Method, device, medium and equipment for predicting dust concentration of transfer station

Abstract

The invention provides a transfer station dust concentration prediction method and device, a medium and equipment, and belongs to the technical field of dust concentration testing. The method comprises the following steps: acquiring a real-time dust concentration value of a target measurement point in a transfer station; acquiring a conveying parameter set of materials on an associated conveying belt for conveying the materials to the target measurement point, wherein the conveying parameter set comprises material attributes and material instantaneous flow rates at multiple moments in the future; predicting a dust concentration sequence of the target measurement point based on the real-time dust concentration value and the conveying parameter set, wherein the dust concentration sequence comprises dust concentration predicted values at multiple moments in the future; detecting whether a dust concentration prediction value exceeding a preset dust concentration threshold value exists in the dust concentration sequence or not; if yes, the conveying parameter set is adjusted, so that the dust concentration prediction value formed based on the adjusted conveying parameter set does not exceed the dust concentration threshold value. According to the invention, the dust concentration exceeding standard can be pre-judged and intervened in advance.

Description

Technical Field

[0001] The present application relates to the technical field of dust concentration testing, and in particular to a method, device, medium and equipment for predicting dust concentration at a transfer station. Background Art

[0002] In industries like steel and metallurgy, transfer stations serve as core nodes in the raw material transportation system, handling bulk materials like iron ore, coke, and coal between various belt conveyors and silos. Due to the impact of height differences and gravity during material unloading and transfer, transfer stations are prone to dust pollution. Dust not only contains harmful components like free silica, but long-term exposure can lead to occupational diseases like pneumoconiosis in workers. High dust concentrations can also pose explosion risks, seriously threatening production safety and environmental quality.

[0003] Dust pollution at transfer stations exhibits significant characteristics, specifically: 1. Dynamic superposition effect: Due to differences in particle size, humidity, and flow velocity, different types of materials (such as coking coal, PCI coal, and sintered ore) converge within a closed space. Dust emissions do not simply add up linearly, but rather exhibit nonlinear coupling. For example, when fine coal dust and coarse mineral dust mix and disperse, airflow disturbances create a more complex concentration distribution, increasing the difficulty of pollution control. 2. Transient peak risk: The impact of falling materials at discharge ports and belt transfer points is a major cause of dust outbreaks. 3. Monitoring lag and blind spots: Traditional monitoring relies on point-based sensors (such as laser scattering and membrane filter weighing). These sensors can only collect historical concentration data at fixed locations and are unable to predict the potential pollution contribution of materials that have not yet arrived (such as those entering the transfer area). By the time the sensor returns a high concentration signal, the dust has already spread to the work area, creating a "passive response" dilemma.

[0004] Existing dust concentration monitoring and control programs have obvious limitations: 1. Response lag: Using a fixed concentration limit (such as 50mg / m³) as the trigger threshold, when the concentration is detected to be exceeded, high-concentration dust has already continued to spread. Even if ventilation and dust reduction measures are immediately initiated, workers will inevitably be exposed to dangerous environments, and health risks cannot be completely avoided. 2. Rough measures: When the conveyor belts in the transfer station are operating at high loads, even if the dust removal effect of the relevant dust removal equipment is turned to the maximum value, there is still a risk of excessive dust concentration. In this case, once the concentration exceeds the standard, material transportation is forcibly terminated without considering the coordinated response requirements of upstream and downstream equipment (such as belt conveyor deceleration, silo buffering, etc.), which can easily lead to secondary problems such as material accumulation and equipment impact damage, resulting in additional production losses.

[0005] Therefore, in view of the dynamic and instantaneous nature of dust pollution in transfer stations and the defects of existing monitoring methods, it is urgent to build an intelligent monitoring solution that can predict pollution trends in advance, accurately cover risk areas, and reserve response windows for prevention and control measures, so as to achieve efficient coordination between active prevention and control of dust pollution and safe production. Summary of the Invention

[0006] The purpose of this application is to provide a method, device, medium and equipment for predicting dust concentration in a transfer station to solve at least one of the above technical problems.

[0007] In a first aspect, the present application provides a method for predicting dust concentration in a transfer station, the method comprising: Obtain real-time dust concentration values ​​at target measurement points within the transfer station, where the target measurement points are located inside the material discharge port seal, at the crusher outlet, or in the inspection channel; Acquire a set of conveying parameters of a material on an associated conveyor belt conveying the material to the target measurement point, the set of conveying parameters including material properties and instantaneous flow rates of the material at multiple future moments; Predicting a dust concentration sequence at the target measurement point based on the real-time dust concentration value and the transport parameter set, wherein the dust concentration sequence includes predicted dust concentration values ​​at multiple future moments; Detecting whether there is a dust concentration prediction value exceeding a preset dust concentration threshold in the dust concentration sequence; If so, the transport parameter set is adjusted so that the dust concentration prediction values ​​in the dust concentration sequence formed based on the adjusted transport parameter set do not exceed the dust concentration threshold.

[0008] Optionally, the predicting the dust concentration sequence of the target measurement point based on the real-time dust concentration value and the transport parameter set includes: Selecting a target prediction function that matches the target measurement point from a plurality of preset dust concentration prediction functions; Determining parameter values ​​of associated parameters in the target prediction function according to the spatial characteristics of the target measurement point and the transport parameter set; The dust concentration sequence of the target measurement point is predicted based on the real-time dust concentration value, the transport parameter set, and a target prediction function that determines parameter values ​​of associated parameters.

[0009] Optionally, adjusting the transport parameter set so that the dust concentration prediction values ​​in the dust concentration sequence formed based on the adjusted transport parameter set do not exceed the dust concentration threshold value includes: Adjusting the value of the associated parameter in the target prediction function to a maximum constraint value, wherein the maximum constraint value is the value of the associated parameter corresponding to the case where the maximized dust removal measure is initiated at the target measurement point; Inversely deriving the material limit flow rate based on the real-time dust concentration value and the target prediction function under the maximum constraint value, so that the dust concentration prediction values ​​in the dust concentration sequence formed under the material limit flow rate do not exceed the dust concentration threshold value; The associated conveyor belt is controlled to convey the material to the target measurement point according to the material restricted flow rate, and a maximum dust removal measure is initiated at the target measurement point.

[0010] Optionally, the associated conveyor belts include multiple ones, and the controlling the associated conveyor belts to convey materials to the target measurement point according to the material limit flow rate includes: selecting one or several associated conveyor belts that can reduce the instantaneous flow rate of the material from the multiple associated conveyor belts as the target conveyor belts; controlling the target conveyor belts to convey materials to the target measurement point according to the material limit flow rate.

