Intelligent linkage control method for coal preparation full process dust

Abstract

The present application belongs to the technical field of dust prevention and control, and discloses a full-process dust intelligent linkage control method for coal preparation. The method comprises the following steps: dividing the coal preparation plant into regions; collecting the dust concentration of each region; evaluating the dust over-standard region according to the dust concentration of each region; collecting the influence parameters of the dust over-standard region; determining the dust over-standard reason and predicting the dust diffusion trend according to the influence parameters; and formulating and executing the linkage control strategy by fusing the dust over-standard reason, the dust diffusion trend and the influence parameters. The present application can effectively control and reduce the dust concentration in the coal preparation plant, realize the coordinated linkage control between different regions and equipment, thereby improving the overall dust prevention and control efficiency, and the control strategy is more targeted, which can significantly reduce the influence of dust emission on the working environment and the surrounding ecology, so as to strengthen the response capability to environmental protection.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of dust control, and more particularly to a coal preparation full-process dust intelligent linkage control method. BACKGROUND

[0002] With the continuous development of the coal industry, coal preparation plants, as important hubs for coal processing and transformation, their operating efficiency and environmental impact are increasingly concerned. Dust is inevitable in the process of raw coal receiving, crushing, screening, washing, dewatering, drying and product storage, especially in key locations such as raw coal storage, crushing room, screening room, drying area and product storage. In recent years, the national and local governments have been increasingly concerned about environmental protection. Therefore, while improving production efficiency, coal preparation plants must effectively control dust emissions to meet environmental protection requirements. Traditional dust control methods often rely on manual monitoring and passive response, making it difficult to achieve real-time and accurate control, and leading to resource waste and cost increases.

[0003] Although the prior art can achieve dust control, the main focus is on dust source characteristic analysis, dust reason analysis and dust amount calculation, and does not specifically describe how to design a dust prevention scheme based on dust source characteristics, dust reasons and dust amount, lacking targeted prevention and control measures. In addition, although the prior art mentions the combination of dust suppression and dust removal, there are certain limitations in the linkage control between different devices, thereby affecting the coordination and efficiency of the overall dust control effect.

[0004] In view of this, the present application proposes a coal preparation full-process dust intelligent linkage control method to solve the above problems. SUMMARY

[0005] In order to overcome the above-mentioned defects of the prior art and achieve the above-mentioned purposes, the present application provides the following technical solution: a coal preparation full-process dust intelligent linkage control method, comprising:

[0006] The coal preparation plant is regionally divided according to different functional areas and the monitoring range of the dust concentration sensor;

[0007] The dust concentration of each region is collected;

[0008] According to the dust concentration of each region and the preset concentration threshold, the dust over-standard region is evaluated;

[0009] The influence parameters of the dust over-standard region are collected;

[0010] According to the influence parameters, the dust over-standard reason is determined using fuzzy logic reasoning; based on the influence parameters and the divided regions, the dust diffusion trend is predicted;

[0011] The reasons for excessive fusion dust, dust diffusion trends and influencing parameters are determined, and a linkage control strategy is formulated by using a natural heuristic optimization algorithm.

[0012] Further, the method for dividing the coal preparation plant into regions comprises:

[0013] According to different functional areas in the coal preparation plant, the coal preparation plant is preliminarily divided into regions; and after the preliminary regional division is completed, each region obtained is further divided into regions according to the monitoring range of the dust concentration sensor, and each region is a rectangle;

[0014] The method for evaluating the dust exceeding region comprises:

[0015] The concentration threshold is calculated, and the dust concentration of each region is compared with the concentration threshold; if the dust concentration is greater than or equal to the concentration threshold, the corresponding region is marked as a dust exceeding region; if the dust concentration is less than the concentration threshold, the corresponding region is not marked; the dust concentration is the number of suspended particulate matters in a unit volume of air;

[0016] The method for calculating the concentration threshold is: collecting n historical dust concentrations, the historical dust concentration being a historically collected dust concentration, n being an integer greater than 1; the mean and the standard deviation of the n historical dust concentrations are calculated respectively, and are marked as the historical mean and the historical standard deviation respectively; the historical standard deviation is multiplied by a coefficient a and then added to the historical mean to obtain the concentration threshold; wherein a∈[1,3] and a is an integer.

[0017] Further, the influencing parameters comprise environmental parameters, equipment parameters and particle parameters;

[0018] The environmental parameters comprise wind speed, wind direction, environmental temperature and environmental humidity; the equipment parameters are operation parameters of each equipment; the particle parameters comprise particle size and particle humidity; the particle size is the diameter of a single particle; and the particle humidity is the amount of moisture contained in a single particle;

[0019] The step of determining the dust exceeding reason comprises:

[0020] Step S501: establishing a fuzzy set, and dividing each parameter in the influencing parameters into a plurality of fuzzy sets;

[0021] Step S502: converting the influencing parameters into fuzzy sets by using a fuzzification technique; the fuzzification is a process of converting accurate numerical values into fuzzy sets; the fuzzy set is described by using a membership function;

[0022] Step S503: defining fuzzy rules;

[0023] Step S504: match the blurred influence parameter with the fuzzy rule, perform fuzzy reasoning, obtain a fuzzy reasoning result, and the fuzzy reasoning result is a membership degree of each dust over-standard reason;

[0024] Step S505: perform a deblurring operation on the fuzzy reasoning result to obtain a deblurring result, and the deblurring result is the dust over-standard reason. The deblurring operation is: according to the fuzzy reasoning result, obtaining the membership degree of each dust over-standard reason; presetting a membership degree threshold, comparing the membership degree of each dust over-standard reason with the membership degree threshold, and obtaining each dust over-standard reason whose membership degree is greater than or equal to the membership degree threshold.

[0025] Further, the method for predicting the dust diffusion trend comprises:

[0026] Taking any vertex of the dust over-standard region as an origin, and the coordinates of the origin being (0, 0, 0), a three-dimensional coordinate system is constructed; and a region center coordinate corresponding to the dust over-standard region is calculated.

[0027] A preset stability coefficient library is provided, and a corresponding stability coefficient is obtained from the stability coefficient library according to the wind speed, the environmental temperature and the environmental humidity; the stability coefficient library includes the wind speed, the environmental temperature and the environmental humidity, and the stability coefficient corresponding to the wind speed, the environmental temperature and the environmental humidity; if the wind speed, the environmental temperature or the environmental humidity in the influence parameter does not exist in the stability coefficient library, an interpolation method is used to estimate the corresponding stability coefficient;

[0028] According to the wind direction, a region adjacent to the dust over-standard region in the direction corresponding to the wind direction is marked as a diffusion region; a grid is set for the diffusion region, and the grid size is a unit volume; coordinates of each position point in the diffusion region are obtained and marked as position coordinates, and the position point is a grid node; a Euclidean distance between each position coordinate and the region center coordinate is calculated as a diffusion distance corresponding to each position point; the diffusion distance of each position point is multiplied by the stability coefficient to obtain a diffusion coefficient of each position point; according to the dust concentration of the dust over-standard region, the wind speed, the diffusion coefficient of each position point, the position coordinate and the region center coordinate, a diffusion concentration corresponding to each position point is calculated, and the diffusion concentration is the dust concentration diffused to each position point;

[0029] The number of position points corresponding to each diffusion region is obtained, the diffusion concentration of each position point corresponding to each diffusion region is sequentially added, and then divided by the number of corresponding position points to obtain an average diffusion concentration of each diffusion region; the average diffusion concentration of each diffusion region is added to the corresponding dust concentration to obtain a total dust concentration of each diffusion region, and marked as a diffusion total concentration.

