Early warning method and system based on geological safety monitoring

Abstract

The invention relates to the technical field of image data processing, in particular to a geological safety monitoring and early warning method and system. The method comprises the following steps: acquiring an elevation map of a mining area and a current sailing path of an unmanned aerial vehicle for executing safety exploration in the mining area, and positioning the path on the elevation map; marking pixel points on the path as navigation pixel points, and obtaining a plurality of prediction lines of the navigation pixel points; acquiring predicted elevation data of the navigation pixel points; acquiring corrected elevation data of the navigation pixel points; obtaining collapse coefficients of the navigation pixel points; and according to the collapse coefficient, determining a dangerous area of the mining area, and realizing early warning based on geological safety monitoring. According to the method, prediction is performed based on the navigation pixel points and the historical elevation data on the plurality of prediction lines, so that error transmission caused by single-direction prediction is avoided, the accuracy and reliability of elevation data prediction are improved, and the accuracy of safety monitoring and early warning of a mine is further improved.

Description

Technical Field

[0001] The present invention relates to the technical field of image data processing, and particularly to a geological safety monitoring and early warning method and system. Background Art

[0002] As a key link in resource development and environmental protection, geological safety monitoring has formed a multi-disciplinary technical system. Traditional methods rely on manual inspections, ground monitoring equipment, and remote sensing satellite data. Although they can cover a large area, they have limitations such as long monitoring cycles, high costs, and difficulty in capturing small deformations. In recent years, unmanned aerial vehicle (UAV) technology, with its flexibility and high-resolution data acquisition capabilities, has gradually become the core means of mine monitoring, especially in areas with complex terrain or difficult access for personnel.

[0003] In the field of mining engineering, the treatment of goafs is a long-term challenge. Backfilling technologies (such as paste filling and high-water material filling) are affected by variable geological conditions, material aging (such as sulfate erosion and carbonation reactions), and groundwater seepage. There are potential collapse risks in some areas. According to statistics, the economic losses caused by goaf collapses exceed tens of billions of yuan every year, involving problems such as farmland damage, building cracking, and ground subsidence, seriously threatening the safety of surrounding residents and the ecological environment.

[0004] In current mine geological safety monitoring and early warning, the accuracy of elevation data prediction has always faced severe challenges. Existing methods mostly predict the elevation data of pixel points in a single direction. This limitation makes the prediction results extremely vulnerable to the errors of pixel points in a single direction. Due to the complex and variable mining area environment, data deviation is inevitably generated during the data acquisition process. The single-direction prediction mode cannot effectively avoid such errors and is difficult to comprehensively capture the terrain change characteristics, resulting in low prediction accuracy. The monitoring plan based on low-precision prediction data cannot accurately judge the potential risks of ground collapse and is difficult to achieve early identification of collapse hazards. At the same time, inaccurate prediction results will mislead the development of mine planning, land reclamation, etc. It may not only cause resource waste but also bring unpredictable risks to the ecological environment, infrastructure, and personnel safety in the mining area and its surrounding areas, severely restricting the effectiveness and reliability of mine geological safety monitoring and early warning work. Summary of the Invention

[0005] In order to solve the problem that in the process of predicting elevation data by existing methods, the elevation data of pixel points are predicted in a single direction, making the prediction results extremely vulnerable to the errors of pixel points in a single direction, resulting in a decrease in prediction accuracy and further reducing the accuracy of mine safety monitoring and early warning, the present invention provides a geological safety monitoring and early warning method and system.

[0006] In the first aspect, the present invention provides a geological safety monitoring and early warning method, which adopts the following technical solution: A geological safety monitoring and early warning method comprises: obtaining an elevation map of a mining area and a navigation path of a drone used for performing safety exploration in the mining area, and positioning the path on the elevation map; recording pixel points on the path as navigation pixel points, recording any navigation pixel point as a target pixel point, obtaining multiple prediction lines of the target pixel point based on a vector formed by the target pixel point and the next navigation pixel point of the target pixel point, determining a prediction value of the target pixel point based on each prediction line according to the most recent historical elevation data of all pixel points on each prediction line of the target pixel point, and taking the average of the prediction values ​​as the target image. The predicted elevation data of the pixel point; the normalized result of the difference between the predicted elevation data and the current navigation elevation data of the target pixel point is used as the correction requirement of the target pixel point; according to the size of the correction requirement, the current navigation elevation data of the target pixel point is corrected to determine the corrected elevation data of the target pixel point; according to the difference between the corrected elevation data of all navigation pixel points and the most recent historical elevation data, and the difference between the corrected elevation data of the target pixel point and multiple historical elevation data, the collapse coefficient of the target pixel point is determined; according to the collapse coefficient, the dangerous area of ​​the mining area is determined to realize geological safety monitoring and early warning.

