A precise dust suppression system based on binocular vision using fog cannon
Through real-time monitoring of dust distribution and combining electrostatic settlement technology, the problem of inaccurate spray control of fog cannon equipment is solved, accurate and intelligent fog cannon spraying and efficient dust suppression are achieved, and energy consumption is reduced.
Patent Information
- Application Number
- CN202410121305.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-01-29
- Publication Date
- 2024-11-19
- Estimated Expiration
- 2044-01-29
AI Technical Summary
Existing fog cannon equipment is difficult to accurately control the spray direction and range, and due to inaccurate monitoring data, the dust reduction effect is poor, which increases energy consumption.
Binocular vision technology is used to monitor the dust concentration and distribution in the environment in real time, and control strategies are generated through data processing and analysis, and fog cannon equipment is intelligently regulated, and dust is treated with electrostatic sedimentation technology.
The precision and intelligence of fog cannon spraying is achieved, the dust suppression efficiency is improved, energy consumption is reduced, and dust suppression needs are adapted to the dust suppression needs in complex environments.
Smart Images

Figure CN118115440B_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of binocular vision imaging, and in particular relates to a fog cannon precise dust suppression system based on binocular vision. Background Art
[0002] Mist cannon is a common dust reduction equipment, which mainly sprays water mist into the air through high-pressure spray, so that the particles suspended in the air are dampened and settled, thereby achieving the effect of dust reduction. However, the range of the mist cannon will be affected by meteorological factors such as wind direction and wind speed, and it is difficult to accurately control the direction and range of the spray; at the same time, the dust reduction effect will be poor due to inadequate monitoring of the concentration and distribution of dust in the environment; and inaccurate monitoring data will increase the spray volume of the mist cannon, increasing energy consumption. Summary of the invention
[0003] The purpose of the present invention is to provide a fog cannon precise dust suppression system based on binocular vision, which uses a binocular camera to monitor the dust concentration and distribution in the environment in real time, and realizes precise and intelligent fog cannon spraying through data processing and analysis.
[0004] The purpose of the present invention can be achieved by the following technical solutions:
[0005] The embodiment of the present application provides a binocular vision-based fog cannon precision dust suppression system, including an environmental monitoring module, a data integration module and an intelligent control module that are sequentially communicatively connected;
[0006] The environment monitoring module is used to monitor the surrounding environment in real time, obtain the real-time distribution of dust in the environment and generate a dust distribution map;
[0007] The data integration module performs image processing and image analysis based on the dust distribution map to generate analysis results;
[0008] The intelligent control module generates a control strategy according to the analysis results and regulates the fog cannon equipment;
[0009] Wherein, the fog cannon precise dust suppression system also includes a fog cannon dust suppression device; the fog cannon dust suppression device includes a water mist generator;
[0010] In the intelligent control module, dust is treated by combining electrostatic precipitation with dust suppression by fog cannon, specifically: an electrostatic generating device is arranged around the water mist generator;
[0011] The steps include:
[0012] The electrostatic generating device generates a strong electric field in the water mist sprayed by the water mist generator to obtain charged water droplets;
[0013] Acquiring charged particles through the strong electric field;
[0014] The charged water droplets and the charged particulate matter form a charged dust-water droplet complex through electrostatic action;
[0015] The sedimentation of the dust-water droplet complex is controlled by controlling the electrostatic charge content of the strong electric field.
[0016] Preferably, the environmental monitoring module comprises a particle monitoring unit, a three-dimensional reconstruction unit and a pollution source positioning unit which are communicatively connected in sequence;
[0017] The particle monitoring unit is used to obtain the dust distribution in the environment through binocular vision and generate a dust distribution map; it is also used to obtain the concentration and density of particles in the dust, and measure the size of particles;
[0018] The three-dimensional reconstruction unit is used to perform three-dimensional model reconstruction according to the dust distribution map to generate a three-dimensional dust distribution model;
[0019] The pollution source positioning unit determines the environmental pollution source based on the dust distribution three-dimensional model and in combination with a positioning algorithm.
