Open-pit coal mine dust safety monitoring and early warning method, system, equipment and storage medium

Abstract

The present invention relates to the technical field of coal mine dust monitoring and control, and specifically to a method, system, equipment and storage medium for monitoring and early warning of dust safety in open-pit coal mines. In order to solve the technical problems of low accuracy and poor effect of dust safety early warning in the prior art, the present invention first obtains the dust concentration of several monitoring points, and then selects whether to perform image combination to further analyze the dust safety situation in the coal shed based on the size comparison between the dust concentration of the monitoring point and the dust concentration threshold. In the process of performing the image combination analysis, the dust concentration value of each dust area is obtained based on the pixel information of the fisheye spliced image, and then the dust hazard value is determined. Then, based on the size comparison relationship between the dust hazard value and the dust hazard value threshold, it is decided to continue monitoring or alarm, or to further refine the dust hazard value in combination with the temperature of the monitoring point and the coal pile. The method is applied to dust safety monitoring and early warning in open-pit coal mines, with higher accuracy and better flexibility.

Description

Technical Field

[0001] The present invention relates to the technical field of coal mine dust monitoring and control, and in particular to an open-pit coal mine dust safety monitoring and early warning method, system, equipment and storage medium. Background Art

[0002] Dust in coal sheds not only reduces the lifespan of equipment but also affects the health of miners. High-concentration dust can explode when exposed to high temperatures or open flames, endangering the lives of underground workers and causing significant losses. Therefore, real-time monitoring of dust concentrations in different areas of a coal mine can help identify dangerous situations and take proactive measures to prevent explosions.

[0003] However, the space in the coal shed is usually large and the ventilation conditions are complex, and the air flow is unstable, which will lead to uneven dust distribution. It makes it difficult for the data obtained by the monitoring point to accurately represent the dust conditions in the entire coal shed, resulting in poor accuracy of the calculated safety factor and poor safety warning effect. Summary of the Invention

[0004] The purpose of the present invention is to provide an open-pit coal mine dust safety monitoring and early warning method, system, equipment and storage medium.

[0005] The technical solutions of the present invention are as follows:

[0006] A dust safety monitoring and early warning method for open-pit coal mines includes the following operations:

[0007] S1. Obtain dust concentrations at several monitoring points in a coal shed of an open-pit coal mine in real time; if the dust concentration at any monitoring point is not lower than a second dust concentration threshold, issue a dust hazard alarm; if the dust concentration at any monitoring point is between a first dust concentration threshold and a second dust concentration threshold, execute S2; if the first dust concentration threshold is lower than the second dust concentration threshold;

[0008] S2. Obtain several fisheye images of the coal shed, correct them separately, and then stitch them together to obtain an overall area map of the coal shed; obtain several dust areas based on the pixel distribution information in the overall area map of the coal shed; obtain the average dust concentration of the several dust areas based on the pixel distribution information in the several dust areas and the dust concentration at the corresponding monitoring points; obtain the hazard values of the several dust areas based on the average dust concentration of the several dust areas, as well as the dust concentration safety value and the maximum dust concentration of the corresponding areas; multiply the hazard values of the several dust areas by the corresponding area weights and then add them together to obtain the dust hazard value, and execute S3;

[0009] S3. Determine whether the dust hazard value exceeds the dust hazard value threshold; if it is between the first dust hazard value threshold and the second dust hazard value threshold, obtain the dust hazard precise value based on the dust hazard value and the temperature of the monitoring point, as well as the temperature of the coal pile in the coal shed; determine whether the dust hazard precise value exceeds the second dust hazard value threshold; if it exceeds, issue a dust hazard alarm; if it is not lower than the second dust hazard value threshold, issue a dust hazard alarm; the first dust hazard value threshold is less than the second dust hazard value threshold.

[0010] In S2, the operations for obtaining the overall area map of the coal shed are specifically as follows: based on the actual pixel coordinates and real-world coordinates of the calibration plate in the fisheye image, the intrinsic parameters and distortion coefficients are obtained; based on the intrinsic parameters and distortion coefficients, several fisheye images are corrected respectively to obtain several fisheye corrected images; the gradient eigenvector of each feature point in each fisheye corrected image is obtained, and based on the gradient eigenvector of the feature point, the matching points between adjacent fisheye corrected images are searched, and the transformation matrix is calculated; based on the transformation matrix, the adjacent fisheye corrected images are pixel-mapped and spliced to obtain the overall area map of the coal shed.