[0011] Optionally, the associated conveyor belts include a plurality of belts, and controlling the associated conveyor belts to convey the material to the target measurement point according to the material restricted flow rate includes: Calculate the influence coefficient of the material on each associated conveyor belt on the dust concentration; Selecting at least one associated conveyor belt whose influence coefficient exceeds a preset coefficient threshold as a target conveyor belt; The target conveying belt is controlled to convey the material to the target measuring point according to the material limit flow rate.

[0012] Optionally, before selecting a target prediction function that matches the target measurement point from a plurality of preset dust concentration prediction functions, the method further includes: Performing simulation based on the spatial characteristics of the target measurement point to construct a dust concentration prediction function that matches the target measurement point; Obtaining a historical dust concentration value set and a historical transport parameter set at the target measurement point; The dust concentration prediction function is fitted and trained based on the historical dust concentration value set and the historical transportation parameter set to determine the adaptive parameter values ​​of the dust concentration prediction function under different material transportation historical information.

[0013] Optionally, the method further includes: acquiring material transportation planning information related to the transfer station; and identifying an associated conveyor belt corresponding to the target measurement point from the material transportation planning information.

[0014] Optionally, after adjusting the conveying parameter set so that the dust concentration prediction values ​​in the dust concentration sequence formed based on the adjusted conveying parameter set do not exceed the dust concentration threshold, it also includes: when the duration of the associated conveying belt transporting materials to the target measurement point according to the adjusted conveying parameter set reaches a first duration, the conveying parameter set is restored to the conveying parameter set before adjustment.

[0015] In a second aspect of the present application, a device for predicting dust concentration in a transfer station is provided, the device comprising: A dust concentration detection module is used to obtain real-time dust concentration values ​​at target measurement points within the transfer station. The target measurement points are set inside the sealing cover of the drop port, the crusher outlet, or the inspection channel; A conveying parameter set acquisition module is used to acquire a conveying parameter set of a material on an associated conveyor belt that conveys the material to the target measurement point, wherein the conveying parameter set includes material properties and instantaneous material flow rates at multiple future moments; a dust concentration prediction module, configured to predict a dust concentration sequence at the target measurement point based on the real-time dust concentration value and the transport parameter set, wherein the dust concentration sequence includes predicted dust concentration values ​​at multiple future moments; The parameter adjustment module is used to detect whether there is a dust concentration prediction value exceeding a preset dust concentration threshold in the dust concentration sequence; if so, adjust the transportation parameter set so that the dust concentration prediction values ​​in the dust concentration sequence formed based on the adjusted transportation parameter set do not exceed the dust concentration threshold.

[0016] In a third aspect of the present application, a computer-readable storage medium is provided, on which executable instructions are stored. When the executable instructions are executed by a processor, the processor executes the method described in any embodiment of the present application.

[0017] In a fourth aspect of the present application, an electronic device is provided, comprising: one or more processors; and a memory for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors execute the method as described in any one of the embodiments of the present application.

[0018] The transfer station dust concentration prediction method, device, medium and equipment in this application have the following beneficial effects: 1. Based on the real-time dust concentration values ​​obtained through real-time monitoring of the target measurement points, combined with the material properties on the associated conveyor belt and the conveying parameter set such as the instantaneous material flow rate at multiple moments in the future, the dust concentration sequence over a period of time is predicted. Based on this dust concentration sequence, it can be determined whether there is a risk of exceeding the dust concentration standard within a preset period of time in the future, thereby achieving early prediction of pollutant exceeding the standard.

[0019] 2. When it is identified that the dust concentration prediction value exceeds the corresponding dust concentration threshold, the conveying parameter set is adjusted in advance so that the dust concentration prediction values ​​in the dust concentration sequence formed based on the adjusted conveying parameter set do not exceed the dust concentration threshold, so that relevant staff can intervene in time to avoid the occurrence of dust concentration exceeding the standard. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope of the present application.

[0021] Figure 1 A schematic flow chart of a method for predicting dust concentration at a transfer station in one embodiment; Figure 2 A schematic diagram of a process for predicting a dust concentration sequence at a target measurement point based on real-time dust concentration values ​​and a transport parameter set in one embodiment; Figure 3 A schematic diagram of a process for adjusting a transport parameter set in one embodiment so that dust concentration prediction values ​​in a dust concentration sequence formed based on the adjusted transport parameter set do not exceed a dust concentration threshold value; Figure 4 A flowchart of a prediction function construction process in one embodiment is shown; Figure 5 2. It is a schematic structural diagram of a dust concentration prediction device for a transfer station in one embodiment; Figure 6 A schematic structural diagram of a dust concentration prediction device for a transfer station in another embodiment; Figure 7 A schematic diagram of the structure of dust concentration prediction at a transfer station in another embodiment; Figure 8 FIG. 1 is a schematic structural diagram of an electronic device in an embodiment. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solutions and advantages of this application more clearly understood, the present application is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0023] All terms (including technical and scientific terms) used in this application have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0024] For example, the terms "first," "second," etc. used in this application may be used herein to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish a first element from another element.

[0025] For example, the terms "include", "comprising", etc. used in this application indicate the existence of features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0026] This application provides a method for predicting dust concentration in a transfer station, such as Figure 1 As shown, the method includes: Step 110: Obtain the real-time dust concentration value of the target measurement point in the transfer station.

[0027] In this embodiment, the target measurement point is set inside the sealing cover of the material discharge port, at the crusher outlet, or in the inspection channel. Multiple measurement points can be set up in the transfer station, and these measurement points can be located at various points in the transfer station, such as the sealing cover of the material discharge port, the crusher outlet, the inspection channel, and any other suitable location.

[0028] The dropout is the point where materials fall from upstream equipment (such as silos or conveyors) to downstream conveyors / chutes. The high-speed impact of the materials (typically 5-8 m / s) generates a significant amount of dust, making it a key dust source within transfer stations. To minimize dust spillage, the dropout is often equipped with a sealed cover, creating a relatively enclosed space. During the crushing process, materials collide and squeeze against each other, generating a significant amount of fine dust. The crusher outlet is typically connected to a discharge chute, where dust escapes as the materials fall. The airflow at the outlet is highly turbulent (due to the slightly elevated temperature of the crushed material, creating a weak updraft), resulting in a wide dust dispersion. Inspection corridors are the paths used by workers or equipment for routine inspections of equipment (conveyors, valves, and sensors). These corridors are typically located along both sides of the conveyor, with a width of 0.8-1.2 m and a height of 2-2.5 m (ensuring that personnel walk upright). While there are no direct dust sources within the corridor, dust concentration is closely related to ventilation conditions (natural or mechanical) due to the influence of upstream dust sources such as the dropout and crusher. There may be eddy current areas in the channel (such as behind the belt support and in the corners of the wall), where dust easily accumulates, creating high-risk areas for long-term exposure of personnel.