[0020] Preferably, reconstructing the three-dimensional model according to the dust distribution map specifically includes the following steps:
[0021] S11, selecting two two-dimensional images at different positions in the dust distribution map;
[0022] S12, registering the two two-dimensional images to obtain a registered image;
[0023] S13, converting the two-dimensional image into three-dimensional point cloud data using a three-dimensional reconstruction algorithm according to the registered image;
[0024] S14, processing the three-dimensional point cloud data to generate a point cloud data set;
[0025] S15, generating a dust distribution three-dimensional model based on the point cloud data set;
[0026] Here, steps S11 to S14 are repeatedly executed until the two selected two-dimensional images at different positions are no longer the same as the two two-dimensional images selected in the previous round.
[0027] Preferably, in the three-dimensional point cloud data of step S14, a minimum distance method is used to remove high-frequency noise points in the three-dimensional point cloud data, and its formula is expressed as:
[0028]
[0029] Among them, d i Represents the distance between two adjacent points on the point cloud;
[0030] d max Represents the maximum value of all distance values;
[0031] represents the average of all distance values;
[0032] λ represents the set length threshold;
[0033] The coordinates of two adjacent points are: i (x i ,y i , z i ) and p i+1 (x i+1 ,y i+1 , z i+1 ).
[0034] Preferably, the determination method for removing high-frequency noise points using the minimum distance method is:
[0035] Compare the distances d between adjacent points i With the length threshold λ, if d i >λ, then ignore one of the two points or take the center point to replace the two points, and judge all the points on the three-dimensional point cloud data in turn.
[0036] Preferably, X-ray imaging is also used to distinguish the particle sizes, specifically: by using an X-ray imaging device to obtain projection images or volume data of the particles, and to determine and distinguish the particle sizes.
[0037] Preferably, the particles in the dust are divided into large particles, medium particles and fine particles according to the size of the particles; wherein the diameter of the large particles is: 10μm<D1≤25μm; the diameter of the medium particles is: 2.5μm<D2≤10μm; the diameter of the fine particles is: D3≤2.5μm.
[0038] Preferably, in the data integration module, the analysis result is generated by obtaining the relationship between the extinction coefficient and the particle concentration; the extinction coefficient is used to measure the absorption and scattering ability of particles in dust to light, and its relationship expression is:
[0039] M f =174μ-26.2;
[0040] Among them, M f represents the particle concentration; μ represents the extinction coefficient.
[0041] Preferably, the extinction coefficient is expressed by atmospheric transmittance, and its expression formula is as follows:
[0042] t(x)=exp(-μ·d(x));
[0043] Where d(x) represents the propagation path of light; t(x) represents the atmospheric transmittance.
[0044] Preferably, the atmospheric transmittance is represented by a vector expression of a dust distribution model, and the vector expression is:
[0045] I(x)=J(x)t(x)+(1-t(x))A;
[0046] Where t(x) represents the atmospheric transmittance;
[0047] The dust distribution model is expressed as:
[0048] I(x,y)=J(x,y)t(x,y)+(1-t(x,y))A;
[0049] Among them, (x, y) represents the coordinates of the image in the two-dimensional plane;
[0050] I(x,y) represents the radiation intensity of the disturbed image observed by binocular vision;
[0051] t(x,y) represents the two-dimensional coordinates of the atmospheric transmittance t(x);
[0052] J(x,y) represents the radiation intensity of the undisturbed image observed by binocular vision.