[0011] The feature point is the pixel point with the extreme value after the fisheye correction image is Gaussian blurred at different scales. The gradient feature vector is the total vector obtained by splicing the corresponding vectors of the pixel gradient direction histogram of all sub-regions in the neighborhood centered on the feature point.

[0012] The specific operation of searching for matching points between adjacent fisheye-corrected images is as follows: based on the gradient feature vector, obtain the similarity measure between the current feature point in the current fisheye-corrected image and all feature points in the next fisheye-corrected image, and use the feature point corresponding to the minimum similarity measure as the nearest neighbor feature point of the current feature point; use the feature point corresponding to the second smallest similarity measure as the second nearest neighbor feature point of the current feature point; if the ratio of the similarity measure between the current feature point and the nearest neighbor feature point and the similarity measure between the current feature point and the second nearest neighbor feature point is less than the ratio threshold, then the nearest neighbor feature point is the matching point of the current feature point; and so on, obtain the matching points corresponding to all feature points of the current fisheye-corrected image in the next fisheye-corrected image.

[0013] S1 also includes obtaining the dust concentration increase value within the historical neighborhood time at the monitoring points where the dust concentration exceeds the first dust concentration threshold; if the dust concentration increase value exceeds the dust concentration increase threshold, a dust hazard alarm is issued.

[0014] S2 also includes identifying events in the overall area map of the coal shed and assigning event hazard values. The event hazard values of all events are aggregated and calculated to obtain the total event hazard value; the total event hazard value and the dust hazard value are weighted to obtain the optimized hazard value, which is used to execute the operations in S3.

[0015] The dust concentration at the monitoring point is measured by setting a suspended laser dust sensor at the monitoring point; the temperature at the monitoring point is measured by setting a suspended temperature sensor at the monitoring point; and the coal pile temperature is measured by a fiber optic temperature sensor inserted into the coal pile.

[0016] An open-pit coal mine dust safety monitoring and early warning system is used to implement the above-mentioned open-pit coal mine dust safety monitoring and early warning method, comprising:

[0017] Laser dust sensor, used to obtain dust concentration at the monitoring point;

[0018] Fisheye camera, used to obtain fisheye images inside the coal shed;

[0019] Control module, including monitoring point dust concentration judgment module, image analysis module and dust hazard value judgment module;

[0020] The dust concentration judgment module is used to judge whether the dust concentration at several monitoring points exceeds the dust concentration threshold; if the dust concentration at any monitoring point is not lower than the second dust concentration threshold, a signal is sent to the alarm module; if the dust concentration at any monitoring point is between the first dust concentration threshold and the second dust concentration threshold, a signal is sent to the image analysis module;

[0021] The image analysis module is used to obtain several fisheye images of the coal shed, stitch them together after correction, and obtain an overall area map of the coal shed; based on the pixel distribution information in the overall area map of the coal shed, several dust areas are obtained; based on the pixel distribution information in the several dust areas and the dust concentrations at the corresponding monitoring points, the average dust concentrations of the several dust areas are obtained; based on the average dust concentrations of the several dust areas, as well as the dust concentration safety values and maximum dust concentrations of the corresponding areas, the hazard values of the several dust areas are obtained; the hazard values of the several dust areas are multiplied by the corresponding area weights and then added to obtain the dust hazard values, which are then sent to the dust hazard value judgment module;

[0022] The dust hazard value judgment module is used to judge whether the dust hazard value exceeds the dust hazard value threshold; if it is between the first dust hazard value threshold and the second dust hazard value threshold, the dust hazard precision value is obtained based on the dust hazard value and the temperature of the monitoring point, as well as the temperature of the coal pile in the coal shed; judge whether the dust hazard precision value exceeds the second dust hazard value threshold; if it exceeds, send a signal to the alarm module; if it is not lower than the second dust hazard value threshold, send a signal to the alarm module; the first dust hazard value threshold is less than the second dust hazard value threshold; the first dust concentration threshold is less than the second dust concentration threshold;

[0023] Alarm module for dust hazard alarm.

