Mining spraying dust fall control method and system based on image recognition

Abstract

The invention relates to the technical field of dust fall control, in particular to a mining spray dust fall control method and system based on image recognition, and the method comprises the steps: determining a corresponding simulation mining area model based on the mining area parameters of a to-be-controlled mining area when an actual dust diffusion diagram contains a shadow region; based on the construction parameters of the to-be-controlled mining area and the simulated mining area model, a simulated dust diffusion diagram corresponding to the to-be-controlled mining area is obtained; determining a target dust diffusion diagram based on the actual dust diffusion diagram and the simulated dust diffusion diagram; edge detection and granularity analysis are carried out on the target dust diffusion diagram, and dust information corresponding to the to-be-controlled mining area is determined from the target dust diffusion diagram; and generating a spraying regulation instruction based on the dust information, wherein the spraying regulation instruction is used for controlling the spraying equipment to perform dust falling operation based on the spraying regulation instruction. The accuracy of a dust detection result is conveniently improved, so that the dust falling effect is improved.

Description

Technical Field

[0001] The present application relates to the technical field of dust reduction control, and in particular to a mining spray dust reduction control method and control system based on image recognition. Background Art

[0002] Mining operations usually involve large-scale excavation, crushing, transportation and other processes, which will generate a lot of dust. In the mining environment, dust not only comes from the mining and processing of raw materials such as coal and ore, but also may be caused by wear and vibration during the operation of machinery and equipment. If the generated dust is not treated, it will not only affect the physical and mental health of the relevant operators, but may also lead to the decline of mining equipment performance and environmental pollution. Therefore, dust control is a long-term and complex challenge in the mining environment.

[0003] In traditional dust reduction methods, the dust situation under the mine is generally detected and evaluated through images, and then ventilation equipment or spray equipment is used to reduce dust based on the detection results. Although the dust concentration can be reduced to a certain extent, due to the complexity of the underground environment, the accuracy of the detection results is low when only the image detection method is used to identify the distribution of dust under the mine. Therefore, when using such low-accuracy detection results as the basis for spray dust reduction control, the accuracy of the spray dust reduction strategy may be reduced, which may affect the dust reduction effect. Summary of the invention

[0004] In order to improve the accuracy of dust detection results and thus improve the dust reduction effect, the present application provides a mining spray dust reduction control method and control system based on image recognition.

[0005] In the first aspect, the present application provides a method for controlling dust suppression by spraying in a mine based on image recognition, which adopts the following technical solution: A mine spray dust control method based on image recognition, comprising: Acquire an actual mining area image, and determine an actual dust diffusion map corresponding to the mining area to be controlled based on the actual mining area image; When the actual dust diffusion map contains a shaded area, a corresponding simulated mining area model is determined based on the mining area parameters of the mining area to be controlled, and a simulated dust diffusion map corresponding to the mining area to be controlled is obtained based on the construction parameters of the mining area to be controlled and the simulated mining area model, wherein the construction parameters include the construction amount, the construction area and the environmental parameters, and the environmental parameters include wind speed and humidity; Determining a target dust diffusion map based on the actual dust diffusion map and the simulated dust diffusion map; Performing edge detection and particle size analysis on the target dust diffusion map, and determining dust information corresponding to the mine area to be controlled from the target dust diffusion map, wherein the dust information includes dust area size and dust concentration; A spray control instruction is generated based on the dust information, and the spray control instruction is used to control the spray equipment to perform dust reduction operations based on the spray control instruction. The spray control instruction includes a spray amount and a spray posture.

[0006] By adopting the above technical scheme, when the actual mining area image contains a shadow area, firstly, a simulated dust diffusion map can be obtained by constructing a simulated mining area model and combining the construction parameters, so as to simulate and predict the mining conditions under the mine, thereby facilitating the understanding of the dust distribution under the mine. However, since the simulation result is relatively ideal, the actual dust diffusion map and the simulated dust diffusion map are fused, and the dust information is identified based on the fusion result, rather than directly using the simulated dust diffusion map to identify the dust information. This is convenient for clearly understanding the dust distribution under the mine while improving the adaptability between the detection results and the actual situation, thereby facilitating the improvement of the accuracy of the detection results. Finally, the spray control instructions generated based on the dust information with higher accuracy are convenient for improving the control of the spray amount and spray posture of the spray equipment, thereby facilitating the accuracy and effectiveness of the spray dust reduction, and further facilitating the improvement of the dust reduction effect.

[0007] In a possible implementation, determining a target dust diffusion map based on the actual dust diffusion map and the simulated dust diffusion map includes: Identifying at least one non-shadow region included in the actual dust diffusion map, and identifying a region edge line corresponding to each non-shadow region; Merging the region edge line of the at least one non-shadow region to obtain a stitched edge line; Identify a simulated edge line corresponding to the simulated dust diffusion map, and if the edge line matching degree between the simulated edge line and the spliced ​​edge line is higher than a preset standard matching degree, determine a diffusion map of the area to be superimposed based on the shadow area and the simulated dust diffusion map; The actual dust diffusion map including the shadow area is supplemented according to the diffusion map of the area to be superimposed to obtain the target dust diffusion map.

[0008] By adopting the above technical scheme, by matching the spliced ​​edge line and the simulated edge line, it is convenient to verify the simulation prediction results. When the edge line matching degree is higher than the preset standard matching degree, it indicates that the simulation data and the actual data have a high consistency in the key feature of the edge line, and also indicates that the adaptation degree between the simulation prediction results and the actual situation is high. In the actual dust diffusion map, the shadow area may cause the dust information to be missing or distorted. By identifying the part of the simulated dust diffusion map that matches the actual dust diffusion map and using the simulated data to complete the shadow area, it is convenient to improve the dust distribution of the entire mining area, making the target dust diffusion map more comprehensive and accurate.

