis represents the geological disaster deformation warning value of the meteorological early warning geological disaster monitoring equipment. It can be seen that this invention can effectively predict geological disasters by utilizing lidar combined with meteorological early warning geological disaster monitoring equipment.

[0093] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications, equivalent substitutions and improvements made by those skilled in the art within the scope of the technology disclosed in the present invention and within the spirit and principles of the present invention should be covered within the scope of protection of the present invention.

Claims

1. A method for monitoring geological disasters in coal mines using lidar combined with meteorological early warning, characterized in that, The method includes the following steps: S1, deploy lidar combined with meteorological early warning and geological disaster monitoring equipment in the upper three zones of the mining area above ground, and collect the current motion frequency of the upper three zones in real time to obtain motion frequency curves; the upper three zones include: bending subsidence zone, fracture zone and caving zone; S2, deploying BeiDou GNSS in the upper three zones of the mining area above ground, smoothing the acquired motion frequency curves and eliminating the influence of atmospheric delay errors; S3, which eliminates the influence of atmospheric delay error and smooths the motion frequency curve, is applied to the actual operation of mining activities in the upper three zones of the surface mining area to obtain deformation information generated at a certain moment in the actual operation of mining activities, and realizes high-precision dynamic coupling monitoring of surface geological disaster deformation in coal mining activities. In step S1, the motion frequency curve is obtained, including: (1) Considering the area ratio of different maximum early warning geological hazard allowable values ​​to ideal early warning geological hazard allowable values. The traditional default value is less than 0.25%H, where H is the height of the upper three bands at each level. At this point, the current motion state of the upper three bands reaches normal deformation. (2) Establish a rectangular coordinate system with the outer edge of the ideal early warning geological disaster allowable value as the origin, along the axial direction x and the radial direction y. To provide an ideal value for the allowable geological disaster warning of the three zones of deformation, This is the accumulation of the allowable value for geological disaster early warning in the upper three zones. The deformation length of the upper three zones; the permissible area for early warning geological disasters at a certain location within the deformation of the upper three zones is... subscript This represents the distance between the allowable value for geological disaster warning and the ideal allowable value for geological disaster warning. The outer edge of the maximum allowable value for geological disaster warning in the upper three zones is based on... The change in shape determines the shape of the three-zone deformation at the other endpoint of the curve, which is designed as a shape function. The function has the characteristic of being continuously monotonically increasing.

2. The method for monitoring geological disasters in coal mines using lidar combined with meteorological early warning as described in claim 1, characterized in that, Ratio of the maximum allowable value for early warning geological disasters to the ideal allowable value for early warning geological disasters Methods for calculating values ​​greater than 1 include: right The frequency of the next motion is optimized to ensure that the cross-sectional area ratio is at least greater than [missing value]. Furthermore, the larger the cross-sectional area ratio, the greater the warning level of optimized motion frequency. Different curve shapes are designed under different cross-sectional area ratios.

3. The method for monitoring geological disasters in coal mines using lidar combined with meteorological early warning as described in claim 1, characterized in that, The mathematical model for the motion frequency of the three-zone deformation on the curve is as follows: ； In the formula, The distance from the ideal early warning geological disaster allowable value Electromagnetic saturation of a lidar with three-zone deformation on a micro-element; The ideal allowable value for lidar electromagnetic saturation in early warning of geological disasters is given. The initial state without lidar electromagnetic input is 0, and the maximum value is... ; The fundamental current of the lidar has a given value. The electromagnetic induction intensity of the lidar at the critical saturation point of the ideal early warning geological disaster. For the first The named value of the current at the next motion frequency. The number of each layer in the upper three bands. The electromagnetic emissivity of vacuum lidar. For the first One lidar band.

4. The method for monitoring geological disasters in coal mines using lidar combined with meteorological early warning as described in claim 1, characterized in that, In step S2, BeiDou GNSS is deployed in the upper three zones of the surface mining area, and the acquired motion frequency curves are smoothed, including: Input real-time acquired motion frequency curve data and process it using an exponential smoothing formula, the expression of which is: ； In the formula, For smooth sequences, For smoothing coefficients, This represents a node value on the motion frequency curve. This is the initial motion frequency curve data sequence. For the motion frequency curve A smooth sequence of -1 nodes.

5. The method for monitoring geological disasters in coal mines using lidar combined with meteorological early warning as described in claim 1, characterized in that, In step S3, deformation information generated at a certain moment during the actual mining operation is obtained, including: The motion frequency feature vector is reduced in dimensionality using principal feature analysis, and a feature classifier is used to identify the deformation of the upper three zones of the LiDAR radiation mining area at a certain moment. By linearly projecting the original motion frequency variable to form a new variable, the principal feature of the feature is calculated, and the expression is: ； In the formula, Main features Let covariance matrix be the variance matrix. For features that require dimensionality reduction, The feature mean of the training samples; covariance matrix The calculation formula is: ； In the formula, The number of training samples. To measure the deviation between the reduced features and the mean features of the training samples Differentiate the order.

6. The method for monitoring geological disasters in coal mines using lidar combined with meteorological early warning as described in claim 5, characterized in that, The feature classifier uses a kernel function to classify the motion frequency feature vectors in the input space. Mapping to a high-dimensional feature space, we search for the generalized optimal classification surface in the high-dimensional space, expressed as: ； In the formula, After mapping the principal features, the optimal generalized classification surface vector is found in the high-dimensional space. For classification coefficients, This represents the mapping deviation. The greater the distance to the nearest motion frequency sample from the classification surface, the less likely the motion frequency detection sample will be misclassified. The motion frequency feature sample points are... The motion frequency sample category is identified as The expression is: ； when When the minimum value is reached, the classification interval is maximized, which is also equivalent to making the classification interval maximized. Minimum.

7. A lidar-based meteorological early warning coal mine geological disaster monitoring system, characterized in that, The system implements the lidar combined with meteorological early warning coal mine geological disaster monitoring method as described in any one of claims 1-6, and the system includes: The motion frequency curve acquisition module (1) is used to deploy lidar combined with meteorological early warning and geological disaster monitoring equipment in the upper three zones of the surface mining area, and to collect the current motion frequency of the upper three zones in real time to obtain the motion frequency curve; the upper three zones include: bending subsidence zone, fracture zone and caving zone; The smoothing module (2) is used to deploy Beidou GNSS in the upper three zones of the surface mining area, smooth the acquired motion frequency curve, and eliminate the influence of atmospheric delay error; The deformation information acquisition module (3) is used to eliminate the influence of atmospheric delay error and smooth the motion frequency curve. It is applied to the actual operation of mining activities in the upper three zones of the mining area to obtain the deformation information generated at a certain moment in the actual operation of mining activities, so as to realize the dynamic coupling high-precision monitoring of surface geological disaster deformation in coal mining activities.

8. The lidar combined with meteorological early warning coal mine geological disaster monitoring system according to claim 7, characterized in that, The lidar combined with meteorological early warning coal mine geological disaster monitoring system is mounted on a computer-readable storage medium. The computer-readable storage medium stores a computer program, which, when executed by a processor, can realize the functions of the lidar combined with meteorological early warning coal mine geological disaster monitoring system.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, the processor performs the laser radar combined with meteorological early warning coal mine geological disaster monitoring method according to any one of claims 1-6.

Images