[0030] Further, the method for calculating the region center coordinate comprises:

[0031] The coordinates of the diagonal point corresponding to the origin in the dust-exceeding area are obtained, the diagonal point corresponding to the origin is a point symmetrical to the origin along the diagonal line of the area; the abscissa of the diagonal point is divided by 2 to obtain the abscissa of the center coordinate of the area; the ordinate of the diagonal point is divided by 2 to obtain the ordinate of the center coordinate of the area; a preset reference height is used as the height coordinate of the center coordinate of the area.

[0032] Further, a natural heuristic optimization algorithm is used to formulate the linkage control strategy, and the steps include:

[0033] Step S601: presetting M parameter sets, setting different digital tags for different parameter sets, and marking as set tags; presetting a population size Z and a number threshold T;

[0034] Step S602: initializing a population, defining the positions of the lampfish in the initialized population in a one-dimensional search space, and one-to-one corresponding the positions of the lampfish to the set tags; the iteration number t corresponding to the initialized population is 0;

[0035] Step S603: determining a fitness function;

[0036] Step S604: selecting a host for each lampfish;

[0037] Step S605: updating the position of each lampfish;

[0038] Step S606: calculating a switching probability, calculating a new position according to the switching probability, judging whether to switch the host according to the calculated new position, and updating the position of the lampfish again;

[0039] Step S607: each lampfish enters a foraging stage, and the position of each lampfish is updated;

[0040] Step S608: setting the iteration number t to t+1; Step S604 is returned to;

[0041] Step S609: repeating steps S604 to S608 until the iteration number t reaches the number threshold T, and the cycle is ended, and step S610 is entered;

[0042] Step S610: calculating the fitness corresponding to the position of each lampfish, sorting all the fitnesses from large to small, obtaining the lampfish position corresponding to the largest fitness, obtaining the parameter set corresponding to the set tag corresponding to the obtained lampfish position, and taking the parameter set as the linkage control strategy.

[0043] Further, in step S601, the range of each operating parameter corresponding to each device in the diffusion area and the dust-exceeding area is obtained, a value is randomly selected from each range to construct a parameter set, and M parameter sets are constructed.​

[0044] In the step S602, the population is initialized , including Z swordfishes, is the Zth swordfish, and Z is the number of crucian carps in the initialized population; the range of the set label and the range of the one-dimensional search space are both ;

[0045] In the step S603, the expression of the fitness function is: ; in the formula, is the fitness, is the total concentration reduction degree; the method for obtaining the total concentration reduction degree comprises the following steps:

[0046] J concentration prediction models are trained, J is the number of areas of the coal preparation plant, the concentration prediction model corresponds to an area of the coal preparation plant in a one-to-one manner; the concentration prediction model corresponding to the diffusion area and the dust over-limit area is obtained and marked as a use model; different digital labels are set for different dust over-limit reasons, the digital label corresponding to the dust over-limit reason obtained in the step S505 is obtained and marked as a reason label; the environmental parameters, the particle parameters, the reason label, the diffusion total concentration, and the dust concentration of the dust over-limit area are used as test data; the set label corresponding to the position of the swordfish is obtained, the set label and the test data are used as analysis data, and the analysis data is input into each use model, the corresponding dust concentration is predicted, and the predicted dust concentration is marked as an adjusted concentration; the total dust concentration of each diffusion area and the dust concentration of the dust over-limit area are respectively subtracted by the corresponding adjusted concentration, the concentration reduction degree of each diffusion area and the concentration reduction degree corresponding to the dust over-limit area are obtained; the concentration reduction degrees of each diffusion area are sequentially added, and the concentration reduction degree corresponding to the dust over-limit area is added, to obtain the total concentration reduction degree.

[0047] Further, in the step S604, the host includes a marlin and a whale; the random number corresponding to each swordfish is obtained and a rounding operation is performed, if the rounded random number is 0, the host of the swordfish parasitism is a whale, if the rounded random number is 1, the host of the swordfish parasitism is a marlin;

[0048] In the step S605, the fitness corresponding to the position of each swordfish is calculated, and the position of the swordfish corresponding to the maximum fitness is marked as .

[0049] Further, in the step S606, the new position is a position adjacent to the host position; a fitness corresponding to the new position is calculated and marked as an adjacent fitness; a fitness corresponding to the current position of the fish is marked as a current fitness; the adjacent fitness is compared with the current fitness; if the adjacent fitness is greater than or equal to the current fitness, the host is not switched; if the adjacent fitness is less than the current fitness, the host is switched;

[0050] The method for updating the position of the fish switching the host is consistent with the method for updating the position of each fish in the step S605.

[0051] Further, the method further comprises: calculating the personnel density of each region and comprehensively evaluating the dust over-standard region according to the corresponding dust concentration.

[0052] The method for calculating the personnel density of each region comprises:

[0053] Collecting a region image of each region; using a trained personnel recognition model to recognize each region image to output a recognition result, and the recognition result is the number of personnel;

[0054] Multiplying the abscissa of the diagonal point by the ordinate of the diagonal point to obtain the area of the region; sequentially adding the number of personnel corresponding to each region image corresponding to each region to obtain the total number of personnel of each region; and dividing the total number of personnel of each region by the area of the region to obtain the personnel density of each region;

[0055] A preset influence factor is multiplied by the personnel density of each region, and then a concentration threshold value is added to obtain a new concentration threshold value corresponding to each region; the dust concentration of each region is compared with the corresponding new concentration threshold value; if the dust concentration is greater than or equal to the new concentration threshold value, the corresponding region is marked as a dust over-standard region; and if the dust concentration is less than the new concentration threshold value, the corresponding region is not marked.

[0056] The technical effects and advantages of the intelligent linkage control method for the whole process of coal selection dust proposed in the application are as follows:

[0057] The application subdivides the regions of the coal preparation plant, monitors the dust concentration of each region in real time, evaluates the over-standard region, considers the influence of multiple environmental parameters and equipment operation parameters on dust formation, determines the dust over-standard reason by using a fuzzy algorithm, predicts the dust diffusion trend combined with the particle parameters, obtains the dust concentration of each position point in the dust diffusion range, and then formulates a scientific and reasonable linkage response strategy by using a natural heuristic optimization algorithm, so that the dust concentration of the coal preparation plant is effectively controlled and reduced, the coordinated linkage control between different regions and equipment is realized, the overall dust prevention and control efficiency is improved, the control strategy is more targeted, the influence of dust emission on the working environment and the surrounding ecology is reduced, and the response capability for environmental protection is strengthened.