[0009] In a possible implementation, when the number of the spray devices is higher than a preset number of devices, the method further includes: Obtain the dust fall rate of the spray range corresponding to each spray device, and determine the spray range with a dust fall rate lower than the preset standard dust fall rate as the focus range; Determining the predicted dust volume of the concerned area based on the regional construction parameters and historical construction data corresponding to the concerned area; When the predicted dust amount is higher than a preset dust amount, identifying the location information of the focus range, and generating a moving route based on the location information; acquiring a spray control instruction corresponding to the focus range, and determining a mobile spray control instruction based on the predicted dust amount and the predicted dust amount; Based on the moving route and the spray control instruction, a moving control instruction is determined, and the moving control instruction is used to control the drone spray equipment to perform mobile dust reduction processing on the focus range according to the generated moving route.

[0010] By adopting the above technical solution, by monitoring the dust reduction rate of the corresponding spray range of each spray equipment and setting a preset standard dust reduction rate, it is easy to accurately identify the focus range where the dust reduction effect is not ideal, which helps to concentrate limited mobile spray resources on areas that most need dust reduction, thereby facilitating the improvement of dust reduction efficiency. In addition, by coordinating the use of drone spray equipment, combining the generated moving route and spray control instructions to perform mobile dust reduction operations, it is easy to realize intelligent mobile dust reduction processing while improving the accuracy of dust reduction operations.

[0011] In one possible implementation, the method further includes: Based on the regional construction parameters and historical construction data corresponding to each spray range, determine the regional dust prediction amount corresponding to each spray range in a preset time period; Obtaining range parameters corresponding to each spray range in the preset time period, wherein the range parameters include temperature and wind speed; Determine the adjusted spray volume corresponding to each spray device based on the predicted dust volume in each area, the range parameter and the simulated mining area model; The spray control instructions corresponding to each spray device in the preset time period are optimized based on each adjusted spray quantity.

[0012] By adopting the above technical solution, by combining the regional construction parameters and historical construction data corresponding to each spray range, it is convenient to more accurately predict the dust amount in each area within the preset time period, and then based on these predicted data, it is convenient to more accurately adjust the spray amount of the spray equipment, so as to more effectively control the dust. Optimizing the spray control instructions can ensure that there is enough spray volume to control the dust when needed, and reduce the spray volume when it is not necessary, thereby avoiding unnecessary interference with the construction progress and improving construction efficiency.

[0013] In one possible implementation, the method further includes: Identifying and marking each spray range from the actual mining area image to obtain a range marking image; Determine the dust change information corresponding to each spray range according to the predicted amount of regional dust corresponding to each spray range in the preset time period; Each dust change information is superimposed on the corresponding position in the range-marked image to obtain a dust transformation map, and the dust change map is fed back.

[0014] By adopting the above technical solution, by identifying and marking the spray range of the mining area, the coverage area of ​​the dust reduction operation can be clearly defined, which is convenient for subsequent analysis and management. The dust change information corresponding to each spray range is superimposed on the range annotation image to create a dust transformation map, which is convenient for providing relevant inspection personnel with an intuitive environmental status display effect. In addition, based on the dust transformation map, it is convenient for relevant inspection personnel to adjust the spray strategy in time and optimize the dust reduction effect.

[0015] In a possible implementation, superimposing each dust change information to a corresponding position in the range-marked image includes: identifying dust features corresponding to each spray range from the actual mining area image; Determine a dust change cloud map corresponding to each spray range in the preset time period according to the regional dust prediction amount and the corresponding dust characteristics corresponding to each spray range, wherein the dust change cloud map includes dust particles and cloud map colors, wherein the dust particles correspond to the dust characteristics, and the cloud map colors correspond to the regional dust prediction amount; Each dust change cloud map is superimposed on a corresponding position in the range-marked image.

[0016] By adopting the above technical solution, by converting the regional dust prediction amount and dust characteristics into the form of a dust cloud map, relevant inspection personnel can intuitively view the changes in dust within a preset time period. In addition, by matching dust particles with dust characteristics and the color of the cloud map with the predicted dust amount, it is convenient to clearly display the dust changes within different spray ranges, which is convenient for relevant inspection personnel to dynamically monitor. The visualized dust changes help relevant inspection personnel to give early warning of high dust risk areas, thereby ensuring the health and safety of relevant workers.

[0017] In a second aspect, the present application provides an electronic device, which adopts the following technical solution: A control system, the control system comprising: at least one processor; Memory; At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the above-mentioned mine spray dust reduction control method based on image recognition.

[0018] In a third aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium includes: a computer program that can be loaded by a processor and execute the above-mentioned mining spray dust reduction control method based on image recognition.

[0019] In a fourth aspect, the present application provides a computer program product, which adopts the following technical solution: A computer program product includes a computer program, and when the computer program is executed by a processor, the above-mentioned mining spray dust reduction control method based on image recognition is implemented.