[0029] Dust sensors are deployed at these measurement points, which measure the real-time dust concentration at the corresponding location. These dust sensors can be any suitable measuring device, such as a distributed laser dust sensor or a beta-ray absorption dust meter. These sensors can wirelessly transmit the measured real-time dust concentration values ​​to an electronic device. The electronic device receives the information uploaded by each dust sensor in real time, parses it to extract the real-time dust concentration value, the dust sensor's identifier, and a timestamp. Based on the correspondence between this identifier and the measurement point, the device can determine the specific measurement point and time at which the real-time dust concentration value was recorded.

[0030] In one embodiment, before step 110, the method further includes: obtaining material transportation planning information related to the transfer station; and identifying an associated conveyor belt corresponding to the target measurement point from the material transportation planning information.

[0031] Material conveyor planning information is structured data that includes the transfer station's belt scheduling plan, material types, flow requirements, time period divisions, and other content for a specific period of time. This provides a time reference for associated belt identification and parameter recovery. The corresponding associated conveyor belt can be determined from this material conveyor planning information.

[0032] Step 120 : Acquire a set of conveying parameters of the material on the associated conveyor belt that conveys the material to the target measurement point.

[0033] In this embodiment, the conveying parameter set includes material properties and the instantaneous flow rate of the material at multiple moments in the future. The associated conveyor belt refers to a belt conveyor that directly or indirectly transports materials to the area where the target measurement point is located, and its conveying behavior will affect the dust concentration at the target measurement point. The discharge section of the directly associated belt conveyor is directly connected to the equipment where the target measurement point is located, and the indirectly associated belt conveyor may be a device that needs to be transferred and finally enter the target measurement point. For example, when the target measurement point is at the drop port, the associated conveyor belt may be the upstream belt of the drop port and the belt conveyor that transports materials with the upstream belt; when the target measurement point is in the crusher, its associated conveyor belt includes the crusher's feed belt and the belt conveyor that transfers materials to the feed belt.

[0034] The conveying parameter set, a collection of parameters that describes the conveying behavior of the associated conveyor belt and the characteristics of the transported material, is the core input for predicting dust concentration. It can include material properties (static characteristics) and instantaneous material flow rate (dynamic characteristics). Material properties refer to the inherent physical characteristics of the material that influence dust generation and dispersion. They reflect the material's inherent physical characteristics and influence its dust generation potential. Instantaneous material flow rate (dynamic characteristics) reflects the amount of material conveyed per unit time and influences dust generation intensity. Its units are typically "tons per hour (t / h)" or "kilograms per second (kg / s)." Material properties can include one or more of the following: material type, particle size distribution, moisture content, density, etc. Materials can include iron ore, coke, sintered ore, and PCI coal. Different materials exhibit varying degrees of hardness and brittleness (e.g., coke is highly brittle and more prone to dust generation during crushing / impact). Particle size distribution reflects the size range and proportion of material particles (e.g., 30% for fine particles <1 mm and 50% for medium particles 1-5 mm). A higher proportion of fine particles indicates greater dust generation. Material humidity reflects the moisture content (e.g., 8% for coke and 12% for iron ore). Higher humidity indicates stronger interparticle cohesion and reduced dust emission. Material density indicates the mass per unit volume (e.g., 4.8 t / m³ for iron ore and 0.8 t / m³ for coke). Density influences the impact strength of a falling material (denser materials experience greater impact and generate more dust). Instantaneous material flow can be measured and stored in real time using belt scales and other related monitoring equipment.

[0035] The system pre-plans and stores the material properties and instantaneous material flow of the materials transported by each belt conveyor. After determining the associated conveyor belt, the conveying parameter set of the material transported on the associated conveyor belt can be obtained.

[0036] Step 130 : predicting a dust concentration sequence of a target measurement point based on the real-time dust concentration value and the transport parameter set.

[0037] The dust concentration sequence is a time series composed of the dust concentration prediction values ​​of the target measurement point at multiple discrete moments in the future, reflecting the changing trend of dust concentration over time. The dust concentration sequence contains the dust concentration prediction values ​​at multiple moments in the future, and these multiple moments in the future are moments within the prediction time window. The prediction time window covers the future preset duration, and the starting moment is the current moment. The time length of the future preset duration is a preset fixed length, such as 10 minutes, 20 minutes, 30 minutes, 1 hour, 2 hours, 4 hours, or any other appropriate duration. Taking the current moment as t0, the prediction step length is (For example, 1 minute), the number of dust concentration prediction values ​​in the dust concentration sequence is n, that is, the dust concentration sequence D for the next n moments is expressed as , where d(t i ) is the time t i Predicted value of dust concentration (unit: mg / m 3 ).

[0038] A prediction model and / or prediction function for dust concentration prediction is pre-built in the electronic device. The prediction model may specifically be a long short-term memory network (LSTM) model.

[0039] Taking the LSTM model as an example, the electronic device pre-collects a large amount of sample training data. This sample training data consists of pre-processed multivariate time series data at each measurement point, collected historically or generated through generative adversarial network model simulation. This multivariate time series data includes dust concentration values, corresponding conveying parameter sets (such as instantaneous material flow rate, material type, particle size distribution, material moisture, material density, etc.), and spatial characteristics of each measurement point (such as the spatial structure of the measurement point, wind speed, temperature, humidity, ventilation status, and other environmental parameters). This sample training data is pre-processed through outlier cleaning, normalization, and time series segmentation to generate the sample training data.

[0040] This LSTM model utilizes a tensorized LSTM layer, upgrading the hidden state of traditional LSTMs to a tensor form. This allows for parallel processing of multivariate time series through tensor operations. The LSTM and MLP layers in the model dynamically adjust parameter sharing weights between tasks through an attention mechanism. The multi-task 1dCNN layer in the model extracts short-term features of local time series, such as sudden changes in dust concentration and short-term fluctuations in wind speed. Each task (measurement point) has its own upper-layer network but shares the underlying convolutional kernel.

[0041] In the iterative training process of the model, the historical dust concentration sequence data T in the sample training data and the local original data L are taken as input, and the dust concentration sequence { , …}. Where, T={ , … },L={ }, Indicates the dust concentration value measured at time tw, Indicates the dust concentration value corresponding to the i-th measurement point at time t+k (which can also be the measured dust concentration value), t represents time, w and k can be the time window size, for example, 10 to 30 minutes; It represents the predicted value of dust concentration at the output of the i-th measurement point at time t+k.