[0058] The present application utilizes deep learning technology to realize accurate regional population statistics and real-time calculation of personnel density in the region, dynamically adjusts the dust concentration threshold of the corresponding region according to the personnel density, can more effectively identify and evaluate the dust over-standard region, fully considers the influence of personnel density on dust diffusion and the influence of personnel density on dust hazard evaluation, not only improves the accuracy of dust over-standard region identification, but also reduces the health risk of workers, thereby better protecting the occupational health of the operating personnel in the coal preparation plant and providing strong support for improving the operating environment. BRIEF DESCRIPTION OF DRAWINGS

[0059] Figure 1 The figure is a flow chart of the intelligent linkage control method of the whole process dust in the coal preparation of the embodiment 1 of the present application.

[0060] Figure 2 The figure is a flow chart of the linkage control strategy making method of the embodiment 1 of the present application.

[0061] Figure 3 The figure is a flow chart of the intelligent linkage control method of the whole process dust in the coal preparation of the embodiment 2 of the present application. DETAILED DESCRIPTION

[0062] The technical solutions in the embodiments of the present application will be described clearly and completely in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the protection scope of the present application.

[0063] Embodiment 1

[0064] Please refer to Figure 1 The intelligent linkage control method of the whole process dust in the coal preparation described in the present embodiment, the method comprises:

[0065] According to the different functional areas in the coal preparation plant and the monitoring range of the dust concentration sensor, the coal preparation plant is divided into regions.

[0066] The method for dividing the coal preparation plant into regions comprises:

[0067] According to different functional areas in the coal preparation plant, the coal preparation plant is preliminarily divided into regions; different functional areas in the coal preparation plant at least include a raw coal receiving area, a crushing area, a screening area, a washing and separating area, a dehydration and drying area and a product storage area, wherein the raw coal receiving area is an area for receiving raw coal transported from outside, and is usually provided with receiving equipment such as a dumper, a belt conveyor and the like; the crushing area is an area for crushing large pieces of raw coal into pieces meeting the requirements of subsequent processing, and is usually provided with crushing equipment such as a jaw crusher, an impact crusher and the like; the screening area is an area for classifying the crushed coal according to particle size, and is usually provided with screening equipment such as a vibrating screen, a classifying screen and the like; the washing and separating area is an area for removing impurities in the coal and separating clean coal, and is usually provided with washing and separating equipment such as a jig, a dense medium cyclone, a flotation machine and the like; the dehydration and drying area is an area for removing excess moisture in the coal after washing and separating and reducing the moisture content of the coal, and is usually provided with dehydration and drying equipment such as a centrifugal dehydrator, a drum dryer and the like; the product storage area is an area for long-term storage of clean coal, medium coal and other coal products, and is usually provided with windproof and dust suppression facilities such as a windproof and dust suppression net, a spray dust suppression system and the like; after the preliminary regional division is completed, each region obtained is further divided into regions according to the monitoring range of the dust concentration sensor, and each region is rectangular; that is, after the further regional division, the range of a region is the monitoring range of a dust concentration sensor; the dust concentration sensor is, for example, a laser particle counter, an optical dust sensor, an electrochemical sensor and the like, and the monitoring range of the dust concentration sensor is obtained according to the technical manual of the dust concentration sensor.

[0068] The dust concentration of each region is collected.

[0069] The dust concentration is the number of suspended particulate matters in a unit volume of air; the dust concentration is obtained by a dust concentration sensor installed in each region.

[0070] According to the dust concentration of each region and a preset concentration threshold, a dust over-standard region is evaluated.

[0071] The method for evaluating the dust over-standard region comprises:

[0072] The concentration threshold is calculated, and the dust concentration of each region is compared with the concentration threshold; if the dust concentration is greater than or equal to the concentration threshold, the corresponding region is marked as a dust over-standard region; if the dust concentration is less than the concentration threshold, the corresponding region is not marked.

[0073] The method for calculating the concentration threshold is: collecting n historical dust concentrations, the historical dust concentration being a historically collected dust concentration, and n being an integer greater than 1; the mean and the standard deviation of the n historical dust concentrations are respectively calculated and are respectively marked as a historical mean and a historical standard deviation; the historical standard deviation is multiplied by a coefficient a and then added to the historical mean to obtain the concentration threshold; wherein , and a is an integer; preferably, a is 2 in this embodiment; the expression of the historical mean value is: ; wherein, is the historical mean value, is the bth historical dust concentration, ; the expression of the historical standard deviation is: ; wherein, is the historical standard deviation.

[0074] It should be noted that the reason for calculating the concentration threshold is to enable the concentration threshold to be dynamically adjusted according to the change of the dust concentration, better adapt to the natural fluctuation of the dust concentration, and thus more accurately identify the abnormal dust concentration, and reduce the probability of false positives and false negatives.

[0075] The influence parameters of the dust-exceeding area are collected.

[0076] The influence parameters include environmental parameters, equipment parameters, and particle parameters.

[0077] The environmental parameters include wind speed, wind direction, environmental temperature, and environmental humidity; wherein, the wind speed is obtained by a wind speed meter installed in each area, the wind direction is obtained by a wind direction marker installed in each area, the environmental temperature is obtained by a temperature sensor installed in each area, and the environmental humidity is obtained by a humidity sensor installed in each area.

[0078] The device parameters are operating parameters of each device, and the device at least includes a crushing device, a screening device, a washing and separating device, a dehydration and drying device, a conveying device, and a dust removal device. The crushing device is a device for crushing large pieces of raw coal into a size that meets the requirements of subsequent processing, including a jaw crusher, an impact crusher, etc. The screening device is a device for classifying the crushed coal according to particle size, including a vibrating screen, a grading screen, etc. The washing and separating device is a device for removing impurities in the coal and separating clean coal, including a jig, a dense medium cyclone, a flotation machine, etc. The dehydration and drying device is a device for removing excess moisture in the coal after washing and separating and reducing the moisture content of the coal, including a centrifugal dehydrator, a drum dryer, etc. The conveying device is a device for transferring coal between different areas, including a conveyor belt, a bucket elevator, etc. The dust removal device is a device for controlling and reducing dust dispersion, including a spray dust suppression machine, a bag dust collector, an induced draft fan, etc. The operating parameters include operating speed, load, device power, etc. The operating speed is the operating speed of the key components of the device when it is running, including the rotor speed of the crushing device, the vibration frequency of the screening device, the stirring speed of the washing and separating device, the drum speed of the dehydration and drying device, the speed of the conveyor belt, the speed of the induced draft fan, etc. The operating speed is obtained by a speed sensor installed in each device. The load is the amount of coal processed by the device when it is running, including the feed amount of the crushing device, the processing amount of the screening device, the feed amount of the washing and separating device, the feed amount of the dehydration and drying device, the amount of coal conveyed by the conveyor belt, etc. The load is obtained by a load sensor installed in each device. The device power is the power output of the device when it is running, including the power output of the crushing device, the screening device, the washing and separating device, the dehydration and drying device, the bucket elevator, the bag dust collector, etc. The device power is obtained by a power sensor installed in each device.