[0020] In summary, the present application includes at least one of the following beneficial technical effects: When the actual mining area image contains shadow areas, we can first construct a simulated mining area model and combine it with construction parameters to obtain a simulated dust diffusion map, which can simulate and predict the mining conditions under the mine, so as to facilitate understanding of the dust distribution under the mine. However, since the simulation results are relatively ideal, the actual dust diffusion map and the simulated dust diffusion map are fused, and the dust information is identified based on the fusion results, rather than directly using the simulated dust diffusion map to identify the dust information. This is convenient for clearly understanding the dust distribution under the mine while improving the fit between the detection results and the actual situation, thereby facilitating improving the accuracy of the detection results. Finally, the spray control instructions generated based on the dust information with higher accuracy are convenient for improving the control of the spray amount and spray posture of the spray equipment, thereby ensuring the accuracy and effectiveness of spray dust reduction, and then facilitating improving the dust reduction effect.

[0021] By converting the predicted regional dust amount and dust characteristics into the form of a dust cloud map, relevant inspection personnel can intuitively view the changes in dust within a preset time period. In addition, by matching dust particles with dust characteristics and the color of the cloud map with the predicted dust amount, it is easy to clearly display the dust changes within different spray ranges, which is convenient for relevant inspection personnel to dynamically monitor. The visualized dust changes help relevant inspection personnel to give early warning of high dust risk areas, thereby ensuring the health and safety of relevant workers. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 It is a flow chart of a method for controlling dust suppression by spraying in a mine based on image recognition in an embodiment of the present application; Figure 2 is a schematic diagram of a shaded area in an embodiment of the present application; Figure 3 is a schematic diagram of a spliced ​​edge line in an embodiment of the present application; Figure 4 It is a schematic diagram of a process for determining a dust change diagram in an embodiment of the present application; Figure 5 It is a structural schematic diagram of a control system in an embodiment of the present application. DETAILED DESCRIPTION

[0023] The following is combined with Figure 1-5 This application is described in further detail.

[0024] After reading this specification, those skilled in the art may make non-creative modifications to this embodiment as needed, but such modifications are protected by patent law as long as they are within the scope of the claims of this application.

[0025] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0026] It should be noted that in the optional embodiments of the present application, the object information and other related data involved, when the embodiments in the present application are applied to specific products or technologies, need to obtain the permission or consent of the object, and the collection, use and processing of the relevant data need to comply with the relevant laws, regulations and standards of the relevant countries and regions. In other words, if the embodiments of the present application involve data related to the object, it needs to be obtained with the authorization and consent of the object, the authorization and consent of the relevant departments, and in compliance with the relevant laws, regulations and standards of the country and region. If personal information is involved in the embodiments, the acquisition of all personal information needs to obtain the consent of the individual. If sensitive information is involved, the separate consent of the information subject needs to be obtained. The embodiments also need to be implemented with the authorization and consent of the object.

[0027] Specifically, the embodiment of the present application provides a method for controlling dust suppression by spraying in a mine based on image recognition, which is executed by a control system, and the control system can be a server or a terminal device, wherein the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited thereto. The terminal device and the server can be directly or indirectly connected via wired or wireless communication, and the embodiment of the present application does not limit this.

[0028] refer to Figure 1 , Figure 1 : is a flow chart of a method for controlling dust suppression by spraying in a mine based on image recognition in an embodiment of the present application, the method comprising steps S110 to S150, wherein: Step S110: Acquire an actual mining area image, and determine an actual dust diffusion map corresponding to the mining area to be controlled based on the actual mining area image.

[0029] Specifically, the actual mining area image can be collected by an image acquisition device set in the mining area to be controlled and uploaded to the control system, wherein the mining area to be controlled is a mining area that needs to be sprayed for dust reduction control. The actual dust diffusion map is the actual diffusion form of dust in the actual mining area image. When determining the actual dust diffusion map from the actual mining area image, the actual mining area image can be preprocessed first to better highlight the diffusion form of dust, wherein the preprocessing operation includes denoising, contrast enhancement, brightness adjustment, etc. The specific content of the preprocessing operation is not specifically limited in the embodiment of this application, and can be limited by relevant technical personnel. Feature detection is performed on the image after the preprocessing operation. Specifically, a scale-invariant feature transformation algorithm or an accelerated robust feature algorithm can be used to detect dust particles in the actual mining area image after the preprocessing operation. The specific feature detection algorithm is not specifically limited in the embodiment of this application, as long as feature detection can be performed. Finally, image segmentation technology can be applied to identify and segment the dust area from the actual mining area image to obtain the actual dust diffusion map. The actual dust diffusion map can intuitively view the dust diffusion state corresponding to the mining area to be controlled.

[0030] Step S120: When the actual dust diffusion map contains a shaded area, the corresponding simulated mining area model is determined based on the mining area parameters of the mining area to be controlled, and based on the construction parameters of the mining area to be controlled and the simulated mining area model, a simulated dust diffusion map corresponding to the mining area to be controlled is obtained, wherein the construction parameters include the construction volume, construction area and environmental parameters, and the environmental parameters include wind speed and humidity.

[0031] Specifically, since the location of the mining area is generally underground, as the depth of the mining area increases, natural light cannot penetrate the surface, which may cause dim light in the mining area. The light may be blocked by mining equipment or mining walls, etc., which may cause shadow areas to appear in the actual dust diffusion image. Shadows are formed when the light is blocked by objects, resulting in some parts without direct light. When judging whether the actual dust diffusion image contains a shadow area, a color analysis method can be used for judgment. Among them, since the shadow area usually has a certain difference in color from other non-shadow areas, for example, the color may be darker or different in tone compared with the non-shadow area, it is possible to judge whether the actual dust diffusion image contains a shadow area by identifying and comparing the color values ​​corresponding to each pixel point. The method for judging whether the actual dust diffusion image contains a shadow area can also be through edge detection, image segmentation, optical flow analysis, etc. The specific method is not specifically limited in the embodiments of this application, as long as it can identify and judge whether the actual dust diffusion image contains a shadow area.