[0042] For each iteration's dust concentration sequence, the corresponding loss function is called to calculate the loss value. Based on the calculated loss value, the corresponding parameters are adjusted. Iterative training is performed again using the adjusted parameters until the calculated loss value is less than the preset loss threshold, or the number of iterations reaches the preset threshold. After completing the iterative training, a trained dust concentration prediction model is finally obtained.

[0043] When using the dust concentration prediction model to predict dust concentration sequences, the real-time dust concentration value, the conveying parameter set, the spatial characteristics of the target measurement point, and the historical dust concentration values ​​(such as the dust concentration values ​​measured / calculated within the previous w time windows (such as 30 minutes, 60 minutes)) can be used as the model input. After being processed through the LSTM layer, MLP layer, 1dCNN layer, etc. in the dust concentration prediction model, the dust concentration sequence for each target measurement point can be output.

[0044] The dust concentration prediction function can be based on one or a combination of a fluid dynamics diffusion model (such as the Gaussian diffusion model), an impact dust prediction model, or related empirical formulas. Understandably, the spatial characteristics of different measurement points vary significantly. For example, the spatial characteristics of measurement points within the material discharge port seal, at the crusher outlet, and in the inspection channel are significantly different. Based on this, the electronic device has a corresponding prediction function for each type of measurement point.

[0045] For example, the dust concentration in the inspection channel follows the convection-diffusion equation. Based on this convection-diffusion equation and the spatial characteristics of the inspection channel, a prediction function that matches the inspection channel can be constructed. The inside of the material port seal and the crusher outlet are more consistent with the impact dust prediction model. Based on this impact dust prediction model and the spatial characteristics of the inside of the material port seal and the crusher outlet, prediction functions suitable for these areas can be constructed.

[0046] By taking the real-time dust concentration value, the transport parameter set, and the spatial characteristics of the target measurement point as inputs of the corresponding prediction model and / or prediction function, a dust concentration sequence of the target measurement point can be output accordingly.

[0047] Step 140 : Detect whether there is a dust concentration prediction value exceeding a preset dust concentration threshold in the dust concentration sequence.

[0048] In this embodiment, the dust concentration threshold is a critical concentration value set in the dust concentration monitoring and control at the transfer station to ensure operational safety, personnel health and production continuity. It is the core basis for determining whether dust pollution requires intervention. Its essence is to divide the "safe zone" and "risk zone" through quantitative indicators, and guide the system to take early warning, control and other measures when the dust concentration reaches or exceeds this value. The dust concentration thresholds corresponding to different measurement points are not necessarily the same. The electronic device has pre-set a correspondence table between different measurement points and dust concentration thresholds. According to the target measurement point, the matching dust concentration threshold can be found from the correspondence table.

[0049] Compare each dust concentration prediction value in the dust concentration sequence with the corresponding dust concentration threshold to identify whether any dust concentration prediction value exceeds the dust concentration threshold. If so, it means that the dust concentration at the target measurement point will exceed the standard at some point in the future, and intervention is required.

[0050] Step 150: If present, adjust the transport parameter set so that the dust concentration prediction values ​​in the dust concentration sequence formed based on the adjusted transport parameter set do not exceed the dust concentration threshold.

[0051] Optionally, if a prediction indicates that dust concentration is about to exceed the standard, the timing and specific parameters for adjusting the conveying parameter set can be determined. For example, the instantaneous material flow rate can be reduced to achieve rapid dust control, supplemented by optimizing static parameters (material properties). Ultimately, the effectiveness of the adjustment can be verified using the predictive model. Adjustments should be made as early as possible to avoid delays that increase difficulty.

[0052] For example, the instantaneous material flow rate can be reduced in steps to avoid material accumulation or equipment impact caused by a sudden drop in flow rate. For example: if the initial predicted concentration is 40mg / m³ (the threshold is 30mg / m³), first reduce the belt speed from 2.5m / s to 2.2m / s (the instantaneous material flow rate is reduced from 800t / h to 700t / h), and re-predict the concentration; if the dust concentration prediction value is still >30mg / m³ after adjustment, 3 If the dust concentration is still above the standard, the speed is reduced to 2.0 m / s (flow rate 600 t / h) until the predicted dust concentration values ​​are all ≤330 mg / m 3 .

[0053] If it does not exist (the dust concentration prediction values ​​in the dust concentration sequence are all less than the dust concentration threshold), material transportation will continue according to the set material transportation planning information without adjusting the transportation parameter set.

[0054] The transfer station dust concentration prediction method in this application, based on the real-time dust concentration value obtained by real-time monitoring of the target measurement point, combines the material properties on the associated conveyor belt and the material instantaneous flow rate at multiple moments in the future and other conveying parameter sets to predict the dust concentration sequence in the future. Based on the dust concentration sequence, it can be known whether there is a risk of exceeding the dust concentration standard within the preset time period in the future, thereby achieving early prediction of pollutant exceeding the standard. Furthermore, when it is identified that the dust concentration prediction value exceeds the corresponding dust concentration threshold, the conveying parameter set is adjusted in advance, so that the dust concentration prediction values ​​in the dust concentration sequence formed based on the adjusted conveying parameter set do not exceed the dust concentration threshold, so that relevant staff can intervene in time to avoid the occurrence of dust concentration exceeding the standard.

[0055] In one embodiment, Figure 2 As shown, the dust concentration sequence of the target measurement point is predicted based on the real-time dust concentration value and the transportation parameter set, including: Step 210 : Select a target prediction function that matches the target measurement point from a plurality of preset dust concentration prediction functions.

[0056] In this embodiment, the electronic device presets a variety of dust concentration prediction functions, each of which corresponds to one or more measurement points. It is understandable that for different types of locations such as the inside of the blanking port sealing cover, the crusher outlet, and the inspection channel, the dust generation and diffusion characteristics are significantly different, so different prediction functions need to be matched to ensure prediction accuracy. The electronic device performs feature classification based on the spatial characteristics of each measurement point, sets a prediction function for the measurement points with the same common spatial characteristics, and establishes a correspondence between the prediction function and the measurement point. Based on the correspondence, the prediction function that matches the target measurement point can be selected as the target prediction function. These prediction functions can be functions formed based on a combination of one or more of the following: power function, quadratic function, etc.

[0057] Step 220 : Determine the parameter values ​​of the associated parameters in the target prediction function according to the spatial characteristics of the target measurement point and the transport parameter set.