[0053] The beneficial effects of the present invention are:
[0054] (1) The present invention uses binocular vision technology to monitor the dust concentration and distribution in the environment in real time, uses image processing and analysis technology to accurately analyze and process the monitored data, and then uses intelligent control algorithms to analyze the data and generate control strategies to accurately adjust the spray direction, spray volume and spray time of the fog cannon, thereby achieving accurate and intelligent fog cannon spraying; at the same time, it also effectively reduces the amount of fog cannon spray, improves dust suppression efficiency while reducing energy consumption, and can better adapt to the dust suppression needs of fog cannons in complex environments. BRIEF DESCRIPTION OF THE DRAWINGS
[0055] For better understanding and implementation, the technical solution of the present application is described in detail below with reference to the accompanying drawings.
[0056] Figure 1 A schematic structural diagram of a binocular vision-based fog cannon precision dust suppression system provided in an embodiment of the present application. DETAILED DESCRIPTION
[0057] In order to further explain the technical means and effects taken by the present invention to achieve the predetermined invention purpose, exemplary embodiments will be described in detail here, and examples thereof are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are only examples of methods and systems consistent with some aspects of the present application as detailed in the attached claims.
[0058] The terms used in this application are only for the purpose of describing specific embodiments and are not intended to limit this application. The singular forms of "a", "said" and "the" used in this application and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used in this article refers to any or all possible combinations of one or more associated listed items.
[0059] The specific implementation methods, features and effects of the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments.
[0060] See also Figure 1 , the embodiment of the present application provides a fog cannon precise dust suppression system based on binocular vision, including an environmental monitoring module, a data integration module and an intelligent control module which are sequentially communicatively connected;
[0061] The environment monitoring module is used to monitor the surrounding environment in real time, obtain the real-time distribution of dust in the environment and generate a dust distribution map;
[0062] The data integration module performs image processing and image analysis based on the dust distribution map to generate analysis results;
[0063] The intelligent control module generates a control strategy according to the analysis result and regulates the fog cannon equipment.
[0064] Specifically, in order to solve the problem of inaccurate spray control in the current dust suppression process of fog cannons, this application first uses the environmental monitoring module to monitor the surrounding environment in real time, obtains the distribution of dust in the environment and generates a dust distribution map; then uses the data integration module to perform image processing and analysis on the dust distribution map and obtain the analysis results; finally, the intelligent control module generates a control strategy based on the above analysis results, and accurately regulates the fog cannon equipment according to the control strategy. Through the synergistic effect of the above system modules, this application is based on real-time monitoring of dust in the environment, and uses image processing and image analysis technology to obtain the precise distribution of dust in the environment, and then adjusts the spray direction and angle of the fog cannon through the acquired precise data, and finally achieves accurate suppression and control of dust.
[0065] The above system modules will be described in detail below.
[0066] Regarding the environmental monitoring module, the existing monitoring methods for dust in the environment are mostly to use dust monitoring devices of different types to detect dust concentration. The dust monitoring device is usually a large dust removal equipment with a detection function. Although the above-mentioned dust monitoring device can detect dust concentration, it is unable to obtain accurate dust distribution and dust particle size data; inaccurate data will cause the subsequent fog cannon dust removal device to be unable to accurately control dust removal. Therefore, to address this problem, this application uses binocular vision technology in the environmental monitoring module to perform real-time monitoring of dust in the environment, and based on this, obtain more accurate data than the existing dust monitoring technology.
[0067] Specifically, the above-mentioned environmental monitoring module includes a particle monitoring unit, a three-dimensional reconstruction unit and a pollution source positioning unit which are communicatively connected in sequence;
[0068] The particle monitoring unit is used to obtain the dust distribution in the environment through binocular vision and generate a dust distribution map; it is also used to obtain the concentration and density of particles in the dust, and measure the size of particles;
[0069] Among them, the dust distribution map obtained by binocular vision technology is a two-dimensional image. Since the two-dimensional image cannot well reflect the distribution and specific situation of particles in the dust, the present application reconstructs the two-dimensional image into three-dimensional images by establishing a three-dimensional model, thereby better and more accurately reflecting the specific distribution and size of particles in the dust;
[0070] The three-dimensional reconstruction unit is used to perform three-dimensional model reconstruction according to the dust distribution map to generate a three-dimensional dust distribution model;
[0071] The pollution source positioning unit determines the environmental pollution source based on the dust distribution three-dimensional model and in combination with a positioning algorithm;
[0072] In summary, because binocular vision technology can use cameras or image sensors to simulate the perspective of human binoculars and simultaneously obtain image information at different positions, the present application uses binocular vision technology to monitor the dust concentration, dust density and particle size in the surrounding environment, and realizes a comprehensive analysis of the overall dust distribution through three-dimensional reconstruction, including but not limited to the spatial distribution, shape and position information of dust, and then combines the positioning algorithm to locate the pollution source, thereby realizing a comprehensive real-time and accurate monitoring of dust and pollution sources.