[0032] The mining area parameters include the mining area location, mining type and mining area scale, etc. Based on the mining area parameters, the accuracy of determining the simulated mining area model corresponding to the mining area to be controlled can be improved. Different mining area parameters correspond to different simulated mining area models. There is a corresponding relationship between the mining area parameters and the simulated mining area models. Based on the corresponding relationship, the simulated mining area model corresponding to any mining area parameter can be determined. The specific content of the corresponding relationship is not specifically limited in the embodiment of the present application, and can be determined by relevant technical personnel based on historical experimental data and uploaded to the control system.

[0033] The construction parameters include construction volume, construction area and environmental parameters. The environmental parameters include wind speed and humidity. The construction area is a mining area in the mine area to be controlled, and the construction volume is the amount of minerals that need to be mined. When the mineral is coal, the construction volume is the amount of coal that needs to be mined. Since the wind speed in the surrounding environment is the main force driving the movement of dust, the greater the wind speed, the greater the aerodynamic force on the dust generated by the mining operation, and the diffusion range and speed will also increase; air humidity also has a significant effect on the cohesion and suspension ability of dust. The increase in humidity in the surrounding environment may cause dust particles to absorb water, increase their weight, and thus reduce their suspension time in the air. Therefore, in order to better simulate the diffusion of dust, it is necessary to consider the wind speed and humidity in the surrounding environment during the simulation process. Environmental parameters can also include temperature. The specific environmental parameters are not specifically limited in the embodiments of this application and can be set by relevant technical personnel according to actual needs.

[0034] When simulating dust diffusion based on the construction parameters of the mine area to be controlled and the simulated mine area model, the simulated mine area model can be set according to the mine area parameters first, and then the construction parameters can be input as simulation conditions into the simulated mine area model to simulate dust behavior. During the simulation process, the simulated mine area model will predict and calculate the movement trajectory of dust under the corresponding construction parameters, and finally display the spatial distribution of dust through a simulated dust diffusion map.

[0035] Step S130: determining a target dust diffusion map based on the actual dust diffusion map and the simulated dust diffusion map.

[0036] Specifically, since the simulated dust diffusion map mainly simulates and restores the distribution of dust in the air, rather than the lighting effect in the physical space, there is generally no shadow area in the simulated dust diffusion map obtained by simulation prediction. Therefore, the distribution of dust corresponding to the shadow area in the actual dust diffusion map can be understood based on the simulated dust diffusion map. Furthermore, in order to make the target dust diffusion map more comprehensive and accurate, the target dust diffusion map is determined based on the actual dust diffusion map and the simulated dust diffusion map, which may specifically include: Identify at least one non-shadow area contained in the actual dust diffusion map, and identify the regional edge line corresponding to each non-shadow area; fuse the regional edge lines of at least one non-shadow area to obtain a stitched edge line; identify the simulated edge line corresponding to the simulated dust diffusion map, if the edge line matching degree between the simulated edge line and the stitched edge line is higher than the preset standard matching degree, then determine the diffusion map of the area to be superimposed based on the shadow area and the simulated dust diffusion map; complement the actual dust diffusion map containing the shadow area according to the diffusion map of the area to be superimposed, and obtain the target dust diffusion map.

[0037] Specifically, when the actual dust diffusion map contains a shadow area, the shadow area may divide the actual dust diffusion map into multiple non-shadow areas. Therefore, when the actual dust diffusion map contains a shadow area, it will correspondingly contain at least one non-shadow area, and at least one non-shadow area and the shadow area constitute the entire actual dust diffusion map.

[0038] When determining the regional edge line of each shadow area, the Canny edge detection, Sobel operator or Hough transform can be used for identification. Since different light and different image shooting angles will cause the shadow area in the actual dust diffusion image to change, at least one non-shadow area in different actual dust diffusion images is not fixed, and the regional edge line corresponding to each non-shadow area is also different, such as Figure 2 As shown, Figure 2 There are three non-shadow areas, and the area edge lines of the three non-shadow areas are represented by dotted lines. When fusing the area edge line of at least one non-shadow area, the following steps can be used: Step 1: Edge recognition: based on the region edge line of each non-shadow region, locate the boundary of each non-shadow region; Step 2: Image segmentation, ensuring that each non-shadow area is completely cut out from the actual dust diffusion image. In this process, threshold processing or the use of color space may be required to distinguish between shadow areas and non-shadow areas; Step 3: Edge matching, determining the adjacent areas of the adjacent non-shadow areas, and then determining the adjacent edge lines of the adjacent areas based on the area edge lines of the adjacent areas. This process can be achieved by comparing the coordinates of the area edge points of the two shadow areas; Step 4: Edge fusion: After determining the adjacent edge lines between adjacent regions, the adjacent edge lines can be merged to eliminate gaps or overlaps and ensure the continuity of the regional edge lines between adjacent regions. In this process, image pixel operations such as closing operations can be used to fill small holes or connect disconnected edges. The specific method is not specifically limited in the embodiments of the present application. Step 5: Result integration: integrate all fused edges into a single, continuous boundary to form a large area range and obtain the stitched edge line, such as Figure 3 shown.