[0024] An open-pit coal mine dust safety monitoring and early warning device comprises a processor and a memory, wherein the processor implements the above-mentioned open-pit coal mine dust safety monitoring and early warning method when executing a computer program stored in the memory.

[0025] A computer-readable storage medium is used to store a computer program, wherein the computer program, when executed by a processor, implements the above-mentioned open-pit coal mine dust safety monitoring and early warning method.

[0026] The beneficial effects of the present invention are:

[0027] The open-pit coal mine dust safety monitoring and early warning method provided by the present invention first obtains the dust concentration of several monitoring points, and then chooses whether to perform image combination to further analyze the dust safety situation in the coal shed based on the comparison between the dust concentration of the monitoring point and the dust concentration threshold. In this way, on the basis of improving the accuracy of safety monitoring, resources can be reasonably allocated and computing resources and time can be reduced. In the process of performing image combination analysis, several fisheye images with a wide viewing angle range are used to form an overall area map of the coal shed to avoid blind spots. Then, based on the image pixel information, the dust concentration value of each dust area is obtained, and then the hazard value of different dust areas is obtained. The hazard values of different dust areas are weighted and summed to obtain a comprehensive dust hazard value that can more accurately reflect the safety characteristics of the coal shed. Then, based on the comparison relationship between the dust hazard value and the dust hazard value threshold, it is decided to continue monitoring or alarm, or to further refine the dust hazard value in combination with the temperature of the monitoring point and the coal pile to improve the accuracy and flexibility of dust safety monitoring. This method is used in the dust safety monitoring and early warning of coal sheds in open-pit coal mines, with higher accuracy and better flexibility. DETAILED DESCRIPTION

[0028] This embodiment provides an open-pit coal mine dust safety monitoring and early warning system for implementing an open-pit coal mine dust safety monitoring and early warning method, including:

[0029] Laser dust sensor, used to obtain the dust concentration at the monitoring point; the dust concentration at the monitoring point is measured by setting a suspended laser dust sensor at the monitoring point;

[0030] Fisheye camera, used to obtain fisheye images inside the coal shed;

[0031] The temperature sensor is used to obtain the temperature of the monitoring point; the temperature of the monitoring point is measured by setting a hanging temperature sensor at the monitoring point;

[0032] The optical fiber temperature sensor is used to obtain the temperature of the coal pile. The temperature of the coal pile is measured by the optical fiber temperature sensor inserted into the coal pile.

[0033] Control module, including monitoring point dust concentration judgment module, image analysis module and dust hazard value judgment module;

[0034] The dust concentration judgment module is used to judge whether the dust concentration at several monitoring points exceeds the dust concentration threshold; if the dust concentration at any monitoring point is not lower than the second dust concentration threshold, a signal is sent to the alarm module; if the dust concentration at any monitoring point is between the first dust concentration threshold and the second dust concentration threshold, a signal is sent to the image analysis module;

[0035] The image analysis module is used to obtain several fisheye images of the coal shed, stitch them together after correction, and obtain an overall area map of the coal shed; based on the pixel distribution information in the overall area map of the coal shed, several dust areas are obtained; based on the pixel distribution information in the several dust areas and the dust concentrations at the corresponding monitoring points, the average dust concentrations of the several dust areas are obtained; based on the average dust concentrations of the several dust areas, as well as the dust concentration safety values and maximum dust concentrations of the corresponding areas, the hazard values of the several dust areas are obtained; the hazard values of the several dust areas are multiplied by the corresponding area weights and then added to obtain the dust hazard values, which are then sent to the dust hazard value judgment module;

[0036] The dust hazard value judgment module is used to judge whether the dust hazard value exceeds the dust hazard value threshold; if it is between the first dust hazard value threshold and the second dust hazard value threshold, the dust hazard precision value is obtained based on the dust hazard value and the temperature of the monitoring point, as well as the temperature of the coal pile in the coal shed; judge whether the dust hazard precision value exceeds the second dust hazard value threshold; if it exceeds, send a signal to the alarm module; if it is not lower than the second dust hazard value threshold, send a signal to the alarm module; the first dust hazard value threshold is less than the second dust hazard value threshold; the first dust concentration threshold is less than the second dust concentration threshold;

[0037] Alarm module for dust hazard alarm.

[0038] The specific operations of the open-pit coal mine dust safety monitoring and early warning method provided in this embodiment are as follows.