[0073] Furthermore, in the above-mentioned 3D reconstruction unit, 3D model reconstruction is performed according to the dust distribution map, which specifically includes the following steps:
[0074] S11, selecting two two-dimensional images at different positions in the dust distribution map;
[0075] S12, registering the two two-dimensional images to obtain a registered image;
[0076] It should be noted that registering a two-dimensional image is beneficial for converting it into point cloud data in a three-dimensional coordinate system;
[0077] S13, converting the two-dimensional image into three-dimensional point cloud data using a three-dimensional reconstruction algorithm according to the registered image;
[0078] S14, processing the three-dimensional point cloud data to generate a point cloud data set;
[0079] Wherein, steps S11 to S14 are repeatedly performed until the two selected two-dimensional images at different positions are not repeated with the two two-dimensional images selected in the previous round, and all the two-dimensional images in the dust distribution map are processed to generate a point cloud data set;
[0080] Processing the above three-dimensional point cloud data includes but is not limited to pre-processing operations such as denoising, filtering and segmentation;
[0081] S15, generating a dust distribution three-dimensional model based on the point cloud data set;
[0082] Specifically, the two-dimensional images obtained by binocular vision technology may have inaccurate disparity calculations due to factors such as lighting changes, texture loss or transparent objects, which may lead to errors in depth perception; at the same time, when there are blurred textures, low contrast or repeated structures, image matching becomes difficult, which will lead to inaccurate disparity calculations. Based on the above problems, this application adopts three-dimensional reconstruction technology to improve the accuracy of depth perception and the precision of depth estimation by aligning and converting two-dimensional images into three-dimensional point cloud data and performing data processing, thereby changing the image quality while reducing errors caused by problems such as image matching.
[0083] Furthermore, in the three-dimensional point cloud data of step S14, there are high-frequency noise points. Therefore, the present application adopts the minimum distance method to remove the high-frequency noise points in the original point cloud of the three-dimensional point cloud data. The formula is expressed as follows:
[0084]
[0085] Among them, d i Represents the distance between two adjacent points on the point cloud;
[0086] d max Represents the maximum value of all distance values;
[0087] represents the average of all distance values;
[0088] λ represents the length threshold set by the minimum distance method;
[0089] The coordinates of the two adjacent points are: i (x i ,y i , z i ) and P i+1 (x i+1 ,y i+1 , z i+1 ).
[0090] The judgment method for removing high-frequency noise points using the minimum distance method is:
[0091] Compare the distances d between adjacent points i With the set length threshold λ, if d i >λ, then ignore one of the two points, or take the center point instead of the two points, and judge all the points on the 3D point cloud data in turn. This can effectively remove the obvious isolated points in the point set and remove the high-frequency noise points. The minimum distance method can also be used for point cloud simplification. The judgment method is: if d i <λ, one of the two points is deleted, or the center point is used to replace the two points. This can remove similar points that are too close to each other, thereby effectively reducing the amount of point cloud data.
[0092] Furthermore, binocular vision technology can well reflect the particle concentration and density of particulate matter in dust through two-dimensional images, but the size of the particles cannot be well reflected. Therefore, based on binocular vision technology, this application also uses X-ray imaging technology to distinguish the size of particles. By using X-ray imaging equipment to obtain the projection image or volume data of the particles, the size of the particles can be judged and distinguished.