[0039] Before using the simulated dust diffusion map to complete the actual dust diffusion map, the accuracy of the simulated dust diffusion map can be verified by matching the edge lines. When the matching degree between the simulated edge line and the spliced ​​edge line is higher than the preset standard matching degree, it indicates that the adaptability between the simulated dust diffusion map and the actual dust diffusion map is high, and image fusion or superposition can be performed; when the matching degree between the simulated edge line and the spliced ​​edge line is not higher than the preset standard matching degree, it indicates that the adaptability between the simulated dust diffusion map and the actual dust diffusion map is low. In order to improve the accuracy of the target dust diffusion map, and thus improve the accuracy in the dust reduction control process, a simulated dust diffusion map can be regenerated from the simulated mining area model, and then image fusion or superposition can be performed based on the new simulated dust diffusion map. Among them, the preset standard matching degree can be 89% or 95%. The specific value is not specifically limited in the embodiment of this application and can be set by relevant technical personnel.

[0040] When the edge line matching degree between the simulated edge line and the stitched edge line is higher than the preset standard matching degree, the representation can be image fusion or superposition. The specific steps can be to locate the position of the shadow area from the simulated dust diffusion map, and then perform a cutout process on the image corresponding to the shadow area from the simulated dust diffusion map to obtain a diffusion map of the area to be superimposed, and cover the diffusion map of the area to be superimposed on the shadow area of ​​the actual dust diffusion map to obtain the target dust diffusion map. In addition to superimposing images, the target dust diffusion map can also be obtained through image fusion technology. The specific method of obtaining the target dust diffusion map is not specifically limited in the embodiment of the present application. By identifying the portion of the simulated dust diffusion map that matches the actual dust diffusion map and using simulated data to complete the shadow area, it is convenient to improve the dust distribution of the entire mining area.

[0041] Step S140: performing edge detection and particle size analysis on the target dust diffusion map, and determining dust information corresponding to the mining area to be controlled from the target dust diffusion map, the dust information including dust area size and dust concentration.

[0042] Specifically, edge detection is performed on the target dust diffusion map to facilitate determination of the dust area size in the target dust diffusion map, and particle size analysis is performed on the target dust diffusion map to facilitate determination of the dust concentration. When determining the dust area size, the target edge line corresponding to the target dust diffusion map can be identified, and after determining the target edge line, the area of ​​the circumscribed rectangle corresponding to the target edge line can be calculated, or the number of pixels within the target edge line can be directly calculated, and then the dust area size of the single pixel area is obtained by multiplying the number of pixels by the dust area size. The method of obtaining the dust area size is not specifically limited in the embodiments of the present application and can be set by relevant technical personnel.

[0043] When performing particle size analysis on the target dust diffusion map, it can be estimated based on the grayscale value. Since the grayscale value of the dust area is related to the dust concentration, the average grayscale value or grayscale histogram of the dust area can be counted, and the dust concentration in the target dust diffusion map can be calculated based on known historical experimental data or a preset standard curve, wherein the historical experimental data and the preset standard curve can be uploaded to the control system in advance by relevant staff. In addition, if the dust particles appear as obvious textures or spots in the target dust diffusion map, the dust concentration can be determined by counting the number, area or volume of these textures or spots, wherein texture analysis methods such as local binary pattern algorithm, grayscale co-occurrence matrix or wavelet transform can be used to extract texture features, and spot detection methods such as Otsu binarization, Canny edge detection, Blob detection or a method based on region growth can be used to identify spot features, and the specific method is not specifically limited in the embodiments of the present application.

[0044] Step S150: Generate a spray control instruction based on the dust information, the spray control instruction is used to control the spray equipment to perform dust reduction operations based on the spray control instruction, and the spray control instruction includes a spray volume and a spray posture.

[0045] Specifically, the dust information includes the dust area size and dust concentration, wherein the larger the dust area, the higher the dust concentration, and the larger the spray volume in the corresponding spray control instruction. There is a first corresponding relationship between the dust information and the spray volume, and the first corresponding relationship can be used to determine the spray volume suitable for different dust information. The specific content of the first corresponding relationship is not specifically limited in the implementation of this application. The spray posture includes the nozzle angle of the spray device. There is a second corresponding relationship between the nozzle angle and the dust area size. The second corresponding relationship includes the dust area size suitable for different nozzle angles. The specific content of the second corresponding relationship is not specifically limited in the embodiment of this application. The spray posture can also include the nozzle height. The specific content is not specifically limited in the embodiment of this application, and the relevant technical personnel can set or modify the content contained in the spray posture according to actual needs. After the spray control instruction is generated, the spray control instruction can be sent to the spray device to control the spray device to perform dust reduction operations according to the spray volume and spray posture in the spray control instruction.

[0046] For the embodiments of the present application, when the actual mining area image contains a shadow area, first, a simulated dust diffusion map can be obtained by constructing a simulated mining area model and combining the construction parameters, which can simulate and predict the mining conditions under the mine, thereby facilitating the understanding of the dust distribution conditions under the mine. However, since the simulation results are relatively ideal, the actual dust diffusion map and the simulated dust diffusion map are fused, and the dust information is identified based on the fusion result, rather than directly using the simulated dust diffusion map to identify the dust information. This is convenient for clearly understanding the dust distribution conditions under the mine while improving the adaptability between the detection results and the actual conditions, thereby facilitating the improvement of the accuracy of the detection results. Finally, the spray control instructions generated based on the dust information with higher accuracy facilitate the improvement of the spray amount and spray posture of the spray equipment, thereby facilitating the improvement of the accuracy and effectiveness of the spray dust reduction, and further facilitating the improvement of the dust reduction effect.