[0007] The beneficial effects are as follows: by constructing multiple prediction lines based on the vector formed by the target pixel point and its next navigation pixel point, and comprehensively utilizing the historical elevation data on multiple prediction lines to predict the elevation of the target pixel point, the error influence caused by single-direction prediction is effectively avoided, and the accuracy of elevation data prediction is significantly improved; the elevation data of this navigation is corrected in a targeted manner based on the correction requirement, which reduces the anomalies caused by environmental changes or data collection errors and ensures the timeliness and authenticity of the elevation data; by performing differential analysis on the corrected elevation data and multiple historical data, the collapse coefficient is accurately calculated, which can more comprehensively and sensitively capture the trend of surface deformation and realize early risk identification and dynamic early warning of geological safety in mining areas; based on high-precision prediction and early warning, the mining area is assisted to reasonably demarcate dangerous areas, accurately guide safety exploration, mining area planning and land reclamation, effectively avoid environmental damage and waste of resources, and ensure the ecological environment, infrastructure and personnel safety of the mining area and its surrounding areas; through the multi-line prediction and correction mechanism, it has strong robustness, can adapt to different geological conditions and dynamic changes, and improve the overall stability and reliability of the mining area geological safety monitoring and early warning system.

[0008] Further, the elevation map is obtained as follows: historical elevation data of all locations within the mining area are obtained through the national mineral resources database and the National Administration of Surveying, Mapping and Geoinformation. The historical elevation data are processed using geographic information system software, and the processing includes denoising, filling holes, and cropping the area where the mining area is located. The processed historical elevation data are converted into a contour map, and then the elevation map of the mining area is generated using the intelligent map function.

[0009] Further, the geographic information system software uses ArcGIS software.

[0010] Further, the multiple prediction lines are obtained as follows: the opposite direction of the vector formed by the target pixel point and the next navigation pixel point of the target pixel point is used as the prediction angle direction. Based on the prediction angle direction, a circular area centered on the target pixel point is evenly divided into multiple parts, and the connection line between all adjacent two parts is recorded as the prediction line.

[0011] Further, the predicted value satisfies: ; in the formula, is the navigation pixel point Based on the predicted value of the th prediction line, and are respectively the historical elevation data of the th and th pixel points on the th prediction line of the navigation pixel point , is the historical elevation data of the next pixel point on the th prediction line of the navigation pixel point , is the number of all pixel points on the th prediction line of the navigation pixel point .

[0012] The beneficial effects are as follows: By calculating the average value of the elevation differences between adjacent pixel points on the prediction line, the overall elevation change trend of the prediction line is reflected, avoiding the sensitivity of the simple average method to local outliers, and helping to more accurately simulate the continuous change of the terrain; Using the historical elevation data difference on the prediction line and the historical elevation of the next navigation pixel point, comprehensively considering the spatial correlation along the prediction line, enhancing the stability and scientificity of the prediction, and thus improving the reliability of the prediction result.

[0013] Further, the corrected elevation data satisfies: ; in the formula, is the corrected elevation data of the navigation pixel point , is the correction requirement degree of the navigation pixel point , is the preset correction threshold is the predicted elevation data of the navigation pixel point is the current navigation elevation data of the navigation pixel point is the similarity between the predicted elevation data and the most recent historical elevation data of the local sequence to which the navigation pixel point belongs is the similarity between the current navigation elevation data and the most recent historical elevation data of the local sequence to which the navigation pixel point belongs

[0014] The beneficial effects are as follows: when the correction requirement degree is lower than the threshold, the measured elevation data is directly used as the corrected elevation data to ensure data robustness; otherwise, according to the similarity weights of the predicted data and the current data with the historical data in the local sequence, the two are weighted and fused to make the correction result more reasonable and dynamically adapt to the actual observation; through the segmented correction strategy, it is possible to make differential treatments for different degrees of correction requirements, effectively cope with the complex and changeable geological environment, and reduce the negative impact of outliers on the overall system prediction; more accurate corrected elevation data can significantly improve the calculation accuracy of the subsequent subsidence coefficient, thereby enhancing the ability to identify early geological risks in the mining area and the warning effect