[0079] The particle parameters include particle size and particle humidity. The particle size is the diameter of a single particle, and the particle size is obtained by a laser particle size analyzer installed in each area. The particle humidity is the amount of moisture contained in a single particle, and the particle humidity is obtained by a microwave humidity sensor.

[0080] It should be noted that each of the influence parameters will affect the dust concentration and dust diffusion trend in the region; among them, high wind speed will accelerate the diffusion of dust, making the dust diffuse to more areas, and low wind speed will cause the dust to gather in local areas, causing the dust concentration to increase; the wind direction determines the diffusion direction of the dust; high temperature will cause the moisture in dry bulk cargo to evaporate, thereby increasing the dust concentration, and low temperature will cause the dust to settle, reducing the dust concentration in the air; high environmental humidity can make the dust particles absorb moisture and become heavy, thereby reducing the dust concentration, and low environmental humidity will cause the dust to be more easily carried by the air, increasing the dust concentration; high operating speed of the crushing equipment, high vibration frequency of the screening equipment, high speed of the conveyor belt, high roller speed of the dehydration drying equipment, etc. High operating speed will increase the throwing and disturbance of coal, thereby increasing dust generation, and low operating speed will reduce the disturbance of coal, thereby reducing the dust concentration, but will affect the production efficiency; high load of the crushing equipment, high load of the screening equipment, high load of the washing and selecting equipment, high load of the conveyor belt, etc. High load will cause the equipment to be overloaded or the coal to be scattered, increasing the dust concentration, and low load will reduce dust generation, but will also reduce the working efficiency of the equipment; high-power equipment such as crushing equipment, screening equipment, washing and selecting equipment, and dehydration drying equipment operates more stably under high load, thereby effectively controlling dust, and low-power equipment operates unstably under high load, causing more dust to be released; smaller particles are more easily suspended in the air and blown away by the wind, while larger particles are more likely to settle or be blocked, so the diffusion range is smaller; higher particle humidity will cause the particles to absorb moisture and expand, increasing the weight, making it easier to settle and reduce the dust concentration in the air, and conversely, under the condition of low particle humidity, the particles are more likely to remain in a suspended state and be spread by the wind.

[0081] It should be understood that the environmental temperature and the environmental humidity also reflect the humidity condition of the particles, but the effect of the particle humidity is different, the particle humidity provides real-time humidity information of the particles, and the environmental temperature and the environmental humidity are helpful for analyzing the long-term change of the particle humidity; the environmental temperature and the environmental humidity will affect the change trend of the particle humidity, thereby more accurately predicting the dust diffusion trend.

[0082] According to the influence parameters, the dust exceeding standard reason is determined using fuzzy logic reasoning; based on the influence parameters and the divided regions, the dust diffusion trend is predicted.

[0083] The step of determining the dust exceeding standard reason includes:

[0084] Step S501: Establish a fuzzy set, and divide each of the influence parameters into a plurality of fuzzy sets; for example: the fuzzy set corresponding to the environmental temperature is high environmental temperature, medium environmental temperature, low environmental temperature, etc., the fuzzy set corresponding to the particle size is large particle, medium particle, small particle, etc., and the fuzzy set corresponding to the operating speed is fast speed, medium speed, slow speed, etc.

[0085] Step S502: converting the influence parameters into fuzzy sets through a fuzzification technique; the fuzzification is a process of converting precise numerical values into fuzzy sets, and the fuzzification technique is, for example, a triangular membership function, a trapezoidal membership function, etc.; the fuzzy set is a mathematical tool for representing a fuzzy concept, and can be described by a membership function; for example, if the numerical value of the ambient temperature is low, it is inferred that the membership degree of the low ambient temperature is high;

[0086] Step S503: defining fuzzy rules, which are defined according to expert knowledge or literature; for example, if the ambient humidity is high, the ambient temperature is low, and the running speed is fast, it is inferred that the cause of dust exceeding the standard is that the production speed is too high; if the ambient humidity is low, the ambient temperature is high, the particle is medium, and the running speed is medium, it is inferred that the cause of dust exceeding the standard is the environmental factor;

[0087] Step S504: matching the fuzzified influence parameters with the fuzzy rules to perform fuzzy reasoning and obtain a fuzzy reasoning result, which is the membership degree of each dust exceeding standard cause; the fuzzy reasoning method is, for example, a Mamdani or Sugeno fuzzy reasoning method; the fuzzy reasoning result is, for example, that the membership degree of the production speed being too high is 0.3, and the membership degree of the environmental factor is 0.7;

[0088] Step S505: performing a defuzzification operation on the fuzzy reasoning result to obtain a defuzzification result, which is the dust exceeding standard cause; the defuzzification is a process of converting the fuzzy reasoning result into a specific recognition result, and the defuzzification operation is: according to the fuzzy reasoning result, obtaining the membership degree of each dust exceeding standard cause; presetting a membership degree threshold, comparing the membership degree of each dust exceeding standard cause with the membership degree threshold, and obtaining each dust exceeding standard cause whose membership degree is greater than or equal to the membership degree threshold; the membership degree threshold is preset by a person skilled in the art according to the actual situation.

[0089] The method for predicting the dust diffusion trend comprises:

[0090] A three-dimensional coordinate system is constructed with any vertex of the dust exceeding standard area as the origin, and the coordinates of the origin are (0, 0, 0); the region center coordinates corresponding to the dust exceeding standard area are calculated; the calculation method of the region center coordinates comprises:

[0091] The coordinates of the diagonal point corresponding to the origin in the dust-exceeding area are obtained, and the diagonal point corresponding to the origin is a point symmetrical to the origin along the diagonal line of the area; the abscissa of the diagonal point is divided by 2 to obtain the abscissa of the center coordinate of the area; the ordinate of the diagonal point is divided by 2 to obtain the ordinate of the center coordinate of the area; a preset reference height is used as the height coordinate of the center coordinate of the area; the reference height is preset by a person skilled in the art according to the actual situation, and the reason for presetting the reference height is that the height of the area has no boundary limit, so it cannot be calculated specifically, and needs to be determined by a preset value.