[0047] When the number of spray devices is higher than the preset number of devices, the method provided in the embodiment of the present application further includes: Obtain the dust reduction rate of the spray range corresponding to each spray device, and determine the spray range with a dust reduction rate lower than the preset standard dust reduction rate as the focus range; determine the predicted dust amount of the focus range based on the regional construction parameters and historical construction data corresponding to the focus range; when the predicted dust amount is higher than the preset dust amount, identify the location information of the focus range, and generate a moving route based on the location information; obtain the spray control instructions corresponding to the focus range, and determine the mobile spray control instructions based on the predicted dust amount and the predicted dust amount; determine the mobile control instructions based on the moving route and the spray control instructions, and the mobile control instructions are used to control the drone spray equipment to perform mobile dust reduction processing on the focus range according to the generated moving route.

[0048] Specifically, the number of preset devices can be 5 or 6. The specific number is not specifically limited in the embodiments of the present application and can be set by relevant technical personnel. Each spray device corresponds to a different spray range. Since the dust area size and dust concentration corresponding to different spray ranges may be different, the spray control instructions corresponding to different spray devices may also be different. Therefore, the dust reduction rates corresponding to different spray ranges are also different. When determining the dust reduction rates corresponding to different spray ranges, the particle concentration detection device set in different spray ranges can be collected and uploaded to the control system. The spray images corresponding to different spray ranges can also be determined after concentration detection. The specific determination method and the specific values ​​of the preset standard dust reduction rate are not specifically limited in the embodiments of the present application.

[0049] The dust fall rate corresponding to the concerned range is lower than the preset standard dust fall rate, wherein the number of concerned ranges may be 0, 1, or multiple. When the dust fall rate within the concerned range is low, it may cause the hidden danger of dust accumulation within the concerned range. At this time, it is necessary to predict the dust amount within the concerned range for a period of time in the future to determine whether the hidden danger of dust accumulation within the concerned range will further deteriorate. When predicting the dust amount within the concerned range for a period of time in the future, it can be determined based on the regional construction parameters and historical construction data of the concerned range, wherein the regional construction parameters of the concerned range include the range construction amount, the range construction area, and the range environmental parameters. When determining the predicted dust amount, the simulated mining area range model corresponding to the concerned range can be determined from the simulated mining area model, and the regional construction parameters are imported into the simulated mining area range model to obtain the predicted dust amount corresponding to the future period of time. The specific prediction method is not specifically limited in the embodiment of the present application. The future period of time can be 2 hours after the current moment, or 1 hour after the current moment. The specific duration is not specifically limited in the embodiment of the present application.

[0050] When the predicted dust volume is higher than the preset dust volume, the potential risk of dust accumulation in the area of ​​concern will be further aggravated. At this time, it is necessary to use drone spray equipment and spray equipment corresponding to the area of ​​concern to jointly carry out dust reduction treatment on the area of ​​concern, so as to increase the dust reduction rate corresponding to the area of ​​concern, thereby reducing the probability of dust accumulation in the area of ​​concern. By monitoring the dust reduction rate of the spray range corresponding to each spray equipment and setting a preset standard dust reduction rate, it is convenient to accurately identify the area of ​​concern where the dust reduction effect is not ideal, which helps to concentrate limited mobile spray resources on areas that need dust reduction the most, thereby improving dust reduction efficiency. In addition, by cooperating with drone spray equipment, combined with the generated mobile route and spray control instructions to perform mobile dust reduction operations, it is convenient to realize intelligent mobile dust reduction processing while improving the accuracy of dust reduction operations.

[0051] Furthermore, the method provided in the embodiment of the present application also includes: Based on the regional construction parameters and historical construction data corresponding to each spray range, determine the regional dust forecast amount corresponding to each spray range in the preset time period; obtain the range parameters corresponding to each spray range in the preset time period, the range parameters include temperature and wind speed; based on the dust forecast amount, range parameters and simulated mining area model of each region, determine the adjusted spray amount corresponding to each spray equipment; based on each adjusted spray amount, optimize the spray control instructions corresponding to each spray equipment in the preset time period.

[0052] Specifically, the method for determining the predicted amount of dust in each spray range corresponding to the area can refer to the method for determining the predicted amount of dust corresponding to the focus range in the above embodiment, which will not be repeated here. The preset time period can be 1 hour after the current moment, or 2 hours after the current moment, and the specific duration is not specifically limited in the embodiment of this application.

[0053] The range parameters corresponding to each spray range can be estimated and obtained from the real-time parameter log corresponding to each spray range. Each spray range corresponds to a real-time parameter log, which can be collected by sensors set in each spray range and uploaded to the control system. The real-time parameter log contains the temperature and wind speed corresponding to each recording moment in the historical period, wherein the interval between each recording moment can be 20 minutes or 10 minutes, and the specific interval length is not specifically limited in the embodiments of the present application. For any real-time parameter log, the temperature and wind speed can be fitted respectively to obtain the temperature fitting trend and the wind speed fitting trend, and then the range parameters are determined based on the temperature fitting trend, the wind speed fitting trend and the preset time period. The method of determining the range parameters is not specifically limited in the embodiments of the present application, as long as the range parameters corresponding to each spray range in the preset time period can be obtained.

[0054] After determining the range parameters corresponding to each spray range, the predicted spray volume corresponding to each spray device is determined based on the regional dust prediction volume, range parameters and simulated mining area model corresponding to each spray range, and then the actual spray volume corresponding to each spray device at the current moment is obtained. Finally, based on the predicted spray volume and actual spray volume corresponding to each spray range, the adjusted spray volume of each spray device in each spray range is determined. For each spray device, the actual spray volume of the spray device is adjusted to reach the predicted spray volume within a preset time period. Based on these predicted data, it is convenient to adjust the spray volume of the spray equipment more accurately, so as to control dust more effectively. Optimizing the spray control instructions can ensure that there is enough spray volume to control dust when needed, and reduce the spray volume when it is not necessary, thereby avoiding unnecessary interference with the construction progress and improving construction efficiency.