[0093] The dust in the environment can be divided into large particles, medium particles and fine particles according to the size of the particles (particles); among them, the diameter D1 of large particles is: 10μm<D1≤25μm; the diameter D2 of medium particles is: 2.5μm<D2≤10μm; the diameter D3 of fine particles is: D3≤2.5μm. The existing fog cannon device can only handle large and medium-sized particles, and cannot accurately handle fine particles. Therefore, the present application also adopts electrostatic precipitation technology and combines it with the fog cannon dust suppression system to handle various particles in the dust; wherein, the electrostatic precipitation technology uses the action of the electrostatic field to make fine particles carry opposite charges and be attracted to the collecting plate with relative charges, thereby realizing the sedimentation and separation of fine particles; and the fog cannon dust suppression device can effectively handle large and medium-sized particles; specifically, static charge is added to the water mist sprayed by the fog cannon device, so that the water droplets in the water mist carry static charge, and when they are close to the dust and fine particles in the air, the dust is adsorbed on the surface of the water droplets due to the electrostatic effect, and then as the water droplets fall to the ground, the dust (i.e., dust) is also settled on the ground. Through the above-mentioned electrostatic precipitation technology and the fog cannon dust suppression device, the present application can effectively settle large, medium and fine particles in the dust, making the dust suppression effect of the fog cannon more obvious, and at the same time, it can also improve the dust capture rate of the electrostatic precipitation technology.
[0094] Specifically, the dust is treated by combining electrostatic precipitation with fog cannon dust suppression, including the following steps:
[0095] S21, a strong electric field is generated in the water mist sprayed by the fog cannon by using an electrostatic generator, so that the water droplets have static charges;
[0096] This can be achieved by arranging an electrostatic generating device near the water mist generator or nozzle, so that the water droplets are charged with static electricity while the water mist is being formed, thereby obtaining charged water droplets;
[0097] S22, obtaining charged particles through the strong electric field;
[0098] That is: through a strong electric field, the fine particles in the dust are allowed to contact the electrodes with relative charges, so that they are charged with charges opposite to those of the electrodes, thereby obtaining charged particles;
[0099] S23, the charged water droplets and the charged particulate matter form a charged dust-water droplet complex through electrostatic action;
[0100] Since water droplets carry static charge, when they approach charged particles in dust, the electrostatic effect causes the charged particles to be adsorbed on the surface of water droplets, forming a charged dust-water droplet complex.
[0101] S24, controlling the settling of the dust-water droplet complex by controlling the electrostatic charge content of the strong electric field;
[0102] That is, the added static charge is controlled by controlling the static charge content, so that the charged dust-water droplet complex gradually falls due to gravity, and finally the dust is settled on the ground.
[0103] Controlling the static charge content can ensure that the adsorbed fine particles can effectively settle to the ground, while avoiding excessive static charge from having adverse effects on the surrounding environment and equipment.
[0104] Regarding the combination of the above-mentioned electrostatic precipitation technology and the fog cannon dust suppression device, the present application is achieved by setting an electrostatic generating device near the water mist generator or nozzle of the fog cannon dust suppression device, so as to give electrostatic charge to water droplets while the water mist is formed; the above-mentioned electrostatic generating device can be an electrostatic generator or other devices.
[0105] Furthermore, in the above-mentioned pollution source positioning unit, the positioning algorithm adopted in the present application is specifically an inversion model, which calculates the location and emission intensity of the pollution source by comparing the dust diffusion equation with the observation data; in the three-dimensional reconstruction, the three-dimensional model of dust distribution is used as the background field, and the inversion calculation is performed in combination with the sensor observation data and meteorological data to determine the environmental pollution source.