[0039] S1. Obtain dust concentrations at several monitoring points in a coal shed of an open-pit coal mine in real time; if the dust concentration at any monitoring point is not lower than a second dust concentration threshold, issue a dust hazard alarm; if the dust concentration at any monitoring point is between the first dust concentration threshold and the second dust concentration threshold, execute S2.

[0040] First, the dust concentration at several monitoring points is obtained. Then, based on the comparison between the dust concentration at the monitoring points and the dust concentration threshold, it is decided whether to perform image combination to further analyze the dust safety situation in the coal shed. This can improve the accuracy of safety monitoring while rationally allocating resources and reducing computing resources and time.

[0041] Monitoring points in the coal shed of an open-pit coal mine are located at the feed and discharge ports of loading and unloading equipment, which are the main sources of dust generation; downwind of the loading and unloading area, which facilitates dust dispersion analysis; the fan inlets and outlets, which facilitates the analysis of the actual working effectiveness of ventilation equipment; the interior and outlets of ventilation ducts, which facilitates the analysis of dust transmission within the ducts; the tops and surrounding areas of coal piles, which are prone to dust generation; passageways between coal piles; personnel passageways and entrances and exits in areas with high human activity; and work platforms and operating rooms. Dust concentration (coal dust concentration) is measured at these monitoring points in the coal shed of the open-pit coal mine in real time. Dust concentration at these monitoring points is measured using suspended laser dust sensors installed at these locations.

[0042] When the dust concentration at all monitoring points does not exceed the first dust concentration threshold, it proves that the dust concentration in the coal shed is low and the coal shed is relatively safe, and the dust concentration should continue to be monitored.

[0043] If the dust concentration at any monitoring point is not lower than the second dust concentration threshold, it proves that the dust concentration at a certain monitoring point in the coal shed is too high and dangerous, and a dust hazard alarm is issued.

[0044] If the dust concentration at any monitoring point is between the first dust concentration threshold and the second dust concentration threshold, the operation of S2 needs to be executed, and a comprehensive safety analysis of all monitoring points in the coal shed is performed in combination with the image.

[0045] The first dust concentration threshold is lower than the second dust concentration threshold.

[0046] In addition, in order to further improve the accuracy of safety monitoring, S1 also includes obtaining the dust concentration increase value of the monitoring points where the dust concentration exceeds the first dust concentration threshold within the historical neighborhood time. If the dust concentration increase value exceeds the dust concentration increase threshold, it means that the dust concentration at the monitoring point at this location is rising rapidly, and it also indicates that the degree of danger is increasing, and timely measures need to be taken to control it, so a dust hazard alarm is issued.

[0047] S2. Obtain several fisheye images of the coal shed, stitch them together after correction, and obtain an overall area map of the coal shed; obtain several dust areas based on the pixel distribution information in the overall area map of the coal shed; obtain the average dust concentration of the several dust areas based on the pixel distribution information in the several dust areas and the dust concentration of the corresponding monitoring points; obtain the danger values of the several dust areas based on the average dust concentration of the several dust areas and the dust concentration safety value and the maximum dust concentration of the corresponding areas; multiply the danger values of the several dust areas by the corresponding area weights and add them together to obtain the dust danger value, and execute S3.

[0048] By using several fisheye images with a wide viewing angle, an overall area map of the coal shed is formed to avoid blind spots in the field of view. The spatial relationship between various objects and areas in the coal shed can be clearly and accurately presented. Then, based on the image pixel information, the dust occurrence area can be accurately located, and the dust concentration value of each dust area can be obtained, and then the hazard value of different dust areas can be obtained. Different weights are assigned to different dust areas according to regional differences. Finally, the hazard values of different dust areas are weighted and summed to obtain a comprehensive dust hazard value that can more accurately reflect the safety characteristics of the coal shed.

[0049] First, several fisheye cameras were set up in the coal shed to ensure that the field of view of each fisheye camera could cover a part of the coal shed area, and the fields of view of adjacent cameras had a certain overlap, which was 30% to 50% of the field of view. The fisheye cameras were used to obtain several fisheye images of the coal shed. These fisheye images were corrected and then spliced together to obtain the overall area map of the coal shed.