[0055] Furthermore, in order to provide an intuitive environmental status display effect to relevant detection personnel, the method provided in the embodiment of the present application further includes steps S1 to S3, such as Figure 4 As shown, where: Step S1: Identify and mark each spray range from the actual mining area image to obtain a range marking image.

[0056] Specifically, different spray ranges correspond to different range identifiers, and each spray range can be identified from the actual mining area image based on the range identifier, wherein the range identifier can be a pre-set range edge line. When marking the spray range in the actual mining area image, it can be marked by a border and text overlay. The marking method is not specifically limited in the embodiment of the present application, as long as different spray ranges can be distinguished from the range marking image.

[0057] Step S2: Determine dust change information corresponding to each spray range according to the predicted amount of regional dust corresponding to each spray range in a preset time period.

[0058] Specifically, the dust change information can be in the form of a data axis or text, which is not specifically limited in the embodiments of the present application. When the dust change information is in the form of a data axis, a data axis coordinate system can be first constructed according to the prediction time period, and then the regional dust prediction amount corresponding to each prediction moment can be imported into the data axis coordinate system to obtain the dust change information corresponding to the spray range in the preset time period. Based on the above steps, the dust change information corresponding to each spray range can be obtained.

[0059] Step S3: superimpose each dust change information to the corresponding position in the range annotation image to obtain a dust transformation map, and feed back the dust change map.

[0060] Specifically, each spray range corresponds to a dust change information. Before superposition, it is necessary to first determine the corresponding spray range from the range annotation image, and then superimpose the dust change information to the corresponding position through data superposition technology. For easy viewing, the corresponding dust change information can be displayed after detecting that the relevant visitor clicks or triggers the corresponding spray range.

[0061] When the dust change information is a change image, each dust change information is superimposed on a corresponding position in the range annotation image, which may specifically include: From the actual mining area image, the dust characteristics corresponding to each spray range are identified; according to the regional dust prediction amount and the corresponding dust characteristics corresponding to each spray range, the dust change cloud map corresponding to each spray range in the preset time period is determined, and the dust change cloud map includes dust particles and cloud map colors, wherein the dust particles correspond to the dust characteristics, and the cloud map colors correspond to the regional dust prediction amount; each dust change cloud map is superimposed on the corresponding position in the range annotation image.

[0062] Specifically, the dust feature is a particle feature. Different spray ranges can use the same preset dust feature or different dust features. When different dust features are used, it is necessary to identify the particle features of the corresponding spray range from the actual mining area image. The specific method is not specifically limited in the embodiment of this application. Using different dust features to construct dust change graphs corresponding to different spray ranges is convenient for improving the fit between the dust change graph and the actual dust distribution of the corresponding spray range, so as to facilitate further intuitive display of the new dust additions in the corresponding spray range.

[0063] For any spray range, when determining the dust change cloud map based on the dust characteristics and the regional dust prediction amount corresponding to the preset time period, the frame image and dust prediction amount corresponding to each preset moment can be determined based on the preset time period and the regional dust prediction amount, and then the dust characteristics corresponding to the dust prediction amount can be superimposed on the frame image to form a dust change frame image. According to the above steps, the dust change frame image corresponding to each preset moment can be determined, and then the multiple dust change frame images can be integrated in chronological order to obtain the dust change cloud map corresponding to the preset time period.

[0064] Among them, different dust characteristics correspond to different dust particle sizes. Different dust characteristics are distinguished by the size of dust particles, which is convenient for intuitively viewing the difference in dust within different spray ranges. There is a corresponding relationship between dust characteristics and dust particles, and the dust particles corresponding to any dust characteristic can be determined through this corresponding relationship. There is a corresponding relationship between the cloud map color and the regional dust prediction amount. The dust level can be first determined according to the regional dust prediction amount. Different dust levels correspond to different cloud map colors. For example, the cloud map color corresponding to the first dust level is green, the cloud map color corresponding to the second dust level is red, and the cloud map color corresponding to the third dust level is purple. The higher the regional dust prediction amount, the higher the corresponding dust level. The higher the dust level, the darker the corresponding cloud map color. There is a corresponding relationship between the cloud map color and the dust level, and there is also a corresponding relationship between the dust level and the regional dust prediction amount. The specific content of the above two corresponding relationships is not specifically limited in the embodiments of this application and can be set by relevant technical personnel.

[0065] After determining the dust change cloud map corresponding to each spray range, the specific implementation method of superimposing the dust change cloud map onto the range annotation image can refer to the method of superimposing each dust change information onto the corresponding position in the range annotation image in the above embodiment, which will not be described in detail here. By matching dust particles with dust characteristics, the color of the cloud map corresponds to the predicted dust amount, so as to clearly display the dust changes within different spray ranges, facilitate dynamic monitoring by relevant inspection personnel, and help relevant inspection personnel to warn of high dust risk areas in advance through visualized dust changes, thereby ensuring the health and safety of relevant operators.

[0066] In an embodiment of the present application, a control system is provided, such as Figure 5 Show, Figure 5 The control system 500 shown includes: a processor 501 and a memory 503. The processor 501 and the memory 503 are connected, such as through a bus 502. Optionally, the control system 500 may also include a transceiver 504. It should be noted that in actual applications, the transceiver 504 is not limited to one, and the structure of the control system 500 does not constitute a limitation on the embodiments of the present application.