[0015] Further, the similarity is the normalized result of the Pearson correlation coefficient

[0016] Further, the subsidence coefficient satisfies ; in the formula is the subsidence coefficient of the navigation pixel point is the difference between the corrected elevation data of the navigation pixel point and the most recent historical elevation data is the mean value of the differences between the corrected elevation data of all navigation pixel points and the most recent historical elevation data is the mean value of the differences between the corrected elevation data of the navigation pixel point and multiple historical elevation data is function

[0017] The beneficial effects are as follows: the subsidence coefficient combines the mean value of the single-point elevation change and the elevation change of the entire navigation path, as well as the historical multiple elevation changes of this point, comprehensively reflects the relationship between local and overall terrain changes, and improves the scientificity and accuracy of subsidence risk assessment; using ​​​The function performs a non - linear mapping on the normalized difference, which can smoothly convert the elevation change difference into a risk index within the range of 0 to 1, enhancing the sensitivity and discrimination of potential collapse risks and facilitating the accurate delineation of dangerous areas. By comparing the differences between current and historical elevation data, it effectively captures the dynamic change process of surface subsidence and collapse, supporting the real - time monitoring and early warning of the geological safety situation in the mining area.

[0018] Further, the determination of the dangerous area in the mining area includes: clustering the navigation pixel points based on the collapse coefficients of all navigation pixel points to obtain two first clustering clusters, obtaining the mean value of the collapse coefficients within each first clustering cluster, and marking the pixel points within the first clustering cluster with the largest mean value of the collapse coefficients as collapse pixel points; clustering the collapse pixel points based on the spatial distances between all collapse pixel points to obtain multiple second clustering clusters, obtaining the mean value of the collapse coefficients within each second clustering cluster, and in response to the mean value of the collapse coefficients within any second clustering cluster being greater than a preset danger threshold, marking the mining area location where the second clustering cluster is located as a dangerous area; in response to the mean value of the collapse coefficients within any second clustering cluster being less than a preset mild - danger threshold, marking the mining area location where the second clustering cluster is located as a mild - danger area; otherwise, marking the mining area location where the second clustering cluster is located as a medium - danger area.

[0019] The beneficial effects are as follows: Through the two - stage clustering method, first distinguish high - collapse - risk points and then subdivide high - risk areas, which can more accurately divide the areas with different risk levels in the mining area and achieve refined identification of dangerous areas; by combining the mean value of the collapse coefficient with a preset threshold, quantify the risk levels of different areas, and provide three - level early warnings of danger, medium - danger, and mild - danger, facilitating the implementation of targeted safety management measures; clearly dividing the risk - level areas in the mining area helps mining area managers to prioritize high - risk areas, allocate resources reasonably, and improve the monitoring efficiency and management effectiveness.

[0020] In a second aspect, the present invention provides a geological safety monitoring and early warning system, adopting the following technical solution: A geological safety monitoring and early warning system includes: a processor and a memory, and the memory stores computer program instructions, which, when executed by the processor, implement the above - mentioned geological safety monitoring and early warning method.

[0021] By adopting the above - mentioned technical solution, generate a computer program for the above - mentioned geological safety monitoring and early warning method and store it in the memory to be loaded and executed by the processor, thereby manufacturing a terminal device based on the memory and the processor, which is convenient to use.

[0022] The present invention has the following technical effects: (1) It changes the way of predicting elevation data in a single direction. Based on the vector formed by the target pixel point and the next navigation pixel point, multiple prediction lines are obtained, and the predicted elevation data of the target pixel point is determined by the average value of the predicted values of the multiple prediction lines. This reduces the interference of the error of pixel points in a single direction, captures the terrain change characteristics more comprehensively, and effectively improves the accuracy of elevation data prediction.

[0023] (2) Accurate predicted elevation data enables the monitoring scheme to accurately judge the potential risk of surface collapse, realize the early identification of collapse hazards, and avoid formulating a monitoring scheme based on low-precision elevation data, thus causing misjudgment.

[0024] (3) The accurate prediction result avoids misleading the development of work such as mine area planning and land reclamation due to low-precision prediction data, reduces resource waste, reduces the risks brought to the ecological environment, infrastructure and personnel safety of the mine area and its surrounding areas, improves the effectiveness and reliability of the geological safety monitoring and early warning work in the mine area, and is conducive to the sustainable development of the mine area.