[0050] The specific operations for obtaining the overall area map of the coal shed are as follows: based on the actual pixel coordinates and real-world coordinates of the calibration plate in the fisheye image, the intrinsic parameters and distortion coefficients are obtained; based on the intrinsic parameters and distortion coefficients, several fisheye images are corrected respectively to obtain several fisheye corrected images; the gradient eigenvector of each feature point in each fisheye corrected image is obtained, and based on the gradient eigenvector of the feature point, the matching points between adjacent fisheye corrected images are searched and the transformation matrix is calculated; based on the transformation matrix, the adjacent fisheye corrected images are spliced by pixel mapping the overlapping parts to obtain the overall area map of the coal shed.

[0051] Among them, the feature points are the pixels of the fisheye corrected image with extreme values after Gaussian blur processing at different scales. These pixels are usually the edges of coal piles, equipment contours, bracket intersections, and other key points that can well describe the local characteristics of the image.

[0052] The gradient feature vector is the sum of the corresponding vectors of the pixel gradient directional histograms of all subregions within the neighborhood centered on the feature point. The number of subregions within the neighborhood can be set according to actual needs. The pixel gradient directional histogram is a histogram of the direction of the maximum pixel gradient change within the subregion.

[0053] The specific operation for searching for matching points between adjacent fisheye-rectified images is as follows: Based on the gradient eigenvector, a similarity measure is obtained between the current feature point in the current fisheye-rectified image and all feature points in the next fisheye-rectified image. The feature point with the minimum similarity measure is selected as the nearest neighbor of the current feature point; the feature point with the second-smallest similarity measure is selected as the next-nearest neighbor of the current feature point. If the ratio of the similarity measure between the current feature point and the nearest neighbor to the current feature point and the similarity measure between the current feature point and the next-nearest neighbor is less than a ratio threshold, the nearest neighbor is considered the matching point of the current feature point. This process is repeated to obtain the matching degree of all feature points in the current fisheye-rectified image in the next fisheye-rectified image. The similarity measure is the difference between the gradient eigenvectors of the two feature points. The current feature point and the next fisheye-rectified image are adjacent images with overlapping portions.

[0054] Then, based on the pixel distribution information in the overall coal shed area map, several dust areas are obtained. The pixel distribution information in the overall coal shed area map is analyzed by edge detection method to obtain the contour information of the dust distribution area, thereby obtaining the dust area.

[0055] Next, based on the pixel distribution information within several dust regions and the dust concentration at the corresponding monitoring points, the average dust concentration of the several dust regions is calculated. Specifically, the ratio of the dust concentration at the monitoring point to the pixel value at the monitoring point within the current dust region is multiplied by all the pixel values in the current dust region, and then divided by the total number of pixels to obtain the average dust concentration of the current dust region.

[0056] Subsequently, based on the average dust concentration of several dust areas, as well as the dust concentration safety value and maximum dust concentration of the corresponding areas, the danger values of several dust areas are obtained.

[0057] The risk value can be calculated using the following formula:

[0058] ,

[0059] r is the danger value of the current dust area, C is the average dust concentration in the current dust area, C s is the safe value of dust concentration in the current dust area, C max It is the maximum dust concentration in the current dust area.

[0060] If there is no monitoring point in the current dust area, the dust concentration mean of the dust area corresponding to the minimum difference between the pixel mean of the current dust area and the current dust area is taken as the dust concentration mean of the previous dust area.

[0061] Finally, the hazard values of several dust areas are multiplied by the corresponding area weights and then added together to obtain the dust hazard value, and S3 is executed.

[0062] To further improve the accuracy of the dust area hazard value in reflecting the safety of the coal shed, S2 also includes identifying events in the overall area map of the coal shed and assigning event hazard values. The event hazard values of all events are aggregated and calculated to obtain the total event hazard value; the total event hazard value and the dust hazard value are weighted to obtain the optimized hazard value, which is used to execute the operations in S3.

[0063] Among them, for beneficial dust elimination events in the event (such as manual use of dust removal spray cannons to remove dust, manual use of fans to reduce dust concentration, manual inspection of equipment, etc.), the corresponding event hazard value is negative, the normal event (such as people transporting coal) event hazard value is 0, and the violation event (such as personnel illegal operation (miners smoking), equipment abnormality (conveyor belt breakage), etc.) event hazard value is positive.