[0058] In this embodiment, spatial characteristics refer to spatial attributes, environmental, or geometric features of the physical environment at the measurement point that are relevant to dust diffusion and concentration distribution. These characteristics may include one or more of position and distance characteristics, spatial geometric characteristics, airflow and ventilation characteristics, surface and sedimentation characteristics, and spatial topological characteristics. Position and distance characteristics can be expressed as the spatial position of the measurement point relative to the dust source (e.g., the drop point of a conveyor or the starting point of a conveyor belt), as well as its distance from key equipment (e.g., fans or baffles). Spatial geometric characteristics refer to the geometric shape, size, or structure of the area where the measurement point is located, which influence the boundary conditions of dust diffusion. Airflow and ventilation characteristics refer to the airflow direction, wind speed, and ventilation method of the environment at the measurement point, which directly influence the direction and rate of dust diffusion. Surface and sedimentation characteristics refer to the surface properties (e.g., material and slope) surrounding the measurement point, which influence the dust sedimentation rate and the likelihood of secondary dust entrainment. Spatial topological characteristics refer to the overall layout or structural hierarchy of the area where the measurement point is located, such as whether it is located at a corner, intersection, or other special location. Some of these spatial characteristics can be determined through design drawings, on-site mapping, or 3D modeling, while others can be determined from the system's control parameters. Some of these spatial characteristics can be adjusted based on the operation of the dust removal equipment in the transfer station. For example, by activating the relevant dust removal equipment, the airflow and ventilation characteristics, material humidity, drop height, drop speed, etc. can be changed to reduce the dust concentration in the environment or reduce the rate at which the dust concentration increases.

[0059] The values ​​of the associated parameters in the corresponding preset functions vary depending on the spatial characteristics and transport parameter sets. Associated parameters refer to parameters in the prediction function that are directly related to the spatial characteristics of the measurement point (such as geometry, ventilation conditions, dust source layout) and / or the transport parameter set. These parameters must be individually calibrated based on the environmental characteristics and transport parameter set of the specific measurement point. Even if the same prediction function is applied to different measurement points, the associated parameter values ​​will vary due to the differences in spatial characteristics.

[0060] The associated parameters may include material-related parameters and / or space-related parameters. According to the pre-established correspondence between the spatial characteristics and the transport parameter set and the associated parameters, the parameter values ​​of the associated parameters in the current objective function may be queried or calculated.

[0061] For example, the pre-established prediction functions can be the following, each prediction being adapted to a different type of measurement point. For example, prediction function 1 is adapted to the measurement point inside the sealing cover of the drop port, prediction function 2 is adapted to the measurement point at the crusher outlet, and prediction function 3 is adapted to the measurement point at the inspection channel. The pre-established prediction functions are as follows: Prediction function 1: ; Prediction function 2: ; Prediction function 3: .

[0062] in, Indicates the tth i Dust concentration at the moment, Indicates that at the tth i+1 Dust concentration at the moment, Indicates that at t i The instantaneous flow rate of the material at the time t i+1 Time and t i The time interval at the moment is , 、 、 、 The concentration attenuation coefficient is calibrated experimentally, and its corresponding value varies under different spatial characteristics. For example, in the same space, the value with dust removal measures activated is smaller than the value without dust removal measures activated (different ventilation volumes); 、 、 Indicates the dust emission coefficient, which is related to spatial characteristics such as the falling speed and falling height of the material; Indicates the humidity correction factor, which is related to the humidity of the material. The higher the humidity, the The bigger; Indicates the material particle size correction coefficient. The smaller the particle size distribution of the material, the The bigger; It represents the air volume correction factor, which is determined based on various factors such as the channel cross-sectional area and channel ventilation volume in the environment.

[0063] Step 230 : predicting a dust concentration sequence of a target measurement point based on the real-time dust concentration value, the transport parameter set, and a target prediction function that determines the parameter values ​​of the associated parameters.

[0064] When the parameter values ​​of the associated parameters are determined, the dust concentration at each moment can be determined based on the above parameter values ​​and the corresponding dust concentration values ​​and the instantaneous flow rate of the material, thereby forming a corresponding dust concentration sequence.

[0065] In this embodiment, by matching a dedicated prediction function to each target measurement point and adapting the prediction function to different parameter values ​​based on different spatial characteristics, the calculated dust concentration prediction value is more accurate. Furthermore, using the preset function to predict dust concentration effectively reduces the complexity of dust concentration prediction and improves engineering practicality.

[0066] In one embodiment, Figure 3As shown, the transport parameter set is adjusted so that the dust concentration prediction values ​​in the dust concentration sequence formed based on the adjusted transport parameter set do not exceed the dust concentration threshold, including: Step 310: Adjust the values ​​of the associated parameters in the target prediction function to the maximum constraint values.

[0067] Step 320 , inversely derive the material flow restriction based on the real-time dust concentration value and the target prediction function under the maximum constraint value, so that the dust concentration prediction values ​​in the dust concentration sequence formed under the material flow restriction do not exceed the dust concentration threshold.

[0068] Step 330 : Control the associated conveyor belt to convey the material to the target measurement point according to the material restricted flow rate, and initiate a maximum dust removal measure at the target measurement point.

[0069] In this embodiment, the maximum constraint value is the value of the associated parameter that corresponds to the activation of the maximum dust removal measure at the target measurement point. In other words, the maximum constraint value is the limit value of the associated parameter when the maximum dust removal measure is activated at the target measurement point. Under this condition, dust expansion is minimized and dust concentration increases at the slowest rate. Different dust removal equipment is installed at different measurement points, each with different dust removal capabilities. Dust removal methods may include one or more of mechanical, pneumatic, and fan dust removal. For mechanical dust removal, a closed hood (such as a sealed guide chute) can be used to enclose the material drop area to reduce dust spillage. A scraper cleaner can be used to closely contact the belt surface to remove residual material and reduce secondary dust generated by falling material. A buffer chute can be installed at the feed inlet to reduce the material's falling velocity and minimize impact dust. For pneumatic dust removal, dust-laden air can be drawn into the enclosure through ducts, filtered through filter bags, and then discharged as clean air. Atomizing nozzles can be installed around the material drop point to absorb dust particles with a fine mist (suitable for non-flammable and explosive environments). An adjustable-volume fan automatically adjusts the exhaust volume based on real-time dust concentration to balance the negative pressure within the enclosure and prevent dust from escaping. A dust inlet can be installed at the top of the silo or at the feed inlet. The fan generates negative pressure, drawing floating dust into dust collection equipment (such as a cyclone dust collector). Axial fans or air ducts can be installed at appropriate locations in inspection corridors to create directional airflow, directing diffuse dust toward the dust collection equipment.