[0025] (4) Considering the complex and changeable mine area environment and the situation that data collection is prone to deviation, the present invention can effectively avoid the influence brought by data deviation through multiple processing and correction of elevation data, and still be able to provide accurate monitoring and early warning in a complex environment, with strong environmental adaptability. Description of the Drawings

[0026] Figure 1 is the flowchart of the method in an embodiment of the geological safety monitoring and early warning method of the present invention.

[0027] Figure 2 is the schematic diagram of the prediction angle direction of step S2 in an embodiment of the geological safety monitoring and early warning method of the present invention. Detailed Embodiments

[0028] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present invention.

[0029] An embodiment of the present invention discloses a geological safety monitoring and early warning method, referring to Figure 1 , including steps S1 - S6: S1: Obtain the elevation map of the mine area and the path of the current flight of the unmanned aerial vehicle used for safety exploration in the mine area, and locate the path on the elevation map.

[0030] Specifically, the acquisition method of the elevation map is: The historical elevation data of all locations in the mining area are obtained through the National Mineral Resources Database and the National Administration of Surveying, Mapping and Geoinformation. The historical elevation data are processed using geographic information system software, including denoising, filling in holes and cropping the area where the mining area is located. The processed historical elevation data are converted into contour maps, and then the elevation map of the mining area is generated using the smart map function.

[0031] Implementers can choose the correction method for scenes in contour maps that require planar correction based on specific implementation situations, for example, using high-precision control points (GCPs) to correct contour maps.

[0032] Specifically, the geographic information system software adopts ArcGIS software.

[0033] In another embodiment, the geographic information system software adopts QGIS software.

[0034] S2: Record the pixel points on the path as navigation pixel points, and obtain multiple prediction lines of the navigation pixel points.

[0035] It should be noted that when the drone uses monitoring equipment above the mining area to obtain real-time elevation data of each area it passes through, it will be affected by environmental factors, resulting in inaccurate elevation data. Therefore, it is necessary to predict the elevation data on its navigation path based on the navigation path of the drone. However, when analyzing the elevation data of the mining area corresponding to its navigation path based on the historical elevation data of the drone, if only the historical elevation data in the direction of the drone's advance is analyzed, the connection between the elevation data in the direction of advance and the elevation data in the surrounding area will be ignored, and if there is an error in the historical elevation data in the direction of advance, it will have a greater impact on the predicted value. Therefore, the pixels within a certain range around the navigation pixel point are delineated, and then multiple prediction lines are obtained to facilitate the subsequent calculation of the predicted value.

[0036] The pixel points on the path are recorded as navigation pixel points, any navigation pixel point is recorded as a target pixel point, and multiple prediction lines of the target pixel point are obtained based on a vector formed by the target pixel point and the next navigation pixel point of the target pixel point.

[0037] Specifically, the multiple prediction lines are obtained in the following manner: like Figure 2 As shown in the figure, the opposite direction of the vector formed by the target pixel point and the next navigation pixel point of the target pixel point is taken as the prediction angle direction (if the target pixel point is the last navigation pixel point, the previous navigation pixel point of the target pixel point is selected), and the circular area with the target pixel point as the center is divided into multiple parts based on the prediction angle direction, and the connecting lines of all two adjacent parts are recorded as prediction lines.

[0038] The implementer can set the evenly divided angle according to the specific implementation situation. For example, taking the predicted angle direction as the reference, rotating counterclockwise around the center of the circle, and making a division every 90° rotation, finally obtaining 4 prediction lines.

[0039] If the navigation pixel point is close to the edge position of the elevation map and cannot form a complete circle, the evenly divided angle is set according to the actual situation, and the prediction line is obtained (at least a circle, that is, a right-angled sector. At this time, a division is made every 30° rotation, and the two sides located in the right-angled sector are also used as prediction lines, finally obtaining 4 prediction lines).

[0040] S3: Obtain the predicted elevation data of the navigation pixel point.

[0041] It should be noted that based on the multi-directional elevation data in the circular range around the target pixel point, a joint evaluation is carried out, that is, the navigation pixel points on the UAV navigation path are located, and based on the change trend of the elevations corresponding to all pixel points in different directions around this navigation pixel point, the elevation data of the navigation pixel point located at the center of the circle is predicted.

[0042] According to the most recent historical elevation data of all pixel points on each prediction line of the target pixel point, determine the prediction value of the target pixel point based on each prediction line, and take the average value of the prediction values as the predicted elevation data of the target pixel point.