[0064] The above-mentioned identification of events in the overall area map of the coal shed can be achieved by training a neural network with an event data set obtained in advance, and then processing the overall area map of the coal shed with the trained neural network.

[0065] The optimization of risk value can be achieved through the following formula:

[0066] ,

[0067] R 1 To optimize the risk value, C j For the j The average dust concentration in each dust area is C j,s For the j The dust concentration safety value of each dust area is C j,max For the j The maximum dust concentration in each dust area is J is the total number of dust areas, w j For the j The regional weight of each dust area, I m For the m The event risk value of an event, M is the total number of events, λ1 and λ2 are the dust weight and event weight, respectively.

[0068] In order to further improve the accuracy of the dust zone's danger value in reflecting the safety of the coal shed, it also includes obtaining the average dust concentration of each dust zone and the dust concentration change value within the historical neighborhood time; based on the dust concentration change values of several dust zones, as well as the dust concentration change safety value and the maximum dust concentration change value of the corresponding zones, the concentration change danger values of several dust zones are obtained; the concentration change danger value is weighted with the total event danger value and the dust danger value to obtain the optimal danger value for executing the operations in S3.

[0069] The optimal risk value can be achieved through the following formula:

[0070]

[0071] R 2 is the optimal risk value, C j For the j The average dust concentration in each dust area is C j,s For the j The dust concentration safety value of each dust area is C j,max For the j The maximum dust concentration in each dust area is ΔC j For the j The dust concentration change value of each dust area, ΔC j,s For the j The dust concentration change safety value in each dust area, ΔC max is the maximum value of dust concentration, J is the total number of dust areas, w j For the j The regional weight of each dust area, I m For the m The event risk value of an event, M is the total number of events, λ1 and λ2 are the dust weight and event weight, respectively.

[0072] S3. Determine whether the dust hazard value exceeds the dust hazard value threshold; if it is between the first dust hazard value threshold and the second dust hazard value threshold, obtain the dust hazard precise value based on the dust hazard value and the temperature of the monitoring point, as well as the temperature of the coal pile in the coal shed; determine whether the dust hazard precise value exceeds the second dust hazard value threshold; if it exceeds, issue a dust hazard alarm; if it is not lower than the second dust hazard value threshold, issue a dust hazard alarm.

[0073] Based on the comparison between the dust hazard value and the dust hazard value threshold, a decision is made to continue monitoring or to issue an alarm, or to further refine the dust hazard value in combination with the temperature of the monitoring point and the coal pile to improve the accuracy and flexibility of dust safety monitoring.

[0074] First, determine whether the dust hazard value, the optimized hazard value, or the optimal hazard value exceeds the dust hazard value threshold.

[0075] If it does not exceed the first dust hazard value threshold, continue to monitor the dust concentration.

[0076] If it is not lower than the second dust hazard value threshold, a dust hazard alarm is issued; the first dust hazard value threshold is lower than the second dust hazard value threshold.

[0077] If it is between the first dust hazard value threshold and the second dust hazard value threshold, the dust hazard precise value is obtained based on the dust hazard value or the optimized hazard value or the optimal hazard value, the monitoring point temperature, and the coal pile temperature in the coal shed.

[0078] The temperature of the above monitoring points is measured by setting a hanging temperature sensor at the monitoring point in the coal shed; the temperature of the coal pile is measured by an optical fiber temperature sensor inserted into the coal pile.

[0079] The dust hazard value can be obtained by the following formula:

[0080] ,

[0081] R 3 is the dust hazard value, R 0 For dust hazard value or optimized hazard value or optimal hazard value, β 1 is the temperature coefficient of the monitoring point, T n For the n The temperature of each monitoring point, T s is the temperature safety value of the monitoring point, w n For the n The position weight of each detection point, N is the total number of monitoring points, β 2 is the coal pile temperature coefficient, T k For the k The temperature of the coal pile, T q is the safe value of coal pile temperature, w k For the kThe location weight of each coal pile, K is the total number of coal piles, λ3, λ4, and λ5 are the third weight, monitoring point temperature, and coal pile temperature weights, respectively.

[0082] This embodiment also provides an open-pit coal mine dust safety monitoring and early warning device, including a processor and a memory, wherein the processor implements the above-mentioned open-pit coal mine dust safety monitoring and early warning method when executing a computer program stored in the memory.