[0092] A preset stability coefficient library is obtained, and the corresponding stability coefficient is obtained from the stability coefficient library according to the wind speed, the environmental temperature and the environmental humidity; the stability coefficient library includes the wind speed, the environmental temperature and the environmental humidity, and the stability coefficient corresponding to the wind speed, the environmental temperature and the environmental humidity; the stability coefficient library is preset by a person skilled in the art in combination with the environmental characteristics in the coal preparation plant workshop, such as the structural difference of the workshop in different functional areas, by referring to relevant literature or carrying out experiments, and at the same time, the influence weight of the wind speed is corrected during the setting process, so as to adapt to the characteristics that the airflow in the coal preparation plant workshop is relatively closed and the wind speed has a weaker influence on dust diffusion than in an open environment; if the wind speed, the environmental temperature, the environmental humidity or the airflow disturbance coefficient in the workshop do not exist in the stability coefficient library, an interpolation method is used to estimate the corresponding stability coefficient, and common interpolation methods include linear interpolation, Lagrange interpolation and the like.

[0093] According to the wind direction, the area adjacent to the dust-exceeding area in the diffusion area is marked as a diffusion area; a grid is set for the diffusion area, and the grid size is a unit volume; the coordinates of each position point in the diffusion area are obtained and marked as position coordinates, and the position point is a grid node; the Euclidean distance between each position coordinate and the center coordinate of the area is calculated as the diffusion distance of each position point, and the calculation method of the Euclidean distance is a prior art, which will not be described in detail here; the diffusion distance of each position point is multiplied by the stability coefficient to obtain the diffusion coefficient of each position point; according to the dust concentration of the dust-exceeding area, the wind speed, the diffusion coefficient of each position point, the position coordinate and the center coordinate of the area, the diffusion concentration corresponding to each position point is calculated, and the diffusion concentration is the dust concentration diffused to each position point; the expression of the diffusion concentration is: ; in the formula, is the diffusion concentration of the jth position point, is the dust concentration of the dust-exceeding area, is the wind speed, is the diffusion coefficient of the jth position point, is the ordinate of the jth position point, is the ordinate of the center coordinate of the area, is the height coordinate of the jth position point, is the height coordinate of the regional center coordinate, exp is the exponential function, , is the total number of position points.

[0094] It should be noted that the expression of the diffusion concentration is a simplification of the classical Gaussian plume model, and Q in the classical Gaussian plume model is the emission rate per unit time, while Q in this embodiment is the dust concentration of the dust exceeding area, ignoring the time dimension of the emission rate, and is more suitable for the scene of calculating the concentration distribution of the diffusion to the surrounding when the area has exceeded, and the dimension of the expression can be modified by the cross-sectional area of the exceeding area and the wind speed.

[0095] Obtain the number of position points corresponding to each diffusion area, add the diffusion concentration of each position point corresponding to each diffusion area in turn, and then divide by the corresponding number of position points to obtain the average diffusion concentration of each diffusion area; add the average diffusion concentration of each diffusion area to the corresponding dust concentration to obtain the total dust concentration of each diffusion area, and mark it as the total diffusion concentration.

[0096] Fusion dust exceeding reason, dust diffusion trend and influence parameter, adopt natural heuristic optimization algorithm to formulate linkage control strategy.

[0097] As shown in Figure 2 , the natural heuristic optimization algorithm is used to formulate the linkage control strategy, and the steps include:

[0098] The natural heuristic optimization algorithm is, for example, genetic algorithm, clone selection algorithm, and dragonfish optimization algorithm. In this embodiment, the dragonfish optimization algorithm is taken as an example to introduce the steps of formulating the linkage control strategy.

[0099] Step S601: preset M parameter sets, set different digital tags for different parameter sets, and mark them as set tags; preset population size Z and number threshold T;

[0100] Step S602: initialize the population, define the position of the dragonfish in the initialized population in a one-dimensional search space, and the position of the dragonfish corresponds to the set tag one by one, and the iteration number t corresponding to the initialized population is 0;

[0101] Step S603: determine the fitness function;

[0102] Step S604: select a host for each dragonfish parasite;

[0103] Step S605: update the position of each dragonfish;

[0104] Step S606: calculate the switching probability, calculate the new position according to the switching probability, and judge whether to switch the host according to the calculated new position, and update the position of the dragonfish again;

[0105] Step S607: Each lanternfish enters the foraging stage, and the position of each lanternfish is updated.

[0106] Step S608: Let the iteration number , and jump back to step S604;

[0107] Step S609: Loop steps S604-S608 until , and end the loop and enter step S610;

[0108] Step S610: Calculate the fitness of the position of each lanternfish, sort all fitnesses from large to small, obtain the lanternfish position corresponding to the fitness at the forefront, obtain the parameter set corresponding to the set label corresponding to the obtained lanternfish position, and use it as the linkage control strategy.

[0109] In the above step S601, the range of each operating parameter corresponding to each device in the diffusion area and the dust over-standard area is obtained, a value is randomly selected from each range, a parameter set is constructed, and M parameter sets are constructed; the range of each operating parameter corresponding to each device in the diffusion area and the dust over-standard area is obtained from the corresponding device technical manual.

[0110] The population size Z is obtained by a person skilled in the art, under the condition of a plurality of different test data in the historical process of formulating a linkage control strategy, a plurality of different population sizes are set for the same test data, a plurality of lanternfish optimization algorithms are performed, after the same iteration number is performed, the corresponding set label is obtained, the population size corresponding to the set label closest to the actual set label is obtained, and the population size corresponding to the set label closest to the actual set label is obtained. The population size corresponding to the test data is obtained; wherein the test data includes environmental parameters, particle parameters, reason labels, total diffusion concentration and dust concentration in the dust over-standard area, the reason label is a digital label corresponding to the dust over-standard reason in step S505, and different digital labels correspond to different dust over-standard reasons; the actual set label is the set label most matched with the test data, and the actual set label is obtained by a person skilled in the art according to actual experience; in this way, the population size corresponding to each test data is obtained, and the mean of the plurality of population sizes is used as the preset population size Z.

[0111] The iteration threshold T is obtained by a person skilled in the art, under the condition of a plurality of different test data in the historical process of formulating a linkage control strategy, a plurality of lanternfish optimization algorithms are performed on the same test data, a plurality of set labels are obtained, wherein the iteration number of each lanternfish optimization algorithm is different, the population size is the same and is Z; the iteration number corresponding to the set label closest to the actual set label is used as the iteration number corresponding to the test data; in this way, the iteration number corresponding to each test data is obtained, and the mean of the plurality of iteration numbers is used as the iteration threshold T.

[0112] It should be appreciated that the population size Z determines the breadth of the search, and a larger population size can explore more solution space, while the number threshold T determines the termination condition of the algorithm, which can control the speed of convergence of the algorithm.

[0113] In step S602, the population is initialized , including Z fish, is the Zth fish, Z is the number of fish in the initialized population; the range of the set label and the range of the one-dimensional search space are ; the expression of the position of each fish is: ; in the formula, is the initial position of the ith fish, is a random number between . .