[0043] Specifically, the prediction value satisfies: ; In the formula, is the prediction value of the navigation pixel point based on the th prediction line, and are respectively the most recent historical elevation data of the th th pixel point and the th pixel point on the th prediction line of the navigation pixel point is the most recent historical elevation data of the next pixel point on the th prediction line of the navigation pixel point , is the navigation pixel point 's th prediction line of the number of all pixel points.

[0044] Among them, represents the The average change trend of the most recent historical elevation data of the pixel points on a prediction line. The larger this value is, the more drastic the terrain change in the direction of this prediction line is, and the larger the predicted value will be; vice versa. Represents the basic reference value for prediction. The larger this value is, the larger the predicted value will be; vice versa.

[0045] S4: Obtain the corrected elevation data of the navigation pixel points.

[0046] It should be noted that in the complex environment of the mining area, the elevation data collected by the UAV may be affected by factors such as sensor errors, terrain occlusion, and electromagnetic interference, resulting in data deviations. Relying solely on the predicted elevation data or the data collected during this navigation is difficult to accurately reflect the real terrain. Therefore, it is necessary to combine the predicted and measured data (the elevation data of this navigation) and introduce the correction requirement degree as the judgment basis to achieve the dynamic optimization of the elevation data, so as to provide more reliable data support for the geological safety of the mining area.

[0047] Take the normalized result of the difference between the predicted elevation data and the elevation data of this navigation of the target pixel point (exemplarily, standard normalization is used for normalization) as the correction requirement degree of the target pixel point; according to the magnitude of the correction requirement degree, correct the elevation data of this navigation of the target pixel point to determine the corrected elevation data of the target pixel point.

[0048] Specifically, the corrected elevation data satisfies: ; In the formula, is the corrected elevation data of the navigation pixel point , is the correction requirement degree of the navigation pixel point , is the preset correction threshold, is the predicted elevation data of the navigation pixel point , is the elevation data of this navigation of the navigation pixel point , is the similarity between the predicted elevation data and the most recent historical elevation data of the local sequence to which the navigation pixel point belongs, is the similarity between the elevation data of this navigation and the most recent historical elevation data of the local sequence to which the navigation pixel point belongs.

[0049] The implementers can set the correction threshold and the length of the local sequence according to the specific implementation situation. For example, the correction threshold is 0.6; the length of the local sequence is based on the navigation pixel point Centered around it, 25 navigation pixel points are selected on each side to form the navigation pixel points of the local sequence. If the number of navigation pixel points on either side is less than 25, it is filled from the other side so that the number of pixel points in the sequence reaches 51.

[0050] Among them, when , it indicates that the difference between the current navigation data and the predicted data is small, and the current navigation elevation data of the navigation pixel points is accurate. Therefore, directly use as the corrected elevation data without additional adjustment; when , it indicates that there are significant anomalies in the current navigation data, which may be caused by measurement errors. At this time, the data is corrected through the weighted average formula, and weights are assigned according to the similarity between the predicted data and the historical data, and the similarity between the measured data and the historical data, so as to balance the influence of the two on the final result and improve the accuracy of the corrected elevation data.

[0051] Specifically, the similarity is the normalized result of the Pearson correlation coefficient.

[0052] Among them, normalization is because the interval of the Pearson correlation coefficient is between. Therefore, add 1 to the Pearson correlation coefficient and divide by 2 to map the Pearson correlation coefficient to between.

[0053] S5: Obtain the collapse coefficient of the navigation pixel points.

[0054] It should be noted that some areas in the mining area will collapse due to loose fillers, etc. Therefore, it is necessary to calculate the collapse coefficient of the navigation pixel points in the mining area to obtain the areas about to collapse, and conduct timely early warnings, rectifications, and personnel transfers, etc. The change in elevation data of the area about to collapse on the time scale is relatively larger than that of other normal areas around. The collapse of the mining area is a long-term geological change process. The change in short-term elevation data predicted once can only reflect the change of a certain position within a short time evolution interval, and cannot reflect the complete situation of the change in elevation data of this area. Therefore, this step calculates the collapse coefficient of the navigation pixel points based on the changes in the multiple historical elevation data of the navigation pixel points.

[0055] Determine the collapse coefficient of the target pixel point according to the difference between the corrected elevation data of all navigation pixel points and the most recent historical elevation data, and the difference between the corrected elevation data of the target pixel point and the multiple historical elevation data.