[0106] Furthermore, the present application adopts an inversion algorithm based on the Bayesian method to establish the above-mentioned inversion model. Specifically, when establishing the inversion model, three-dimensional point cloud data is used as observation data, and the location and emission intensity of the pollution source are estimated in combination with the prior probability distribution, thereby obtaining the posterior probability distribution, and then determining the location of the pollution source.
[0107] In summary, the inversion algorithm based on the Bayesian method used in this application has strong uncertainty processing capabilities, information fusion capabilities and flexibility when establishing an inversion model using three-dimensional point cloud data. It can provide more comprehensive and reliable inversion results, thereby more accurately determining the source of environmental pollution and facilitating the subsequent pollution source control work.
[0108] Regarding the data integration module, it includes an image processing unit and an image analysis unit that are communicatively connected to each other;
[0109] The image processing unit is used to perform image processing on the dust distribution map to obtain a dust distribution processing map;
[0110] The image analysis unit is used to perform image analysis on the dust distribution processing image to obtain analysis results.
[0111] Specifically, binocular vision acquires dust concentration data and distribution in the surrounding environment, and the surrounding environment will affect the acquired data due to light and atmospheric scattering, and then affect the generated image. Therefore, in order to perform data analysis more accurately in the future, the image processing unit of this application needs to acquire the relationship between light scattering and the concentration of particles in the dust. According to the atmospheric scattering theory, Mie scattering will occur when the size of the particles is not much different from or close to the wavelength of light.
[0112] Because the light intensity will be attenuated to a certain extent due to the particles in the dust, the application defines the attenuation degree of the light intensity as: the ratio of the outgoing light intensity to the incident light intensity, that is, the atmospheric transmittance; and in this attenuation process, the degree of absorption of the light by the atmosphere is expressed as the attenuation coefficient (extinction coefficient) of the light; therefore, the relationship between the atmospheric transmittance t(x) and the attenuation coefficient μ is expressed as follows:
[0113] t(x)=exp(-μ·d(x));
[0114] Wherein, μ represents the extinction coefficient; d(x) represents the propagation path of light.
[0115] It can be seen that under the premise of a certain propagation distance, the greater the attenuation coefficient, the lower the atmospheric transmittance. The relationship between atmospheric transmittance and propagation optical path is: the greater the visible propagation optical path, the lower the atmospheric transmittance.
[0116] Regarding the above-mentioned atmospheric transmittance t(x), based on the above-mentioned dust distribution map, the present application adopts a dust distribution model to represent the above-mentioned dust distribution map, which is specifically expressed as follows:
[0117] I(x,y)=J(x,y)t(x,y)+(1-t(x,y))A;
[0118] Among them, (x, y) is the coordinate of the image in the two-dimensional plane; I(x, y) is the image affected by the atmosphere observed by binocular vision, that is, the radiation intensity of the image captured by the binocular camera; t(x, y) represents the part of the light that transmits through the atmosphere to the camera, that is, the part that is not scattered, which is the propagation coefficient of the light in the atmosphere, that is, the atmospheric transmittance; J(x, y) is the radiation intensity of the image without interference.
[0119] The above dust distribution model is represented by a vector, and the specific formula is as follows:
[0120] I(x)=J(x)t(x)+(1-t(x))A;
[0121] Among them, the atmospheric transmittance t(x) is the vector representation of the above image coordinates.
[0122] Furthermore, because the extinction coefficient μ and the diameter and wavelength of the particles in the dust are related, the relationship between the extinction coefficient μ and the particle concentration is obtained. The extinction coefficient is used to measure the absorption and scattering ability of the particles in the dust to light, and the relationship expression is:
[0123] M f =174μ-26.2;
[0124] Among them, M f Indicates the concentration of particulate matter.
[0125] In summary, the above expression describes the relationship between particle concentration and extinction coefficient. If you want to estimate the particle concentration, you need to calculate the extinction coefficient μ; and the extinction coefficient μ can be calculated through atmospheric transmittance and the distance of light propagation.