[0083] This embodiment further provides a computer-readable storage medium for storing a computer program, wherein the computer program, when executed by a processor, implements the above-mentioned open-pit coal mine dust safety monitoring and early warning method.

[0084] The open-pit coal mine dust safety monitoring and early warning method provided in this embodiment first obtains dust concentrations at several monitoring points, and then, based on the comparison between the dust concentration at the monitoring point and the dust concentration threshold, selects whether to perform image combination to further analyze the dust safety situation in the coal shed. This can reasonably allocate resources and reduce computing resources and time on the basis of improving the accuracy of safety monitoring. In the process of performing image combination analysis, several fisheye images with a wide viewing angle are used to form an overall area map of the coal shed to avoid blind spots. Then, based on the image pixel information, the dust concentration value of each dust area is obtained, and then the hazard value of different dust areas is obtained. The hazard values of different dust areas are weighted and summed to obtain a comprehensive dust hazard value that can more accurately reflect the safety characteristics of the coal shed. Then, based on the comparison between the dust hazard value and the dust hazard value threshold, it is decided to continue monitoring or alarm, or to further refine the dust hazard value in combination with the temperature of the monitoring point and the coal pile to improve the accuracy and flexibility of dust safety monitoring. This method is applied to dust safety monitoring and early warning in open-pit coal mines, with higher accuracy and better flexibility.

Claims

1. A dust safety monitoring and early warning method for open-pit coal mines, characterized in that: The following operations are included: S1. Real-time acquisition of dust concentration at several monitoring points in the coal shed of an open-pit coal mine; If the dust concentration at any monitoring point is not lower than the second dust concentration threshold, a dust hazard alarm is issued; If the dust concentration at any monitoring point is between the first dust concentration threshold and the second dust concentration threshold, execute S2; The first dust concentration threshold is less than the second dust concentration threshold; S2. Acquire several fisheye images of the coal shed, correct them separately, and then stitch them together to obtain an overall area map of the coal shed; Based on the pixel distribution information in the overall area map of the coal shed, several dust areas are obtained; based on the pixel distribution information in several dust areas and the dust concentrations at the corresponding monitoring points, the average dust concentrations of several dust areas are obtained; Based on the average dust concentration of several dust areas, as well as the dust concentration safety value and the maximum dust concentration of the corresponding areas, the hazard values of the several dust areas are obtained; the hazard values of the several dust areas are multiplied by the corresponding area weights and then added to obtain the dust hazard value, and S3 is executed; S3, determining whether the dust hazard value exceeds the dust hazard value threshold; If the dust hazard value is between the first dust hazard value threshold and the second dust hazard value threshold, a dust hazard precise value is obtained based on the dust hazard value, the temperature at the monitoring point, and the temperature of the coal pile in the coal shed; and it is determined whether the dust hazard precise value exceeds the second dust hazard value threshold; If exceeded, a dust hazard alarm will be issued; If it is not lower than the second dust hazard value threshold, a dust hazard alarm is issued; the first dust hazard value threshold is lower than the second dust hazard value threshold.

2. The open-pit coal mine dust safety monitoring and early warning method according to claim 1 is characterized in that: In S2, the operation of obtaining the overall area map of the coal shed is specifically as follows: Based on the actual pixel coordinates and real-world coordinates of the calibration plate in the fisheye image, intrinsic parameters and distortion coefficients are obtained; based on the intrinsic parameters and distortion coefficients, several fisheye images are corrected to obtain several fisheye-corrected images; The gradient eigenvector of each feature point in each fisheye-rectified image is obtained. Based on the gradient eigenvector of the feature point, matching points between adjacent fisheye-rectified images are searched and the transformation matrix is calculated. Based on the transformation matrix, adjacent fisheye-rectified images are pixel-mapped and spliced to obtain the overall area map of the coal shed.

3. The open-pit coal mine dust safety monitoring and early warning method according to claim 2 is characterized in that: The characteristic points are pixels with extreme values after the fisheye-corrected image is Gaussian blurred at different scales; The gradient feature vector is a total vector obtained by concatenating the corresponding vectors of the pixel gradient direction histograms of all sub-regions within a neighborhood centered on the feature point.