[0056] Specifically, the collapse coefficient satisfies:[[]] ; In the formula, Navigation pixels The collapse coefficient, Navigation pixels The difference between the corrected elevation data and the most recent historical elevation data, is the average of the differences between the corrected elevation data of all navigation pixels and the most recent historical elevation data. Navigation pixels The average of the differences between the corrected elevation data and multiple historical elevation data, for function.

[0057] Implementers can set the number of historical elevation data based on specific implementation circumstances, for example, historical elevation data within the last 12 months.

[0058] in, Indicates navigation pixels The larger the recent elevation change amplitude is compared with the overall recent elevation change amplitude, the more likely the navigation pixel point is in the process of collapse change. The larger the size, the smaller the size; and vice versa. Indicates navigation pixels The magnitude of the recent elevation change compared to the long-term trend of the elevation change of the pixel point. The larger the value, the more recent changes deviate from the long-term trend, suggesting that there is a potential risk of collapse. The larger the value, the greater the value; vice versa. The function maps the result of the calculation to interval, smoothing the values ​​to avoid interference from extreme values. The center point of the function moves from 0.5 to 0, making It can distinguish between elevation increases (negative values) and decreases (positive values). The function of 2 is to scale the output range to , enhancing the expressiveness of abnormal changes.

[0059] S6: According to the collapse coefficient, the dangerous area of ​​the mining area is determined to achieve early warning based on geological safety monitoring.

[0060] It should be noted that the subsidence and collapse of the mining area often appear in blocky form in the plane space, that is, the possible collapse area may sink higher than the surrounding normal area. Therefore, the navigation pixels with drastic changes in elevation data are not scattered, but appear in a clustered form in the local area on the elevation map, and the collapse coefficients of these navigation pixels are relatively close. Therefore, this step locates the area of ​​the mining area that is about to collapse according to the spatial distribution of the collapse coefficients of the navigation pixels.

[0061] Specifically, the determination of the dangerous area in the mining area includes: Based on the collapse coefficients of all navigation pixel points, the navigation pixel points are clustered to obtain two first clustering clusters. The mean value of the collapse coefficients within each first clustering cluster is obtained, and the pixel points within the first clustering cluster with the largest mean value of the collapse coefficients are denoted as collapse pixel points; Based on the spatial distances between all collapse pixel points, the collapse pixel points are clustered to obtain multiple second clustering clusters. The mean value of the collapse coefficients within each second clustering cluster is obtained. In response to the mean value of the collapse coefficients within any second clustering cluster being greater than a preset danger threshold, the mining area location where the second clustering cluster is located is denoted as a dangerous area; in response to the mean value of the collapse coefficients within any second clustering cluster being less than a preset mild danger threshold, the mining area location where the second clustering cluster is located is denoted as a mild danger area; otherwise, the mining area location where the second clustering cluster is located is denoted as a moderate danger area.

[0062] Implementers can set the number of second clustering clusters, the danger threshold, and the mild danger threshold according to the specific implementation situation. For example, the number of second clustering clusters is 5, the danger threshold is 0.8, and the mild danger threshold is 0.4.

[0063] An embodiment of the present invention also discloses a geological safety monitoring and early warning system, including a processor and a memory. The memory stores computer program instructions, and when the computer program instructions are executed by the processor, a geological safety monitoring and early warning method according to the present invention is implemented.

[0064] The above system also includes other components well-known to those skilled in the art such as a communication bus and a communication interface. Their settings and functions are known in the art, so they will not be described in detail here.

[0065] The above are all preferred embodiments of the present invention. The protection scope of the present invention is not limited by this. Therefore, all equivalent changes made according to the structure, shape, and principle of the present invention should be covered within the protection scope of the present invention.