[0126] Based on the relationship between the extinction coefficient and the particle concentration, the present application can eliminate other influencing factors in the environment through analysis and derive the particle concentration and the corresponding distribution, which is conducive to the subsequent intelligent control module to generate a control strategy and achieve precise regulation of the fog cannon equipment.
[0127] Regarding the intelligent control module, it includes a strategy generation unit and a fog cannon control unit which are communicatively connected to each other;
[0128] The strategy generation unit generates a control strategy using an intelligent control algorithm based on the analysis result;
[0129] The mist cannon control unit is used to control the mist cannon equipment / mist cannon dust suppression device according to the control strategy.
[0130] Specifically, through the processing and analysis of the dust distribution map by the data integration module, the present application can obtain accurate analysis results, which reflect the concentration and distribution position of the particulate matter in the environment; then the strategy generation unit generates a control strategy based on the analysis result using an intelligent control algorithm, and the control strategy is generated based on the concentration and position of the particulate matter in the analysis result, and is the best control method generated by the strategy algorithm; finally, in the fog cannon control unit, the spray direction, spray amount and spray time of the fog cannon equipment (that is, the fog cannon dust suppression device) are optimally adjusted and controlled according to the above control strategy, so as to achieve precise suppression and control of dust, and also effectively reduce the amount of fog cannon spray on the basis of improving the dust suppression effect, thereby reducing energy consumption.
[0131] In summary, the binocular vision-based fog cannon precise dust suppression system described in this application uses a binocular camera to monitor the dust concentration and distribution in the environment in real time, and realizes precise and intelligent fog cannon spraying through data processing and analysis. The system accurately adjusts the spray direction, spray volume and spray time of the fog cannon based on the real-time monitoring data, thereby realizing precise suppression and control of dust. Through binocular vision monitoring and intelligent control, the amount of fog cannon spray can be effectively reduced, the dust suppression effect can be improved, and the impact of the environment on the human body can be reduced.
[0132] This application uses binocular visual imaging technology to obtain the real-time distribution of dust in the environment, uses image processing and analysis technology to accurately analyze and process the monitored data, and then uses intelligent control algorithms to analyze the data and generate control strategies to achieve precise control of fog cannon spraying.
[0133] This application can better adapt to the dust suppression needs of fog cannons in complex environments, improve dust suppression efficiency while reducing energy consumption, and realize intelligent and precise dust suppression operations.
[0134] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0135] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.
[0136] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.
[0137] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.
Claims
1. A fog cannon precise dust suppression system based on binocular vision, Features: It includes an environment monitoring module, a data integration module and an intelligent control module which are sequentially connected in communication; The environment monitoring module is used to monitor the surrounding environment in real time, obtain the real-time distribution of dust in the environment and generate a dust distribution map; The data integration module performs image processing and image analysis based on the dust distribution map to generate analysis results; The intelligent control module generates a control strategy according to the analysis results and regulates the fog cannon equipment; Wherein, the fog cannon precise dust suppression system also includes a fog cannon dust suppression device; the fog cannon dust suppression device includes a water mist generator; In the intelligent control module, dust is treated by combining electrostatic precipitation with dust suppression by fog cannon, specifically: an electrostatic generating device is arranged around the water mist generator; The steps include: The electrostatic generating device generates a strong electric field in the water mist sprayed by the water mist generator to obtain charged water droplets; Acquiring charged particles through the strong electric field; The charged water droplets and the charged particulate matter form a charged dust-water droplet complex through electrostatic action; Controlling the settling of the dust-water droplet complex by controlling the electrostatic charge content of the strong electric field; In the data integration module, the analysis result is generated by obtaining the relationship between the extinction coefficient and the particle concentration; the extinction coefficient is used to measure the absorption and scattering ability of particles in dust to light, and its relationship expression is: M f =174μ-26.2; Among them, M f represents the particle concentration; μ represents the extinction coefficient; The extinction coefficient is expressed by the atmospheric transmittance, and its expression formula is as follows: t(x)=exp(-μ·d(x)); Where, d(x) represents the propagation path of light; t(x) represents the atmospheric transmittance; The atmospheric transmittance is represented by a vector expression of a dust distribution model, and the vector expression is: I(x)=J(x)t(x)+(1-t(x))A; Where t(x) represents the atmospheric transmittance; The dust distribution model is expressed as: I(x,y)=J(x,y)t(x,y)+(1-t(x,y))A; Where (x, y) represents the coordinates of the image in the two-dimensional plane; I(x, y) represents the radiation intensity of the disturbed image observed by binocular vision; t(x, y) represents the two-dimensional coordinates of the atmospheric transmittance t(x); J(x, y) represents the radiation intensity of the undisturbed image observed by binocular vision.