[0070] Based on the relationship between the value of the associated parameter and the spatial characteristics, combined with the dust removal capabilities of each dust removal method, the value corresponding to the associated parameter (i.e., the maximum constraint value) when the dust removal capability is maximized is determined.

[0071] After determining the maximum constraint value, based on the target prediction function, with the condition that the calculated dust concentration prediction values ​​do not exceed the corresponding dust concentration threshold, the material instantaneous flow rate is taken as an unknown number for reverse solution, and the appropriate material instantaneous flow rate is calculated. The calculated material instantaneous flow rate is used as the material limit flow rate.

[0072] Through the extreme constraints of associated parameters and flow reverse calculation, a balance between "safety compliance" and "production efficiency" is achieved. It is particularly suitable for industrial scenarios with large fluctuations in dust concentration and high prevention and control requirements.

[0073] In one embodiment, before selecting a target prediction function that matches the target measurement point from a plurality of preset dust concentration prediction functions, the above method further includes a process of constructing a prediction function. Figure 4 As shown, the process includes: Step 410 : Perform simulation based on the spatial characteristics of the target measurement point to construct a dust concentration prediction function that matches the target measurement point.

[0074] In this embodiment, CFD (computational fluid dynamics) is used to simulate the diffusion of dust within the target measurement point's space. The quantitative relationship between concentration and influencing factors (such as flow rate and height) is extracted, and the mathematical form of the prediction function is constructed based on this. Specifically, ANSYS Fluent or other related software can be used to construct a geometric model of the target measurement point (including details such as the dropout, sealing cover, observation window, and belt) and define boundary conditions. For example, the inner wall of the sealing cover is a no-slip boundary, the observation window is a pressure outlet (open to the atmosphere), and the dropout point is the dust source (with the particle size distribution set to be consistent with the material properties).

[0075] After establishing a geometric model of the target measurement point, multi-condition CFD simulation can be performed. Each condition is simulated and a time-varying curve of dust concentration is output for each condition. Each condition has corresponding variables, including a set of relevant conveying parameters such as instantaneous material flow rate, drop height, drop speed, ventilation volume, and material properties.

[0076] Regression analysis is performed on the simulation data to construct the initial form of the prediction function. For example, the three initial prediction functions mentioned above can be constructed.

[0077] Step 420: Obtain a historical dust concentration value set and a historical transport parameter set at the target measurement point.

[0078] Step 430 : performing fitting training on the dust concentration prediction function based on the historical dust concentration value set and the historical transportation parameter set, and determining adaptive parameter values ​​of the dust concentration prediction function under different material transportation history information.

[0079] Based on the initial prediction function, the electronic device further obtains the historical dust concentration value set measured at the measurement point, as well as the corresponding historical conveying parameter set and related spatial characteristics. It then fits the training set data using a relevant machine learning algorithm to solve the values ​​of the undetermined parameters in the prediction function under different operating conditions and verify the adaptability of the parameters under different historical information (such as high humidity and low flow). The machine learning algorithm can be a least squares set network search, with the goal of minimizing the mean square error between the calculated predicted value (i.e., the dust concentration predicted value) and the actual value (i.e., the historical dust concentration value). This allows the relationship between the associated parameters in the model, the spatial characteristics, and the conveying parameter set to be determined, resulting in the adaptive parameter values ​​of the dust concentration prediction function under different material conveying historical information.

[0080] In this embodiment, a prediction function for dust concentration is formed by constructing a function through simulation and training with historical data fitting, which can improve the accuracy of the prediction function construction.

[0081] In one embodiment, controlling the associated conveyor belts to convey materials to a target measuring point according to a material restricted flow rate includes: selecting one or more associated conveyor belts that can reduce the instantaneous flow rate of the material from a plurality of associated conveyor belts as target conveyor belts; and controlling the target conveyor belts to convey materials to a target measuring point according to the material restricted flow rate.

[0082] In this embodiment, the measurement point may include multiple associated conveyor belts, all of which are conveying material. For example, three conveyor belts may be combined in a silo and discharged from an outlet chute, ultimately affecting the dust concentration at the target measurement point. If dust concentration is predicted to exceed the standard, one or more of these three conveyor belts can be selected for control.

[0083] Furthermore, each conveyor belt typically conveys material according to a pre-designed instantaneous material flow rate. The instantaneous material flow rate on some conveyor belts can be adjusted, while on others it cannot. The electronic device adjusts the material flow rate on the associated conveyor belt that can reduce the instantaneous material flow rate, controlling it to convey material according to the calculated material limit flow rate. This material limit flow rate is within the allowable conveying flow rate range of the corresponding conveyor belt.

[0084] In one embodiment, controlling the associated conveyor belts to convey materials to the target measurement point according to the material restricted flow rate includes: calculating the influence coefficient of the material on each associated conveyor belt on the dust concentration; selecting at least one associated conveyor belt whose influence coefficient exceeds a preset coefficient threshold as the target conveyor belt; and controlling the target conveyor belt to convey materials to the target measurement point according to the material restricted flow rate.

[0085] In this embodiment, the influence coefficient is a parameter that quantifies the degree to which a change in the material flow of a single conveyor belt affects the dust concentration at a target measurement point. The larger the influence coefficient, the more significant the influence of the conveyor belt on the dust concentration.

[0086] For each associated conveyor belt at the measurement point, based on the target prediction function, the influence of each associated conveyor belt on the dust concentration is separated by the control variable method, and the corresponding influence coefficient is calculated based on the influence of each associated conveyor belt.

[0087] The coefficient threshold can be adaptively set in combination with relevant process requirements and historical data. After obtaining the influence coefficient of each associated conveyor belt, the associated conveyor belt corresponding to the influence coefficient exceeding the coefficient threshold is used as the target conveyor belt. The selected target conveyor belt is the conveyor belt that can reduce the instantaneous flow rate of the material.

[0088] For each selected target conveyor belt, flow is allocated to each associated conveyor belt based on the calculated material flow limit, so that the total flow of the allocated associated conveyor belts is adjusted to the material flow limit. Specifically, the allocated flow to each target conveyor belt can be allocated based on one or more factors such as the task priority of the corresponding conveyor belt, the minimum allowable flow rate, etc. The calculated flow reduction amount is allocated to the target conveyor belt, and precise control is achieved through the PLC system to adjust parameters such as the material conveying speed of the conveyor belt to ensure that the dust concentration value within a preset time period after the adjustment does not exceed the dust concentration threshold.