Claims

1. A geological safety monitoring and early warning method, characterized in that, Including: Obtain the elevation map of the mining area and the path of the current flight of the drone for performing safety exploration in the mining area, and locate the path on the elevation map; Mark the pixel points on the path as navigation pixel points, mark any navigation pixel point as a target pixel point, based on the vector formed by the target pixel point and the next navigation pixel point of the target pixel point, obtain multiple prediction lines of the target pixel point, and determine the prediction value of the target pixel point based on each prediction line according to the most recent historical elevation data of all pixel points on each prediction line of the target pixel point, and take the mean value of the prediction values as the predicted elevation data of the target pixel point; Take the normalized result of the difference between the predicted elevation data and the current flight elevation data of the target pixel point as the correction requirement degree of the target pixel point; Correct the current flight elevation data of the target pixel point according to the magnitude of the correction requirement degree to determine the corrected elevation data of the target pixel point; Determine the subsidence coefficient of the target pixel point according to the difference between the corrected elevation data of all navigation pixel points and the most recent historical elevation data, and the difference between the corrected elevation data of the target pixel point and multiple historical elevation data; Determine the dangerous area of the mining area according to the subsidence coefficient to achieve geological safety monitoring and early warning.

2. The geological safety monitoring and early warning method according to claim 1, characterized in that The acquisition method of the elevation map is: Collect the historical elevation data of all locations in the mining area through the national mineral resources database and the National Administration of Surveying, Mapping and Geoinformation, and use geographic information system software to process the historical elevation data. The processing includes denoising, filling holes, and cropping the area where the mining area is located. Convert the processed historical elevation data into a contour map, and then use the intelligent map function to generate the elevation map of the mining area.

3. The method for geological safety monitoring and early warning according to claim 2, characterized in that, The geographic information system software uses ArcGIS software.

4. The geological safety monitoring and early warning method according to claim 1, characterized in that, The acquisition method of the multiple prediction lines is: Take the opposite direction of the vector formed by the target pixel point and the next navigation pixel point of the target pixel point as the prediction angle direction. Based on the prediction angle direction, divide the circular area centered on the target pixel point into multiple parts, and mark the connection line between all adjacent two parts as the prediction line.

5. The geological safety monitoring and early warning method according to claim 1, characterized in that The prediction value satisfies: ； Wherein, is the navigation pixel point is the predicted value based on the th prediction line, and are respectively the th th pixel point and the th pixel point on the th prediction line of the navigation pixel point is the most recent historical elevation data of the next pixel point of the navigation pixel point on the th prediction line, is the number of all pixel points on the th prediction line of the navigation pixel point.

6. The geological safety monitoring and early warning method according to claim 1, characterized in that The corrected elevation data satisfies: ； Wherein, is the corrected elevation data of the navigation pixel point , is the correction requirement degree of the navigation pixel point , is the preset correction threshold is the predicted elevation data of the navigation pixel point , is the current navigation elevation data of the navigation pixel point , is the similarity between the predicted elevation data and the most recent historical elevation data of the local sequence to which the navigation pixel point belongs, is the similarity between the current navigation elevation data and the most recent historical elevation data of the local sequence to which the navigation pixel point belongs.

7. The geological safety monitoring and early warning method according to claim 6, wherein, The similarity is the result after normalizing the Pearson correlation coefficient.

8. A geological safety monitoring and early warning method according to claim 1, characterized in that The subsidence coefficient satisfies: ； In the formula, is the collapse coefficient of the navigation pixel point . is the difference between the corrected elevation data of the navigation pixel point and the most recent historical elevation data. is the mean value of the differences between the corrected elevation data of all navigation pixel points and the most recent historical elevation data. is the mean value of the differences between the corrected elevation data of the navigation pixel point and multiple historical elevation data. is function.

9. A geological safety monitoring and early warning method according to claim 1, characterized in that Determining the dangerous area of the mining area includes: Based on the subsidence coefficients of all navigation pixel points, cluster the navigation pixel points to obtain two first clustering clusters, obtain the mean value of the subsidence coefficients within each first clustering cluster, and mark the pixel points within the first clustering cluster with the largest mean value of the subsidence coefficients as subsidence pixel points; based on the spatial distances between all subsidence pixel points, cluster the subsidence pixel points to obtain multiple second clustering clusters, obtain the mean value of the subsidence coefficients within each second clustering cluster, and in response to the mean value of the subsidence coefficients within any second clustering cluster being greater than the preset dangerous threshold, mark the location of the mining area where the second clustering cluster is located as the dangerous area; in response to the mean value of the subsidence coefficients within any second clustering cluster being less than the preset mild danger threshold, mark the location of the mining area where the second clustering cluster is located as the mild danger area; otherwise, mark the location of the mining area where the second clustering cluster is located as the moderate danger area.

10. A geological safety monitoring and early warning system, characterized in that, Comprising: A processor and a memory, the memory storing computer program instructions which, when executed by the processor, implement a geological safety monitoring and early warning method according to any one of claims 1-9.

Images