[0067] Processor 501 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. Processor 501 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0068] The bus 502 may include a path to transmit information between the above components. The bus 502 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 502 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 The fact that only one line is used in the diagram does not mean that there is only one bus or only one type of bus.

[0069] The memory 503 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0070] The memory 503 is used to store the application code for executing the solution of the present application, and the execution is controlled by the processor 501. The processor 501 is used to execute the application code stored in the memory 503 to implement the contents shown in the above method embodiment. Figure 5 The control system shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0071] An embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer-readable storage medium is run on a computer, the computer can execute the corresponding content in the aforementioned method embodiment.

[0072] An embodiment of the present application provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the method in any of the above embodiments is implemented.

[0073] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0074] The above description is only a partial implementation method of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for controlling dust suppression by spraying in mines based on image recognition, characterized in that: include: Acquire an actual mining area image, and determine an actual dust diffusion map corresponding to the mining area to be controlled based on the actual mining area image; When the actual dust diffusion map contains a shaded area, a corresponding simulated mining area model is determined based on the mining area parameters of the mining area to be controlled, and a simulated dust diffusion map corresponding to the mining area to be controlled is obtained based on the construction parameters of the mining area to be controlled and the simulated mining area model, wherein the construction parameters include the construction amount, the construction area and the environmental parameters, and the environmental parameters include wind speed and humidity; Determining a target dust diffusion map based on the actual dust diffusion map and the simulated dust diffusion map; Performing edge detection and particle size analysis on the target dust diffusion map, and determining dust information corresponding to the mine area to be controlled from the target dust diffusion map, wherein the dust information includes dust area size and dust concentration; A spray control instruction is generated based on the dust information, and the spray control instruction is used to control the spray equipment to perform dust reduction operations based on the spray control instruction. The spray control instruction includes a spray amount and a spray posture.

2. A method for controlling dust suppression by spraying in mines based on image recognition according to claim 1, characterized in that: The step of determining a target dust diffusion map based on the actual dust diffusion map and the simulated dust diffusion map includes: Identifying at least one non-shadow region included in the actual dust diffusion map, and identifying a region edge line corresponding to each non-shadow region; Merging the region edge line of the at least one non-shadow region to obtain a stitched edge line; Identify a simulated edge line corresponding to the simulated dust diffusion map, and if the edge line matching degree between the simulated edge line and the spliced ​​edge line is higher than a preset standard matching degree, determine a diffusion map of the area to be superimposed based on the shadow area and the simulated dust diffusion map; The actual dust diffusion map including the shadow area is supplemented according to the diffusion map of the area to be superimposed to obtain the target dust diffusion map.

3. The method for controlling dust suppression by spraying in mining based on image recognition according to claim 1, characterized in that: When the number of the spray equipment is higher than the preset number of equipment, it also includes: Obtain the dust fall rate of the spray range corresponding to each spray device, and determine the spray range with a dust fall rate lower than the preset standard dust fall rate as the focus range; Determining the predicted dust volume of the concerned area based on the regional construction parameters and historical construction data corresponding to the concerned area; When the predicted dust amount is higher than a preset dust amount, identifying the location information of the focus range, and generating a moving route based on the location information; acquiring a spray control instruction corresponding to the focus range, and determining a mobile spray control instruction based on the predicted dust amount and the predicted dust amount; Based on the moving route and the spray control instruction, a moving control instruction is determined, and the moving control instruction is used to control the drone spray equipment to perform mobile dust reduction processing on the focus range according to the generated moving route.

4. A method for controlling dust suppression by spraying in mines based on image recognition according to claim 3, characterized in that: Also includes: Based on the regional construction parameters and historical construction data corresponding to each spray range, determine the regional dust prediction amount corresponding to each spray range in a preset time period; Obtaining range parameters corresponding to each spray range in the preset time period, wherein the range parameters include temperature and wind speed; Determine the adjusted spray volume corresponding to each spray device based on the predicted dust volume in each area, the range parameter and the simulated mining area model; The spray control instructions corresponding to each spray device in the preset time period are optimized based on each adjusted spray quantity.

5. A method for controlling dust suppression by spraying in mines based on image recognition according to claim 4, characterized in that: Also includes: Identifying and marking each spray range from the actual mining area image to obtain a range marking image; Determine the dust change information corresponding to each spray range according to the predicted amount of regional dust corresponding to each spray range in a preset time period; Each dust change information is superimposed on the corresponding position in the range-marked image to obtain a dust transformation map, and the dust change map is fed back.

6. A method for controlling dust suppression by spraying in mines based on image recognition according to claim 5, characterized in that: The step of superimposing each dust change information to a corresponding position in the range-marked image includes: From the actual mining area image, identifying dust features corresponding to each spray range; Determine a dust change cloud map corresponding to each spray range in the preset time period according to the regional dust prediction amount and the corresponding dust characteristics corresponding to each spray range, wherein the dust change cloud map includes dust particles and cloud map colors, wherein the dust particles correspond to the dust characteristics, and the cloud map colors correspond to the regional dust prediction amount; Each dust change cloud map is superimposed on a corresponding position in the range-marked image.

7. A control system, characterized in that: The control system includes: at least one processor; Memory; At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute a mining spray dust control method based on image recognition as described in any one of claims 1-6.

8. A computer-readable storage medium, characterized in that: include: A computer program is stored which can be loaded by a processor and executes a method for controlling spray dust reduction for mining based on image recognition as described in any one of claims 1 to 6.

9. A computer program product, characterized in that It comprises a computer program, which, when executed by a processor, implements the steps of a mining spray dust reduction control method based on image recognition as described in any one of claims 1 to 6.

Images