4. The open-pit coal mine dust safety monitoring and early warning method according to claim 2, characterized in that: The specific operation of searching for matching points between adjacent fisheye-rectified images is: Based on the gradient eigenvector, obtain the similarity measure between the current feature point in the current fisheye-rectified image and all feature points in the next fisheye-rectified image, and take the feature point corresponding to the minimum similarity measure as the nearest neighbor feature point of the current feature point; The feature point with the second smallest similarity measure is regarded as the next nearest neighbor feature point of the current feature point; if the ratio of the similarity measure between the current feature point and the nearest neighbor feature point and the similarity measure between the current feature point and the next nearest neighbor feature point is less than the ratio threshold, the nearest neighbor feature point is regarded as the matching point of the current feature point; Similarly, the matching points corresponding to all feature points of the current fisheye-rectified image in the next fisheye-rectified image are obtained.

5. The open-pit coal mine dust safety monitoring and early warning method according to claim 1 is characterized in that: Said S1 also includes obtaining the dust concentration increase value within the historical neighborhood time at the monitoring points where the dust concentration exceeds the first dust concentration threshold; if the dust concentration increase value exceeds the dust concentration increase threshold, a dust hazard alarm is issued.

6. The open-pit coal mine dust safety monitoring and early warning method according to claim 1, characterized in that: Said S2 also includes identifying events in the overall area map of the coal shed and assigning event risk values, and the event risk values of all events are aggregated and calculated to obtain a total event risk value; The total event hazard value and the dust hazard value are weighted to obtain an optimized hazard value, which is used to execute the operation in S3.

7. The open-pit coal mine dust safety monitoring and early warning method according to claim 1, characterized in that: The dust concentration at the monitoring point is measured by setting a suspended laser dust sensor at the monitoring point; the temperature at the monitoring point is measured by setting a suspended temperature sensor at the monitoring point; and the coal pile temperature is measured by a fiber optic temperature sensor inserted into the coal pile.

8. An open-pit coal mine dust safety monitoring and early warning system, used to implement the open-pit coal mine dust safety monitoring and early warning method according to claim 1, characterized in that: include: Laser dust sensor, used to obtain dust concentration at the monitoring point; Fisheye camera, used to obtain fisheye images inside the coal shed; Control module, including monitoring point dust concentration judgment module, image analysis module and dust hazard value judgment module; The dust concentration judgment module is used to judge whether the dust concentration at several monitoring points exceeds the dust concentration threshold; if the dust concentration at any monitoring point is not lower than the second dust concentration threshold, a signal is sent to the alarm module; if the dust concentration at any monitoring point is between the first dust concentration threshold and the second dust concentration threshold, a signal is sent to the image analysis module; The image analysis module is used to obtain several fisheye images of the coal shed, stitch them together after correction, and obtain an overall area map of the coal shed; based on the pixel distribution information in the overall area map of the coal shed, several dust areas are obtained; based on the pixel distribution information in the several dust areas and the dust concentrations at the corresponding monitoring points, the average dust concentrations of the several dust areas are obtained; based on the average dust concentrations of the several dust areas, as well as the dust concentration safety values and maximum dust concentrations of the corresponding areas, the hazard values of the several dust areas are obtained; the hazard values of the several dust areas are multiplied by the corresponding area weights and then added to obtain the dust hazard values, which are then sent to the dust hazard value judgment module; The dust hazard value judgment module is used to judge whether the dust hazard value exceeds the dust hazard value threshold; if it is between the first dust hazard value threshold and the second dust hazard value threshold, the dust hazard precision value is obtained based on the dust hazard value and the temperature of the monitoring point, as well as the temperature of the coal pile in the coal shed; judge whether the dust hazard precision value exceeds the second dust hazard value threshold; if it exceeds, send a signal to the alarm module; if it is not lower than the second dust hazard value threshold, send a signal to the alarm module; the first dust hazard value threshold is less than the second dust hazard value threshold; the first dust concentration threshold is less than the second dust concentration threshold; Alarm module for dust hazard alarm.

9. An open-pit coal mine dust safety monitoring and early warning device, characterized in that: The method comprises a processor and a memory, wherein when the processor executes the computer program stored in the memory, the open-pit coal mine dust safety monitoring and early warning method as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that Used to store a computer program, wherein when the computer program is executed by a processor, the open-pit coal mine dust safety monitoring and early warning method according to any one of claims 1 to 7 is implemented.

Images