[0114] In step S603, the expression of the fitness function is: ; in the formula, is the fitness, is the total concentration drop; the method for obtaining the total concentration drop includes:

[0115] J concentration prediction models are trained, J is the number of regions of the coal preparation plant, and the concentration prediction model corresponds to one region of the coal preparation plant; the concentration prediction model corresponding to the diffusion region and the dust exceeding region is obtained and marked as the use model; the set label corresponding to the fish position is obtained, the set label and the test data are used as analysis data, and the analysis data is input into each use model to predict the corresponding dust concentration and mark it as the adjusted concentration.

[0116] The training process of the concentration prediction model includes:

[0117] H sets of analysis data are set with corresponding dust concentrations in advance, H is an integer greater than 1; the corresponding dust concentration of the analysis data is set by a person skilled in the art in the process of historically formulating the linkage control strategy, collecting H sets of analysis data, and sequentially performing experiments under the condition of each set of analysis data, collecting the corresponding dust concentration after each experiment is completed, and setting the corresponding dust concentration for H sets of different analysis data;

[0118] The analysis data and the corresponding dust concentration are converted into a corresponding set of feature vectors; each set of feature vectors is used as the input of the concentration analysis model, the concentration analysis model takes a set of predicted dust concentrations corresponding to each set of analysis data as the output, and the actual dust concentration corresponding to each set of analysis data as the prediction target, and the actual dust concentration is the digital label of the preliminary identification result corresponding to the analysis data set in advance; the training target is to minimize the sum of the prediction errors of all analysis data; wherein the calculation formula of the prediction error is , wherein is a prediction error, h is a group number of a feature vector corresponding to the analysis data, is a predicted dust concentration corresponding to the hth group of analysis data, is an actual dust concentration corresponding to the hth group of analysis data; the concentration analysis model is trained until the sum of prediction errors reaches convergence, and the training is stopped;

[0119] The concentration analysis model is specifically a deep neural network model.

[0120] The total dust concentration of each diffusion region is respectively subtracted by the corresponding adjustment concentration to obtain the concentration reduction degree of each diffusion region; the dust concentration of the dust over-limit region is subtracted by the corresponding adjustment concentration to obtain the concentration reduction degree corresponding to the dust over-limit region; and the concentration reduction degrees of each diffusion region are sequentially added, and the concentration reduction degree corresponding to the dust over-limit region is added to obtain the total concentration reduction degree.

[0121] In the step S604, the hosts include marlin and whale; a random number corresponding to each marlin is obtained and a rounding operation is performed, if the random number after rounding is 0, the host parasitized by the marlin is a whale, if the random number after rounding is 1, the host parasitized by the marlin is a flag fish; the marlin effectively guides the search direction by parasitizing the host.

[0122] In the step S605, the fitness corresponding to the position of each marlin is calculated, and the position of the marlin corresponding to the largest fitness value is marked as .

[0123] If the parasitized host is a whale, the calculation method of the updated marlin position includes:

[0124] ;

[0125] ;

[0126] In the formula, is the position of the i th marlin after updating, is the position of the i th marlin before updating, is a search range adjustment coefficient, is a random number between 0 and 1, and e is a natural constant. If the parasitized host is a flag fish, the calculation method of the updated marlin position includes:

[0127]

[0128] ; In the formula,

[0129] is the position of the i th marlin before updating. ​

[0130] The expression of the switching probability is as follows: The new position is a position adjacent to the host position; the fitness corresponding to the new position is marked as adjacent fitness; the fitness corresponding to the current position of the fish is marked as current fitness; the adjacent fitness is compared with the current fitness; if the adjacent fitness is greater than or equal to the current fitness, the host is not switched; if the adjacent fitness is less than the current fitness, the host is switched; the expression of the new position is as follows: wherein, is the new position, is a random movement factor, is a movement step length, is a limiting factor for limiting the movement factor, and in the embodiment, preferably is 0.2, is a random number between 0 and 1, , , is the position of a randomly selected fish.

[0131] The method for updating the position of the fish switching the host is consistent with the method for updating the position of each fish in step S605.

[0132] It should be understood that the reason for calculating the switching probability is that, in the early iteration period, the fish will frequently evaluate the environment around the host to determine whether the host needs to be switched due to the lack of food in the region; in the later iteration period, the fish will reduce the need to switch the host due to the sufficient food in the region, which is more consistent with the living habits of the fish, and thus the switching probability is linearly decreasing.

[0133] It should be noted that the purpose of switching the host is to indicate that the environment around the host is poor when the adjacent fitness is less than the current fitness, and the fitness of the new position is low, that is, the current host position may have approached a local optimum, and following the current host may not bring significant improvement, and thus by switching the host, the fish can jump out of the current local region, explore a wider solution space, increase the opportunity to find a global optimal solution, and avoid all individuals gathering in the same region, increase the diversity of the population, and make the algorithm have stronger adaptability and robustness.

[0134] In step S607, the method for updating the position of the fish in the foraging stage includes the following steps.

[0135]

[0136] ;​​​

[0137] ;

[0138] ;

[0139] wherein, is the updated position of the i-th lamprey after the foraging stage, is the updated position of the i-th lamprey after switching the host, is the global optimal position, is the moving distance of the i-th lamprey in the foraging stage, is the volume of the host parasitized by the i-th lamprey, is the lamprey factor for limiting the position of the lamprey, , is the volume of the i-th lamprey, is the random number between 0 and 1.

[0140] It should be noted that the reason for adopting the lamprey optimization algorithm to formulate the linkage control strategy is that the lamprey optimization algorithm has strong flexibility and adaptability, can define the fitness function according to the specific device linkage control demand, and flexibly cope with different device parameter control problems; and has excellent global search ability, can explore in a wide search space through the lamprey parasitic host to constantly update the position, improve the probability of finding the global optimal solution; at the same time, the host switching and foraging mechanism is adopted, which can effectively overcome the problem of local optimum and speed up the convergence speed of the algorithm; in addition, the requirement for computing resources is low, the result is strong in interpretability, and the application scope is wide.

[0141] In this embodiment, the coal preparation plant area is subdivided, the dust concentration of each area is monitored in real time, and the area exceeding the standard is evaluated, while considering the influence of multiple environmental parameters and equipment operation parameters on dust formation; the fuzzy algorithm is used to determine the dust exceeding standard reason, and the dust diffusion trend is predicted combined with the particle parameters to obtain the dust concentration of each position point in the dust diffusion range; and then a natural heuristic optimization algorithm is used to formulate a scientific and reasonable linkage response strategy; the dust concentration in the coal preparation plant is effectively controlled and reduced, the coordinated linkage control between different areas and equipment is realized, thereby improving the overall dust prevention and control efficiency, and the control strategy is more targeted, which can significantly reduce the influence of dust emission on the working environment and the surrounding ecology, to strengthen the response ability to environmental protection.