[0089] In this embodiment, by quantifying the influence weight of each belt, "precise positioning and targeted regulation" is achieved. In the multi-belt collaborative feeding scenario, the dust concentration can be efficiently controlled while minimizing interference with production.

[0090] In one embodiment, after adjusting the conveying parameter set so that the dust concentration prediction values ​​in the dust concentration sequence formed based on the adjusted conveying parameter set do not exceed the dust concentration threshold, it also includes: when the duration of the associated conveyor belt transporting materials to the target measurement point according to the adjusted conveying parameter set reaches a first duration, the conveying parameter set is restored to the conveying parameter set before adjustment.

[0091] In this embodiment, the first duration may be determined based on one or more factors such as the material transportation planning information and a dust concentration value measured at a future moment.

[0092] For example, if the instantaneous material flow rate is adjusted at 9:30 AM, and according to the material transportation planning information, it is necessary to ensure that the instantaneous material flow rate is restored to the set flow rate before 10:00 AM, the first time period may be 30 minutes. Furthermore, if it is detected that the dust concentration value at the target measurement point has dropped to a very low and safe value at a certain time before 10:00 AM, the conveying parameter set can be restored to the pre-adjustment conveying parameter set at that time, so that the associated conveyor belt will continue to transport materials according to the set conveying parameter set from that moment on.

[0093] By restoring the transport parameter set after the first period of operation, a balance can be struck between the temporary and planned nature of parameter adjustments, so that dust control can meet both real-time safety requirements and adapt to long-term production plans, thereby improving the coordination and efficiency of transfer station operations.

[0094] In one embodiment, Figure 5 As shown, a transfer station dust concentration prediction device is provided, which includes: The dust concentration detection module 510 is used to obtain the real-time dust concentration value of the target measurement point in the transfer station. The target measurement point is set in the sealing cover of the drop port, the crusher outlet or the inspection channel.

[0095] The conveying parameter set acquisition module 520 is used to obtain a conveying parameter set of the material on the associated conveyor belt that conveys the material to the target measurement point. The conveying parameter set includes material properties and instantaneous material flow rates at multiple future moments.

[0096] The dust concentration prediction module 530 is used to predict the dust concentration sequence of the target measurement point based on the real-time dust concentration value and the transportation parameter set. The dust concentration sequence includes the dust concentration prediction values ​​at multiple moments in the future.

[0097] The parameter adjustment module 540 is used to detect whether there is a dust concentration prediction value that exceeds a preset dust concentration threshold in the dust concentration sequence; if so, the transportation parameter set is adjusted so that the dust concentration prediction values ​​in the dust concentration sequence formed based on the adjusted transportation parameter set do not exceed the dust concentration threshold.

[0098] In one embodiment, the dust concentration prediction module 530 is also used to select a target prediction function that matches the target measurement point from a plurality of preset dust concentration prediction functions; determine the parameter values ​​of the associated parameters in the target prediction function according to the spatial characteristics of the target measurement point and the transport parameter set; and predict the dust concentration sequence of the target measurement point based on the real-time dust concentration value, the transport parameter set, and the target prediction function with the parameter values ​​of the associated parameters determined.

[0099] In one embodiment, the parameter adjustment module 540 is also used to adjust the value of the associated parameter in the target prediction function to the maximum constraint value, which is the value of the associated parameter corresponding to the case where the maximum dust removal measure is initiated at the target measurement point; based on the real-time dust concentration value and the target prediction function under the maximum constraint value, the material limit flow rate is inferred so that the dust concentration prediction values ​​in the dust concentration sequence formed under the material limit flow rate do not exceed the dust concentration threshold; the associated conveyor belt is controlled to transport the material to the target measurement point according to the material limit flow rate, and the maximum dust removal measure is initiated at the target measurement point.

[0100] In one embodiment, the parameter adjustment module 540 is further used to select one or more associated conveyor belts that can reduce the instantaneous flow of materials from multiple associated conveyor belts as target conveyor belts; and control the target conveyor belts to convey materials to the target measurement point according to the material limit flow.

[0101] In one embodiment, the parameter adjustment module 540 is also used to calculate the influence coefficient of the material on each associated conveyor belt on the dust concentration; select at least one associated conveyor belt whose influence coefficient exceeds a preset coefficient threshold as the target conveyor belt; and control the target conveyor belt to transport the material to the target measurement point according to the material limit flow rate.

[0102] In one embodiment, Figure 6 As shown, the above device also includes: The prediction function construction module 550 is used to simulate the spatial characteristics of the target measurement point to construct a dust concentration prediction function that matches the target measurement point; obtain the historical dust concentration value set and the historical transportation parameter set at the target measurement point; fit the dust concentration prediction function based on the historical dust concentration value set and the historical transportation parameter set to determine the adaptive parameter value of the dust concentration prediction function under different material transportation history information.

[0103] In one embodiment, Figure 7 As shown, the above device also includes: The associated conveyor belt determination module 560 is used to obtain material conveying planning information related to the transfer station; and identify the associated conveyor belt corresponding to the target measurement point from the material conveying planning information.

[0104] The parameter adjustment module 540 is further configured to restore the conveying parameter set to the pre-adjustment conveying parameter set when the duration for the associated conveying belt to transport materials to the target measurement point according to the adjusted conveying parameter set reaches a first duration.

[0105] In one embodiment, a computer-readable storage medium is provided, on which executable instructions are stored. When the instructions are executed by a processor, the processor executes the steps in the above-mentioned method embodiments.

[0106] In one embodiment, an electronic device is also provided, comprising one or more processors; a memory, wherein one or more programs are stored in the memory, wherein when the one or more programs are executed by one or more processors, the one or more processors execute the steps in the above-mentioned method embodiments.

[0107] In one embodiment, Figure 8 , which shows a schematic diagram of the structure of an electronic device for implementing an embodiment of the present application. The electronic device includes a central processing unit (CPU) 801, which can perform various appropriate actions and processes based on programs stored in a read-only memory (ROM) 802 or programs loaded from a storage unit 808 into a random access memory (RAM) 803. The RAM 803 also stores various programs and data required for the operation of the electronic device. The CPU 801, ROM 802, and RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0108] The following components are connected to the I / O interface 805: an input section 806 including a keyboard, mouse, and the like; an output section 807 including devices such as a cathode ray tube (CRT), a liquid crystal display (LCD), and speakers; a storage section 808 including a hard disk; and a communication section 809 including a network interface card such as a LAN card or a modem. The communication section 809 performs communication processing via a network such as the Internet. A drive 810 is also connected to the I / O interface 805 as needed. Removable media 811, such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, is installed in the drive 810 as needed, so that computer programs read from the removable media can be installed in the storage section 808 as needed.