2. According to the binocular vision-based fog cannon precision dust suppression system of claim 1, Features: The environmental monitoring module includes a particle monitoring unit, a three-dimensional reconstruction unit and a pollution source positioning unit which are communicatively connected in sequence; The particle monitoring unit is used to obtain the dust distribution in the environment through binocular vision and generate a dust distribution map; it is also used to obtain the concentration and density of particles in the dust, and measure the size of particles; The three-dimensional reconstruction unit is used to perform three-dimensional model reconstruction according to the dust distribution map to generate a three-dimensional dust distribution model; The pollution source positioning unit determines the environmental pollution source based on the dust distribution three-dimensional model and in combination with a positioning algorithm.
3. According to the binocular vision-based fog cannon precision dust suppression system of claim 2, Features: Reconstructing the three-dimensional model according to the dust distribution map specifically includes the following steps: S11, selecting two two-dimensional images at different positions in the dust distribution map; S12, registering the two two-dimensional images to obtain a registered image; S13, converting the two-dimensional image into three-dimensional point cloud data using a three-dimensional reconstruction algorithm according to the registered image; S14, processing the three-dimensional point cloud data to generate a point cloud data set; S15, generating a dust distribution three-dimensional model based on the point cloud data set; Here, steps S11 to S14 are repeatedly executed until the two selected two-dimensional images at different positions are no longer the same as the two two-dimensional images selected in the previous round.
4. According to the binocular vision-based fog cannon precision dust suppression system of claim 3, Features: In the three-dimensional point cloud data of step S14, the minimum distance method is used to remove high-frequency noise points in the three-dimensional point cloud data, and its formula is expressed as: Among them, d i Represents the distance between two adjacent points on the point cloud; d max Represents the maximum value of all distance values; represents the average of all distance values; λ represents the set length threshold; The coordinates of two adjacent points are: i (x i ,y i , z i ) and P i+1 (x i+1 ,y i+1 , z i+1 ).
5. According to the binocular vision-based fog cannon precision dust suppression system of claim 4, Features: The judgment method for removing high-frequency noise points using the minimum distance method is: Compare the distances d between adjacent points i With the length threshold λ, if d i >λ, then ignore one of the two points or take the center point to replace the two points, and judge all the points on the three-dimensional point cloud data in turn.
6. According to claim 2, a binocular vision-based fog cannon precision dust suppression system, Features: X-ray imaging is also used to distinguish the size of particles. Specifically, X-ray imaging equipment is used to obtain projection images or volume data of particles, and to determine and distinguish the size of particles.
7. According to claim 6, a binocular vision-based fog cannon precision dust suppression system, Features: According to the size of the particles, the particles in the dust are divided into large particles, medium particles and fine particles; wherein the diameter of the large particles is: 10μm<D 1 ≤25μm; the diameter of the medium-sized particles is: 2.5μm<D 2 ≤10μm; the diameter of the fine particles is: D 3 ≤2.5μm.
Citation Information
Cited By
A control method for linking dust image analysis and fog gun pointing
CN123047663A