[0142] Embodiment 2

[0143] Please refer to Figure 3 ​As shown, the embodiment is further improved on the basis of embodiment 1. Dust has many hazards to human health, such as respiratory diseases, cancer risk, cardiovascular system impact, etc. When the personnel density in the area is large, the air flow in the area will be hindered, the air flow is poor, which leads to the decline of the diffusion and dilution effect of dust in the air, and the dust concentration in the area rises. In the personnel-intensive area, the exposure time of workers or operators is usually longer. Even if the dust concentration is relatively low in the overall environment, the long-term exposure of personnel in these areas will lead to higher inhalation and health risks. Therefore, the embodiment provides a coal selection full-process dust intelligent linkage control method, which further comprises:

[0144] Calculate the personnel density of each area and comprehensively evaluate the dust exceeding area according to the corresponding dust concentration.

[0145] The method for calculating the personnel density of each area comprises:

[0146] Collect the area image of each area. The area image is obtained by an image sensor installed in each area. At least one image sensor is installed in each area to ensure that the area image collected by all image sensors in the area can completely cover the area. A trained personnel recognition model is used to identify each area image and output the identification result, which is the number of personnel.

[0147] The specific training process of the personnel recognition model comprises:

[0148] Pre-collect multiple area images and digitally label each area image, which is the number of personnel. Divide the labeled area images into a training set and a test set. 70% of the area images are used as the training set and 30% of the area images are used as the test set. The personnel recognition model is trained using the training set and tested using the test set. A preset error threshold is output when the mean of the prediction error of all area images in the test set is less than the error threshold. The formula for calculating the mean of the prediction error is , wherein is the prediction error, w is the number of area images, is the prediction label corresponding to the wth group of area images, is the actual label corresponding to the wth group of area images, and U is the number of area images in the test set. The error threshold is preset according to the accuracy required by the personnel recognition model.

[0149] The above personnel recognition model is specifically a convolutional neural network model.

[0150] Multiply the x-coordinate of the diagonal point by the y-coordinate of the diagonal point to obtain the area of ​​the region; since each region is divided according to the monitoring range of the dust concentration sensor, the area of ​​each region is the same; add up the number of people corresponding to the area image of each region in turn to obtain the total number of people in each region; divide the total number of people in each region by the area of ​​the region to obtain the population density of each region.

[0151] A preset influence factor is used. The population density of each area is multiplied by the influence factor, and then added to the concentration threshold to obtain the new concentration threshold for each area. The dust concentration of each area is compared with the corresponding new concentration threshold. If the dust concentration is greater than or equal to the new concentration threshold, the corresponding area is marked as a dust exceeding the standard area. If the dust concentration is less than the new concentration threshold, the corresponding area is not marked. The influence factor is the degree of influence of population density on the concentration threshold, which is obtained by those skilled in the art through experiments and combined with practical experience.

[0152] This embodiment utilizes deep learning technology to achieve accurate population statistics in a region and calculate the population density in real time. Based on the population density, the dust concentration threshold of the corresponding region is dynamically adjusted, which can more effectively identify and assess areas with excessive dust. By fully considering the impact of population density on dust diffusion and on dust hazard assessment, it not only improves the accuracy of identifying areas with excessive dust but also significantly reduces worker health risks, thereby better protecting the occupational health of coal preparation plant workers and providing strong support for improving the working environment.

[0153] Furthermore, according to embodiments of this application, the processes described in the above-referenced flowcharts can be implemented as computer software programs. For example, this application provides a non-transitory machine-readable storage medium storing machine-readable instructions that can be executed by a processor to perform instructions corresponding to the method steps provided in this application, such as a coal preparation process dust intelligent linkage control method. When this computer program is executed by a central processing unit (CPU), it performs the functions defined in the method of this application.

[0154] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

[0155] In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A coal selection full-process dust intelligent linkage control method, characterized in that, The method comprises the following steps: dividing the coal preparation plant into regions according to different functional areas and the monitoring range of the dust concentration sensor; collecting the dust concentration of each region; evaluating the dust over-standard region according to the dust concentration of each region and the preset concentration threshold value; collecting the influence parameters of the dust over-standard region; determining the dust over-standard reason by using fuzzy logic reasoning according to the influence parameters; predicting the dust diffusion trend based on the influence parameters and the divided regions, specifically including: constructing a three-dimensional coordinate system with any vertex of the dust over-standard region as the origin, and the coordinates of the origin being (0, 0, 0); calculating the coordinates of the center of the dust over-standard region; presetting a stability coefficient library, and obtaining the corresponding stability coefficient from the stability coefficient library according to the wind speed, the environmental temperature and the environmental humidity; the stability coefficient library includes the wind speed, the environmental temperature and the environmental humidity, and the stability coefficient corresponding to the wind speed, the environmental temperature and the environmental humidity; if the wind speed, the environmental temperature or the environmental humidity in the influence parameters does not exist in the stability coefficient library, the corresponding stability coefficient is estimated by using an interpolation method; according to the wind direction, marking the region adjacent to the dust over-standard region in the direction corresponding to the wind direction as a diffusion region; setting a grid for the diffusion region, and the size of the grid being a unit volume; obtaining the coordinates of each position point in the diffusion region, and marking the coordinates as position coordinates; the position point is a grid node; calculating the Euclidean distance between each position coordinate and the coordinates of the center of the region as the diffusion distance corresponding to each position point; multiplying the diffusion distance of each position point by the stability coefficient to obtain the diffusion coefficient of each position point; and calculating the diffusion concentration corresponding to each position point according to the dust concentration of the dust over-standard region, the wind speed, the diffusion coefficient of each position point, the position coordinates and the coordinates of the center of the region; the diffusion concentration is the dust concentration diffused to each position point; obtaining the number of position points corresponding to each diffusion region; adding the diffusion concentration of each position point corresponding to each diffusion region in turn, and then dividing the sum by the number of position points corresponding to each diffusion region to obtain the average diffusion concentration of each diffusion region; adding the average diffusion concentration of each diffusion region to the corresponding dust concentration to obtain the total dust concentration of each diffusion region, and marking the total dust concentration as the diffusion total concentration; fusing the dust over-standard reason, the dust diffusion trend and the influence parameters, and formulating a linkage control strategy by using a natural heuristic optimization algorithm.

2. The intelligent linkage control method for coal preparation full process dust according to claim 1, characterized in that, The method for dividing the coal preparation plant into regions comprises: preliminarily dividing the coal preparation plant into regions according to different functional areas; and dividing each region obtained after the preliminary division into regions according to the monitoring range of the dust concentration sensor, each region being a rectangle; The method for evaluating the dust over-standard region comprises: calculating a concentration threshold value, and comparing the dust concentration of each region with the concentration threshold value; if the dust concentration is greater than or equal to the concentration threshold value, the corresponding region is marked as a dust over-standard region; if the dust concentration is less than the concentration threshold value, the corresponding region is not marked; the dust concentration is the number of suspended particulate matters in a unit volume of air; The method for calculating the concentration threshold comprises: collecting n historical dust concentrations, the historical dust concentrations being historical collected dust concentrations, n being an integer greater than 1; calculating the mean value and the standard deviation of the n historical dust concentrations respectively, and marking the mean value and the standard deviation as a historical mean value and a historical standard deviation respectively; multiplying the historical standard deviation by a coefficient a and adding the historical mean value to obtain the concentration threshold; wherein a [1, 3], and a is an integer.