[0109] In particular, according to embodiments of the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present application include a computer program product comprising a computer-readable medium carrying instructions. In such embodiments, the instructions can be downloaded and installed from a network via the communication portion 809 and / or installed from removable media 811. When the instructions are executed by the central processing unit (CPU) 801, the various method steps described in this application are performed.

[0110] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some or all of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application.

[0111] Furthermore, those skilled in the art will appreciate that although some embodiments herein include certain features included in other embodiments but not others, combinations of features from different embodiments are intended to be within the scope of this application and to form different embodiments. For example, all of the above embodiments may be used in any combination. The information disclosed in this background section is intended solely to enhance understanding of the overall background of this application and should not be construed as an admission or any form of implication that such information constitutes prior art known to those skilled in the art.

Claims

1. A method for predicting dust concentration at a transfer station, characterized in that: The method comprises: Obtain real-time dust concentration values ​​at target measurement points within the transfer station, where the target measurement points are located inside the material discharge port seal, at the crusher outlet, or in the inspection channel; Acquire a set of conveying parameters of a material on an associated conveyor belt conveying the material to the target measurement point, the set of conveying parameters including material properties and instantaneous flow rates of the material at multiple future moments; Predicting a dust concentration sequence at the target measurement point based on the real-time dust concentration value and the transport parameter set, including: selecting a target prediction function that matches the target measurement point from a plurality of preset dust concentration prediction functions, determining parameter values ​​of associated parameters in the target prediction function based on spatial characteristics of the target measurement point and the transport parameter set, and predicting a dust concentration sequence at the target measurement point based on the real-time dust concentration value, the transport parameter set, and the target prediction function having determined the parameter values ​​of the associated parameters, wherein the dust concentration sequence includes predicted dust concentration values ​​at a plurality of future moments; Detecting whether there is a dust concentration prediction value exceeding a preset dust concentration threshold in the dust concentration sequence; If so, the transport parameter set is adjusted so that the dust concentration prediction values ​​in the dust concentration sequence formed based on the adjusted transport parameter set do not exceed the dust concentration threshold.

2. The method according to claim 1, characterized in that The adjusting the transport parameter set so that the dust concentration prediction values ​​in the dust concentration sequence formed based on the adjusted transport parameter set do not exceed the dust concentration threshold value includes: Adjusting the value of the associated parameter in the target prediction function to a maximum constraint value, wherein the maximum constraint value is the value of the associated parameter corresponding to the case where the maximized dust removal measure is initiated at the target measurement point; Inversely deriving the material limit flow rate based on the real-time dust concentration value and the target prediction function under the maximum constraint value, so that the dust concentration prediction values ​​in the dust concentration sequence formed under the material limit flow rate do not exceed the dust concentration threshold value; The associated conveyor belt is controlled to convey the material to the target measurement point according to the material restricted flow rate, and a maximum dust removal measure is initiated at the target measurement point.

3. The method according to claim 2, characterized in that The associated conveyor belts include a plurality of belts, and controlling the associated conveyor belts to convey the material to the target measurement point according to the material restricted flow rate includes: Select one or more associated conveyor belts that can reduce the instantaneous flow of materials from multiple associated conveyor belts as target conveyor belts; The target conveying belt is controlled to convey the material to the target measuring point according to the material limit flow rate.

4. The method according to claim 2, characterized in that The associated conveyor belts include a plurality of belts, and controlling the associated conveyor belts to convey the material to the target measurement point according to the material restricted flow rate includes: Calculate the influence coefficient of the material on each associated conveyor belt on the dust concentration; Selecting at least one associated conveyor belt whose influence coefficient exceeds a preset coefficient threshold as a target conveyor belt; The target conveying belt is controlled to convey the material to the target measuring point according to the material limit flow rate.

5. The method according to claim 1, wherein Before selecting a target prediction function that matches the target measurement point from a plurality of preset dust concentration prediction functions, the method further includes: Performing simulation based on the spatial characteristics of the target measurement point to construct a dust concentration prediction function that matches the target measurement point; Obtaining a historical dust concentration value set and a historical transport parameter set at the target measurement point; The dust concentration prediction function is fitted and trained based on the historical dust concentration value set and the historical transportation parameter set to determine the adaptive parameter values ​​of the dust concentration prediction function under different material transportation historical information.

6. The method according to any one of claims 1 to 5, characterized in that The method further comprises: Obtaining material transportation planning information related to the transfer station; identifying an associated conveyor belt corresponding to the target measurement point from the material conveyance planning information; After adjusting the transport parameter set so that the dust concentration prediction values ​​in the dust concentration sequence formed based on the adjusted transport parameter set do not exceed the dust concentration threshold, the method further includes: When the duration of the associated conveyor belt transporting the material to the target measurement point according to the adjusted conveyor parameter set reaches a first duration, the conveyor parameter set is restored to the conveyor parameter set before adjustment.

7. A dust concentration prediction device for a transfer station, characterized in that: The device comprises: A dust concentration detection module is used to obtain real-time dust concentration values ​​at target measurement points within the transfer station. The target measurement points are set inside the sealing cover of the drop port, the crusher outlet, or the inspection channel; A conveying parameter set acquisition module is used to acquire a conveying parameter set of a material on an associated conveyor belt that conveys the material to the target measurement point, wherein the conveying parameter set includes material properties and instantaneous material flow rates at multiple future moments; a dust concentration prediction module, configured to predict a dust concentration sequence at the target measurement point based on the real-time dust concentration value and the transport parameter set, comprising: selecting a target prediction function that matches the target measurement point from a plurality of preset dust concentration prediction functions, determining parameter values ​​of associated parameters in the target prediction function based on spatial characteristics of the target measurement point and the transport parameter set, and predicting a dust concentration sequence at the target measurement point based on the real-time dust concentration value, the transport parameter set, and the target prediction function having determined parameter values ​​of the associated parameters, wherein the dust concentration sequence includes predicted dust concentration values ​​at multiple future moments; The parameter adjustment module is used to detect whether there is a dust concentration prediction value exceeding a preset dust concentration threshold in the dust concentration sequence; if so, adjust the transportation parameter set so that the dust concentration prediction values ​​in the dust concentration sequence formed based on the adjusted transportation parameter set do not exceed the dust concentration threshold.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium stores executable instructions, which, when executed by a processor, enable the processor to perform the method according to any one of claims 1 to 6.

9. An electronic device, characterized in that: include: one or more processors; A memory for storing one or more programs, which, when executed by the one or more processors, causes the one or more processors to perform the method according to any one of claims 1 to 6.

Images