3. The intelligent linkage control method for coal preparation full process dust according to claim 2, characterized in that, The influence parameters include environmental parameters, equipment parameters and particle parameters; The environmental parameters include wind speed, wind direction, environmental temperature and environmental humidity; the equipment parameters are operation parameters of each equipment; the particle parameters include particle size and particle humidity; the particle size is the diameter of a single particle; and the particle humidity is the amount of moisture contained in a single particle; The step of determining the dust over-standard reason comprises: Step S501: establishing a fuzzy set, and dividing each parameter in the influence parameters into a plurality of fuzzy sets; Step S502: converting the influence parameters into fuzzy sets through a fuzzification technique; the fuzzification is a process of converting accurate numerical values into fuzzy sets; and the fuzzy sets are described by membership functions; Step S503: defining fuzzy rules; Step S504: matching the fuzzified influence parameters with the fuzzy rules, performing fuzzy reasoning, obtaining a fuzzy reasoning result, and the fuzzy reasoning result being the membership degree of each dust over-standard reason; Step S505: performing a defuzzification operation on the fuzzy reasoning result to obtain a defuzzification result, and the defuzzification result being the dust over-standard reason; the defuzzification operation being: obtaining the membership degree of each dust over-standard reason according to the fuzzy reasoning result; presetting a membership degree threshold; comparing the membership degree of each dust over-standard reason with the membership degree threshold to obtain each dust over-standard reason whose membership degree is greater than or equal to the membership degree threshold.

4. The intelligent linkage control method for coal preparation full process dust according to claim 1, characterized in that, The method for calculating the region center coordinates comprises: Obtaining the coordinates of a diagonal point corresponding to the origin in the dust over-standard region, the diagonal point corresponding to the origin being a point symmetrical to the origin along a diagonal line of the region; dividing the horizontal coordinate of the diagonal point by 2 to obtain the horizontal coordinate of the region center coordinates; dividing the vertical coordinate of the diagonal point by 2 to obtain the vertical coordinate of the region center coordinates; and presetting a reference height as the height coordinate of the region center coordinates.

5. The intelligent linkage control method for coal preparation full process dust according to claim 4, characterized in that, The linkage control strategy is formulated by using a natural heuristic optimization algorithm, and the steps comprise: Step S601: presetting M parameter sets, setting different digital tags for different parameter sets, and marking the parameter sets as set tags; presetting a population size Z and a frequency threshold T; Step S602: initializing a population, defining the positions of the lampfish in the initialized population in a one-dimensional search space, the positions of the lampfish corresponding to the set tags one by one, and the iteration frequency t of the initialized population being 0; Step S603: determining a fitness function; Step S604: selecting a host for each lampfish; Step S605: updating the position of each lampfish; Step S606: calculating a switching probability, calculating a new position according to the switching probability, and updating the position of the lampfish again for the lampfish switching the host; Step S607: each lampfish entering a foraging stage, and updating the position of each lampfish. Step S608: Let the iteration number i = i + 1 , jump back to step S604; Step S609: Looping step S604 to step S608 until The loop ends at this time, and step S610 is entered. Step S610: calculate the fitness corresponding to the position of each lanternfish, sort all fitnesses from large to small, obtain the position of the lanternfish corresponding to the fitness ranked first, obtain the parameter set corresponding to the set label according to the obtained position of the lanternfish, and take the parameter set as the linkage control strategy.

6. The intelligent linkage control method for coal preparation full process dust according to claim 5, characterized in that, In step S601, the range of each operating parameter corresponding to each device in the diffusion area and the dust over-standard area is obtained, a value is randomly selected from each range, and a parameter set is constructed, and a total of M parameter sets are constructed; In the step S602, the population is initialized , including Z number of lampreys, is the Zth lamprey, Z is the number of crucian carp in the initialized population; the range of the set label and the range of the one-dimensional search space are both ; In the step S603, the expression of the fitness function is: wherein, is the fitness, is the total concentration decrease. The method for obtaining the total concentration reduction degree comprises: The method for obtaining the total concentration reduction degree comprises:

7. The intelligent linkage control method for coal preparation full process dust according to claim 6, characterized in that, In the step S604, the host includes a sailfish and a whale; a random number corresponding to each oarfish is obtained and a rounding operation is performed, if the rounded random number is 0, the host of the oarfish parasitism is a whale, if the rounded random number is 1, the host of the oarfish parasitism is a sailfish; In the step S605, the fitness corresponding to the position of each lanternfish is calculated, and the position of the lanternfish corresponding to the maximum fitness value is marked as the optimal position of the lanternfish .

8. The intelligent linkage control method for a coal preparation full process dust according to claim 7, characterized in that, The method for obtaining the total concentration reduction degree comprises: The method for obtaining the total concentration reduction degree comprises:

9. The intelligent linkage control method for coal preparation full process dust according to claim 8, characterized in that, In step S606, the new position is a position adjacent to the host position; the fitness corresponding to the new position is calculated and marked as an adjacent fitness; the fitness corresponding to the current position of the lanternfish is marked as a current fitness; the adjacent fitness is compared with the current fitness; if the adjacent fitness is greater than or equal to the current fitness, the host is not switched; if the adjacent fitness is less than the current fitness, the host is switched; The method for updating the position of the lanternfish that switches the host again is consistent with the method for updating the position of each lanternfish in step S605. The method further comprises: calculating the personnel density of each area and comprehensively evaluating the dust over-standard area according to the corresponding dust concentration. The method for calculating the personnel density of each area comprises: An area image of each area is collected; a trained personnel recognition model is used to recognize each area image, and an identification result is output, wherein the identification result is the number of personnel; The horizontal coordinate of the diagonal point is multiplied by the vertical coordinate of the diagonal point to obtain the area of the region; the number of personnel corresponding to each area image corresponding to each area is sequentially added to obtain the total number of personnel in each area; and the total number of personnel in each area is divided by the area of the region to obtain the personnel density of each area. The horizontal coordinate of the diagonal point is multiplied by the vertical coordinate of the diagonal point to obtain the area of the region; the number of personnel corresponding to each area image corresponding to each area is sequentially added to obtain the total number of personnel in each area; and the total number of personnel in each area is divided by the area of the region to obtain the personnel density of each area. The preset influence factor is multiplied by the personnel density of each area, and the concentration threshold is added to obtain a new concentration threshold corresponding to each area; the dust concentration of each area is compared with the new concentration threshold corresponding thereto; if the dust concentration is greater than or equal to the new concentration threshold, the corresponding area is marked as a dust over-standard area; if the dust concentration is less than the new concentration threshold, the corresponding area is not marked.

Images